[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-amc-run-video-calibration":3,"mdc-xcnii0-key":34,"related-repo-nvidia-amc-run-video-calibration":3371,"related-org-nvidia-amc-run-video-calibration":3466},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"amc-run-video-calibration","calibrate video datasets with AutoMagicCalib","Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on these videos', or similar. For RTSP\u002Flive streams, use amc-run-rtsp-calibration instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,17,20],{"name":13,"slug":14,"type":15},"Automation","automation","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Imaging","imaging",{"name":21,"slug":22,"type":15},"Video","video",2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-17T05:28:53.905004","Apache-2.0",281,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"AI agent skills published by NVIDIA","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Famc-run-video-calibration","---\nname: \"amc-run-video-calibration\"\ndescription: \"Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on these videos', or similar. For RTSP\u002Flive streams, use amc-run-rtsp-calibration instead.\"\nowner: \"NVIDIA CORPORATION\"\nservice: \"auto-magic-calib\"\nversion: \"1.0.0\"\nreviewed: \"2026-04-28\"\nlicense: \"Apache-2.0\"\nmetadata:\n  author: \"NVIDIA CORPORATION\"\n  tags: [amc, calibration, rest-api, camera, python]\n---\n\n# Skill: Calibrate from Video Files\n\n## When to Use This Skill\n\nActivate this skill when the user has pre-recorded MP4 files and wants to calibrate them via the AMC REST API. Typical prompts:\n\n- \"calibrate my videos\" \u002F \"run AMC on these videos\"\n- \"calibrate from video files\"\n\nDrives calibration through the REST API on user-supplied **pre-recorded MP4 files** — no CLI scripts or Docker bind-mounts required, just a running microservice and your files.\n\nDo not use this skill for live RTSP streams or `rtsp:\u002F\u002F...` URLs; route those requests to `skills\u002Famc-run-rtsp-calibration\u002FSKILL.md`.\n\n## Prerequisites\n\n- [ ] AMC microservice **and** UI running (follow `skills\u002Famc-setup-calibration-stack\u002FSKILL.md`)\n- [ ] You know the microservice URL (e.g. `http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>`) and UI URL\n- [ ] Video files locally as `cam_00.mp4`, `cam_01.mp4`, … time-synchronized, ~1920×1080\n- [ ] Python 3 with `requests`\n\n## Data Privacy\n\nVideo files uploaded via this skill are transmitted to the AutoMagicCalib backend (REST endpoint). Only use this skill when the backend is deployed on a trusted platform \u002F network.\n\n## What to Ask the User\n\n### Required\n(Video-file naming and the microservice URL are specified under Prerequisites above — collect the inputs below.)\n1. **Videos directory** — the folder the skill globs for `cam_*.mp4`, uploaded sorted alphabetically.\n2. **Microservice URL**\n3. **Project name** — short descriptive string\n\n### Auto-Detected (ask only if not found)\n\nThe script searches the videos dir, its first-level subdirectories, and its parent. If exactly one match is found, it is used; otherwise the script prints the searched locations and continues to explicit path or UI fallback:\n\n| File | Candidate filenames | UI fallback |\n|---|---|---|\n| Calibration settings | `settings.json`, `config.json`, `calibration_config.json` | UI Step 3: Parameters |\n| Alignment JSON | `alignment_data.json` | UI Step 4: Alignment |\n| Layout PNG | `layout.png` | UI Step 4: Alignment |\n\nPosting the settings file replaces UI Step 3 and may pin the detector (`resnet`\u002F`transformer`), which is passed to `\u002Fcalibrate` separately — see Step 4.\n\n### Optional\n4. **Ground truth zip** — `GT.zip` with `_World_Cameras_Camera_XX\u002F` folders (enables evaluation metrics)\n5. **Focal lengths** — one per camera, e.g. `1269.0, 1099.5, 1099.5`\n6. **Detector type** — `resnet` (default, fast) or `transformer` (slower, better under occlusion)\n7. **Run VGGT refinement?** — if VGGT is ready after AMC completes, ask the user whether to run refinement (see setup skill)\n\nSee root `README.md` \"Custom Dataset\" section for input-video guidelines and ground-truth format.\n\n---\n\n## Instructions\n\nAll endpoints below are implemented end-to-end in the [Complete Python Script](#complete-python-script) — the prose is the workflow plus the decisions the agent must make; the script is the authoritative runnable.\n\n### Step 1 — Create Project\n\n`POST \u002Fv1\u002Fcreate_project` (form field `project_name`) → save the returned `project_id`.\n\n### Step 2 — Upload Videos (required)\n\n`POST \u002Fv1\u002Fupload_video_files\u002F\u003Cproject_id>` (multipart `files`). **Upload sorted alphabetically** — the server assigns camera indices by upload order.\n\n### Step 3 — Resolve Local Files (Auto-Scan, Ask, or UI)\n\nFor each of calibration-settings, alignment, and layout, run this resolution:\n\n1. **Auto-scan** `VIDEO_DIR`, one level of subdirectories under `VIDEO_DIR`, and `VIDEO_DIR.parent` for the candidate filenames (table above).\n2. If **exactly one match**, use it and print what was found.\n3. If **zero or multiple matches**, print the searched locations, then ask the user for an explicit path using the host's question mechanism; if none is available, ask in chat and wait. If they don't have the file, mark it for UI fallback.\n4. **UI fallback**: tell the user to complete the corresponding UI step; wait for confirmation; for alignment\u002Flayout also verify files landed in `projects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F`.\n\n### Step 4 — Upload Resolved Files\n\nUpload each file resolved locally:\n\n| File | Endpoint | Notes |\n|---|---|---|\n| Calibration settings | `POST \u002Fv1\u002Fconfig\u002F\u003Cproject_id>` (JSON, posted as-is) | Replaces UI Step 3 (rectification, bundle-adjustment, evaluation, detector, …). Non-2xx is surfaced — never silently fall back. Skip on the UI-fallback path. |\n| Alignment | `POST \u002Fv1\u002Fupload_alignment\u002F\u003Cproject_id>` (`alignment_data.json`) | |\n| Layout | `POST \u002Fv1\u002Fupload_layout\u002F\u003Cproject_id>` (`layout.png`) | |\n| Ground truth (optional) | `POST \u002Fv1\u002Fupload_gt_file\u002F\u003Cproject_id>` (`GT.zip`) | Enables evaluation metrics |\n| Focal lengths (optional) | `POST \u002Fv1\u002Fupload_focal_length\u002F\u003Cproject_id>` (repeated `focal_length=`) | Overrides GeoCalib estimates |\n\nAfter a successful settings POST, parse the file for `\"detector\"` \u002F `\"detector_type\"` — if it's `\"resnet\"` or `\"transformer\"`, use that value for the `\u002Fcalibrate` call in Step 7 (detector is a separate API parameter, not consumed by `\u002Fconfig`).\n\n### Step 5 — UI Fallback (only for files the user doesn't have locally)\n\nIf any of settings \u002F alignment \u002F layout was not resolved in Step 3, direct the user to the appropriate UI step:\n\n- **Settings missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 3: Parameters**, tune via the settings dialog (or accept defaults), click Save.\" **Also**: before the `\u002Fcalibrate` call, ask the user which detector to use (`resnet` or `transformer`) using the host's question mechanism; if none is available, ask in chat and wait. UI Step 3 does not cover detector choice.\n- **Alignment or layout missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 4: Alignment**, upload layout, mark correspondence points, click Save.\"\n\nWait for user confirmation. For non-interactive script runs, provide the needed files up front; the script exits with a clear message rather than waiting on input. For alignment\u002Flayout, verify on disk before continuing:\n\n```bash\n: \"${REPO_ROOT:?set REPO_ROOT to the auto-magic-calib checkout. Run amc-setup-calibration-stack Step 0b first.}\"\ngrep -q \"AutoMagicCalib\" \"$REPO_ROOT\u002FREADME.md\" 2>\u002Fdev\u002Fnull && grep -q \"auto-magic-calib-ms\" \"$REPO_ROOT\u002Fcompose\u002Fms\u002Fcompose.yml\" 2>\u002Fdev\u002Fnull || { echo \"ERROR: REPO_ROOT is not an auto-magic-calib checkout: $REPO_ROOT\" >&2; exit 1; }\n# Resolve PROJECT_DIR from the Compose environment file (default: projects\u002F at repo root).\nCOMPOSE_ENV_BASENAME=\"env\"\nCOMPOSE_ENV_FILE=\"$REPO_ROOT\u002Fcompose\u002F.${COMPOSE_ENV_BASENAME}\"\nPROJECT_DIR_REL=$(grep ^PROJECT_DIR \"$COMPOSE_ENV_FILE\" 2>\u002Fdev\u002Fnull | cut -d= -f2 | tr -d '[:space:]')\nHOST_PROJECTS=$(cd \"$REPO_ROOT\u002Fcompose\" && realpath \"${PROJECT_DIR_REL:-..\u002F..\u002Fprojects}\")\n\nls \"$HOST_PROJECTS\u002Fproject_\u003Cproject_id>\u002Fmanual_adjustment\u002F\"\n# Expected: alignment_data.json, layout.png\n```\n\n### Step 6 — Verify Project\n\n`POST \u002Fv1\u002Fverify_project\u002F\u003Cproject_id>` → must return `{\"project_state\": \"READY\"}` before calibrating.\n\n### Step 7 — Start Calibration\n\n**Confirm the plan before calibrating.** Whether the settings file and detector were auto-detected or asked, present a short summary and get explicit user confirmation before `POST \u002Fcalibrate` using the host's question mechanism; if none is available, ask in chat and wait. The resolved values are the defaults, so confirming is one click, but the user can switch the detector or skip an auto-detected settings file. The standalone Python script prints the same plan and prompts only when stdin is interactive. Summarize:\n\n- **Detector** — `resnet` or `transformer` (the value to be sent).\n- **Calibration settings** — the file being applied (path), or \"defaults\" if none.\n- **Optional overrides** — ground-truth zip and focal lengths, if any.\n\n```\nPOST \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n{\"detector_type\": \"resnet\"}\n```\n\n### Step 8 — Poll for Completion\n\n`GET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>` every 10 s — `project_info.project_state` goes `RUNNING` → `COMPLETED` (or `ERROR`, pull the log). Typical time: **10–60 min** depending on video length and detector.\n\n### Step 9 — Get Results\n\n`GET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Fevaluation_statistics` (only if GT was uploaded; includes `Average L2 distance(m)` and `Average reprojection error 0(px)`), and `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog` for the calibration log.\n\n### Status Fields from `get_project_info`\n\n`project_info.project_state` is the AMC calibration lifecycle for the project: `RUNNING` → `COMPLETED` (or `ERROR`).\n\n`project_info.vggt_state` is also **per-project**, a project-scoped VGGT refinement lifecycle rather than a direct global service or model-load status. A newly created project can report `vggt_state: \"INIT\"` even when the VGGT model is present and mounted. The expected VGGT lifecycle is `INIT` → `READY` after AMC calibration completes → `RUNNING` while VGGT refinement runs → `COMPLETED` (or `ERROR`).\n\nUse `vggt_state == \"READY\"` only as the gate for optional VGGT refinement in Step 10. Interpret `INIT` on a new or uncalibrated project as normal project state. If AMC calibration is complete and the project remains in a non-ready VGGT state, confirm VGGT setup and model availability with the setup skill checks and service logs.\n\n### Step 10 — (Optional) VGGT Refinement\n\nAfter AMC calibration completes, read `vggt_state` from `GET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>`.\n\n- If the project reports `vggt_state == \"READY\"`, ask the user whether to run VGGT refinement using the host's question mechanism; if none is available, ask in chat and wait.\n- If the user confirms, `POST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F\u003Cproject_id>`, poll `vggt_state` via `get_project_info`, then `GET \u002Fv1\u002Fvggt_results\u002F\u003Cproject_id>\u002Fevaluation_statistics`.\n- If VGGT is not ready, skip refinement and explain that the user can set up VGGT with `amc-setup-calibration-stack` and rerun this optional step later.\n\nThe standalone Python script prompts only when stdin is interactive. In non-interactive runs, set `RUN_VGGT = True` to opt in; otherwise the script prints that VGGT is ready and continues without blocking.\n\n---\n\n## Complete Python Script\n\nUse the bundled script from the `amc-run-video-calibration` skill package, not from the `auto-magic-calib` repo root. If the user points the agent at this skill folder directly instead of installing it, set `AMC_VIDEO_SKILL_DIR` to the directory containing this `SKILL.md`, or run the command from that directory. Set `BASE_URL`, `PROJECT_NAME`, and `VIDEO_DIR`; optional env vars are `CONFIG_FILE`, `ALIGNMENT_JSON`, `LAYOUT_PNG`, `GT_ZIP`, `FOCAL_LENGTHS`, `DETECTOR_TYPE`, `RUN_VGGT`, `REPO_ROOT`, and `PROJECTS_DIR`. The script implements UI fallback, plan confirmation, VGGT prompt\u002Fopt-in behavior, polling, and refined statistics retrieval.\n\n```bash\n# Optional but recommended: REPO_ROOT points to the auto-magic-calib checkout.\n# PROJECTS_DIR can be set explicitly when project outputs live elsewhere.\nif [ -z \"${DEEPSTREAM_REPO_ROOT:-}\" ] && [ -n \"${REPO_ROOT:-}\" ] && [ -d \"$REPO_ROOT\u002F..\u002F..\u002Fskills\u002Famc-run-video-calibration\" ]; then\n  DEEPSTREAM_REPO_ROOT=\"$(cd \"$REPO_ROOT\u002F..\u002F..\" && pwd)\"\nfi\n\nSCRIPT_PATH=\"\"\nfor candidate in \\\n  \"${AMC_VIDEO_SKILL_DIR:+$AMC_VIDEO_SKILL_DIR\u002Fscripts\u002Frun_video_calibration.py}\" \\\n  \"$PWD\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"${DEEPSTREAM_REPO_ROOT:+$DEEPSTREAM_REPO_ROOT\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py}\" \\\n  \"$PWD\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.claude\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.codex\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.cursor\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\"; do\n  if [ -f \"$candidate\" ]; then\n    SCRIPT_PATH=\"$candidate\"\n    break\n  fi\ndone\n\n[ -n \"$SCRIPT_PATH\" ] || {\n  echo \"ERROR: could not find amc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" >&2\n  echo \"Set AMC_VIDEO_SKILL_DIR to the amc-run-video-calibration skill directory, or run this block from that directory.\" >&2\n  exit 1\n}\n\npython3 \"$SCRIPT_PATH\"\n```\n\n## Success Criteria\n\n- `project_state == \"COMPLETED\"` after polling.\n- If manual alignment was used: `projects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` contains `alignment_data.json` + `layout.png`.\n- If GT was uploaded: evaluation returns typical thresholds:\n  - `Average L2 distance(m)` \u003C 1.5\n  - `Average reprojection error 0(px)` \u003C 5\n- No `ERROR` state.\n\n## Key Output Files (on server)\n\n```\nprojects\u002Fproject_\u003Cproject_id>\u002F\n├── manual_adjustment\u002F\n│   ├── alignment_data.json\n│   └── layout.png\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba\u002F\n│       ├── initial\u002FcamInfo_XX.yaml\n│       └── refined\u002FcamInfo_XX.yaml          # ← final calibration\n└── calibration.log\n```\n\n## Troubleshooting\n\n| Issue | Fix |\n|---|---|\n| `verify_project` state not `READY` | Confirm videos uploaded and alignment + layout are present (either via API or via UI manual alignment) |\n| Manual alignment files missing after UI step | User didn't click Save; also verify `projects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` exists |\n| Calibration stuck `RUNNING` > 90 min | `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` — usually insufficient tracklets (scene too static). See \"Custom Dataset\" guidelines in root README. |\n| Immediate `ERROR` state | Check video naming: must be `cam_00.mp4`, `cam_01.mp4`, … contiguous |\n| Low L2 but high reprojection | Provide explicit `focal_length` override via Step 3 |\n| VGGT stays non-ready after AMC completes | `INIT` is expected for a new project. After AMC calibration reaches `COMPLETED`, the project should transition to `READY` before optional VGGT refinement when VGGT is configured. If refinement is required and the state remains `INIT` or otherwise non-ready, confirm VGGT setup and model availability with setup skill Step 2 and MS logs. |\n| Upload timeout | Large videos — bump `timeout=300` to e.g. `600` in the script |\n\n## For Downstream Skills — MV3DT Export\n\nA downstream Multi-View 3D Tracking skill fetches the MV3DT-format calibration directly from the microservice (this skill does **not** download it; it returns the `project_id`). After this skill reports `COMPLETED`:\n\n- `GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc` → `mv3dt_output.zip` (contains `transforms.yml`).\n- If VGGT ran to `COMPLETED` (Step 10): `?result_type=vggt` → `vggt_mv3dt_output.zip`.\n\n## Related Skills\n\n- `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` — start MS + UI first.\n- `skills\u002Famc-run-sample-calibration\u002FSKILL.md` — verify the stack with the bundled sample before trying your own.\n- `skills\u002Famc-run-rtsp-calibration\u002FSKILL.md` — same calibration tail, but sourcing footage from live RTSP streams through VIOS.\n\nRoot `README.md` \"Custom Dataset\" and \"Calibration Workflow (UI)\" sections document input-video guidelines and the UI-driven alternative to this API flow.\n\n\u003C!-- signing marker -->\n",{"data":35,"body":47},{"name":4,"description":6,"owner":36,"service":37,"version":38,"reviewed":39,"license":26,"metadata":40},"NVIDIA CORPORATION","auto-magic-calib","1.0.0","2026-04-28",{"author":36,"tags":41},[42,43,44,45,46],"amc","calibration","rest-api","camera","python",{"type":48,"children":49},"root",[50,59,66,72,87,100,122,128,218,224,229,235,242,247,287,293,298,410,439,445,524,537,541,547,561,567,593,599,625,631,636,711,717,722,886,938,944,949,1026,1031,1616,1622,1641,1647,1665,1709,1719,1725,1775,1781,1816,1828,1856,1916,1936,1942,1961,2023,2036,2039,2044,2163,2908,2914,2993,2999,3008,3014,3228,3234,3259,3313,3319,3353,3365],{"type":51,"tag":52,"props":53,"children":55},"element","h1",{"id":54},"skill-calibrate-from-video-files",[56],{"type":57,"value":58},"text","Skill: Calibrate from Video Files",{"type":51,"tag":60,"props":61,"children":63},"h2",{"id":62},"when-to-use-this-skill",[64],{"type":57,"value":65},"When to Use This Skill",{"type":51,"tag":67,"props":68,"children":69},"p",{},[70],{"type":57,"value":71},"Activate this skill when the user has pre-recorded MP4 files and wants to calibrate them via the AMC REST API. Typical prompts:",{"type":51,"tag":73,"props":74,"children":75},"ul",{},[76,82],{"type":51,"tag":77,"props":78,"children":79},"li",{},[80],{"type":57,"value":81},"\"calibrate my videos\" \u002F \"run AMC on these videos\"",{"type":51,"tag":77,"props":83,"children":84},{},[85],{"type":57,"value":86},"\"calibrate from video files\"",{"type":51,"tag":67,"props":88,"children":89},{},[90,92,98],{"type":57,"value":91},"Drives calibration through the REST API on user-supplied ",{"type":51,"tag":93,"props":94,"children":95},"strong",{},[96],{"type":57,"value":97},"pre-recorded MP4 files",{"type":57,"value":99}," — no CLI scripts or Docker bind-mounts required, just a running microservice and your files.",{"type":51,"tag":67,"props":101,"children":102},{},[103,105,112,114,120],{"type":57,"value":104},"Do not use this skill for live RTSP streams or ",{"type":51,"tag":106,"props":107,"children":109},"code",{"className":108},[],[110],{"type":57,"value":111},"rtsp:\u002F\u002F...",{"type":57,"value":113}," URLs; route those requests to ",{"type":51,"tag":106,"props":115,"children":117},{"className":116},[],[118],{"type":57,"value":119},"skills\u002Famc-run-rtsp-calibration\u002FSKILL.md",{"type":57,"value":121},".",{"type":51,"tag":60,"props":123,"children":125},{"id":124},"prerequisites",[126],{"type":57,"value":127},"Prerequisites",{"type":51,"tag":73,"props":129,"children":132},{"className":130},[131],"contains-task-list",[133,161,178,203],{"type":51,"tag":77,"props":134,"children":137},{"className":135},[136],"task-list-item",[138,144,146,151,153,159],{"type":51,"tag":139,"props":140,"children":143},"input",{"disabled":141,"type":142},true,"checkbox",[],{"type":57,"value":145}," AMC microservice ",{"type":51,"tag":93,"props":147,"children":148},{},[149],{"type":57,"value":150},"and",{"type":57,"value":152}," UI running (follow ",{"type":51,"tag":106,"props":154,"children":156},{"className":155},[],[157],{"type":57,"value":158},"skills\u002Famc-setup-calibration-stack\u002FSKILL.md",{"type":57,"value":160},")",{"type":51,"tag":77,"props":162,"children":164},{"className":163},[136],[165,168,170,176],{"type":51,"tag":139,"props":166,"children":167},{"disabled":141,"type":142},[],{"type":57,"value":169}," You know the microservice URL (e.g. ",{"type":51,"tag":106,"props":171,"children":173},{"className":172},[],[174],{"type":57,"value":175},"http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>",{"type":57,"value":177},") and UI URL",{"type":51,"tag":77,"props":179,"children":181},{"className":180},[136],[182,185,187,193,195,201],{"type":51,"tag":139,"props":183,"children":184},{"disabled":141,"type":142},[],{"type":57,"value":186}," Video files locally as ",{"type":51,"tag":106,"props":188,"children":190},{"className":189},[],[191],{"type":57,"value":192},"cam_00.mp4",{"type":57,"value":194},", ",{"type":51,"tag":106,"props":196,"children":198},{"className":197},[],[199],{"type":57,"value":200},"cam_01.mp4",{"type":57,"value":202},", … time-synchronized, ~1920×1080",{"type":51,"tag":77,"props":204,"children":206},{"className":205},[136],[207,210,212],{"type":51,"tag":139,"props":208,"children":209},{"disabled":141,"type":142},[],{"type":57,"value":211}," Python 3 with ",{"type":51,"tag":106,"props":213,"children":215},{"className":214},[],[216],{"type":57,"value":217},"requests",{"type":51,"tag":60,"props":219,"children":221},{"id":220},"data-privacy",[222],{"type":57,"value":223},"Data Privacy",{"type":51,"tag":67,"props":225,"children":226},{},[227],{"type":57,"value":228},"Video files uploaded via this skill are transmitted to the AutoMagicCalib backend (REST endpoint). Only use this skill when the backend is deployed on a trusted platform \u002F network.",{"type":51,"tag":60,"props":230,"children":232},{"id":231},"what-to-ask-the-user",[233],{"type":57,"value":234},"What to Ask the User",{"type":51,"tag":236,"props":237,"children":239},"h3",{"id":238},"required",[240],{"type":57,"value":241},"Required",{"type":51,"tag":67,"props":243,"children":244},{},[245],{"type":57,"value":246},"(Video-file naming and the microservice URL are specified under Prerequisites above — collect the inputs below.)",{"type":51,"tag":248,"props":249,"children":250},"ol",{},[251,269,277],{"type":51,"tag":77,"props":252,"children":253},{},[254,259,261,267],{"type":51,"tag":93,"props":255,"children":256},{},[257],{"type":57,"value":258},"Videos directory",{"type":57,"value":260}," — the folder the skill globs for ",{"type":51,"tag":106,"props":262,"children":264},{"className":263},[],[265],{"type":57,"value":266},"cam_*.mp4",{"type":57,"value":268},", uploaded sorted alphabetically.",{"type":51,"tag":77,"props":270,"children":271},{},[272],{"type":51,"tag":93,"props":273,"children":274},{},[275],{"type":57,"value":276},"Microservice URL",{"type":51,"tag":77,"props":278,"children":279},{},[280,285],{"type":51,"tag":93,"props":281,"children":282},{},[283],{"type":57,"value":284},"Project name",{"type":57,"value":286}," — short descriptive string",{"type":51,"tag":236,"props":288,"children":290},{"id":289},"auto-detected-ask-only-if-not-found",[291],{"type":57,"value":292},"Auto-Detected (ask only if not found)",{"type":51,"tag":67,"props":294,"children":295},{},[296],{"type":57,"value":297},"The script searches the videos dir, its first-level subdirectories, and its parent. If exactly one match is found, it is used; otherwise the script prints the searched locations and continues to explicit path or UI fallback:",{"type":51,"tag":299,"props":300,"children":301},"table",{},[302,326],{"type":51,"tag":303,"props":304,"children":305},"thead",{},[306],{"type":51,"tag":307,"props":308,"children":309},"tr",{},[310,316,321],{"type":51,"tag":311,"props":312,"children":313},"th",{},[314],{"type":57,"value":315},"File",{"type":51,"tag":311,"props":317,"children":318},{},[319],{"type":57,"value":320},"Candidate filenames",{"type":51,"tag":311,"props":322,"children":323},{},[324],{"type":57,"value":325},"UI fallback",{"type":51,"tag":327,"props":328,"children":329},"tbody",{},[330,367,389],{"type":51,"tag":307,"props":331,"children":332},{},[333,339,362],{"type":51,"tag":334,"props":335,"children":336},"td",{},[337],{"type":57,"value":338},"Calibration settings",{"type":51,"tag":334,"props":340,"children":341},{},[342,348,349,355,356],{"type":51,"tag":106,"props":343,"children":345},{"className":344},[],[346],{"type":57,"value":347},"settings.json",{"type":57,"value":194},{"type":51,"tag":106,"props":350,"children":352},{"className":351},[],[353],{"type":57,"value":354},"config.json",{"type":57,"value":194},{"type":51,"tag":106,"props":357,"children":359},{"className":358},[],[360],{"type":57,"value":361},"calibration_config.json",{"type":51,"tag":334,"props":363,"children":364},{},[365],{"type":57,"value":366},"UI Step 3: Parameters",{"type":51,"tag":307,"props":368,"children":369},{},[370,375,384],{"type":51,"tag":334,"props":371,"children":372},{},[373],{"type":57,"value":374},"Alignment JSON",{"type":51,"tag":334,"props":376,"children":377},{},[378],{"type":51,"tag":106,"props":379,"children":381},{"className":380},[],[382],{"type":57,"value":383},"alignment_data.json",{"type":51,"tag":334,"props":385,"children":386},{},[387],{"type":57,"value":388},"UI Step 4: Alignment",{"type":51,"tag":307,"props":390,"children":391},{},[392,397,406],{"type":51,"tag":334,"props":393,"children":394},{},[395],{"type":57,"value":396},"Layout PNG",{"type":51,"tag":334,"props":398,"children":399},{},[400],{"type":51,"tag":106,"props":401,"children":403},{"className":402},[],[404],{"type":57,"value":405},"layout.png",{"type":51,"tag":334,"props":407,"children":408},{},[409],{"type":57,"value":388},{"type":51,"tag":67,"props":411,"children":412},{},[413,415,421,423,429,431,437],{"type":57,"value":414},"Posting the settings file replaces UI Step 3 and may pin the detector (",{"type":51,"tag":106,"props":416,"children":418},{"className":417},[],[419],{"type":57,"value":420},"resnet",{"type":57,"value":422},"\u002F",{"type":51,"tag":106,"props":424,"children":426},{"className":425},[],[427],{"type":57,"value":428},"transformer",{"type":57,"value":430},"), which is passed to ",{"type":51,"tag":106,"props":432,"children":434},{"className":433},[],[435],{"type":57,"value":436},"\u002Fcalibrate",{"type":57,"value":438}," separately — see Step 4.",{"type":51,"tag":236,"props":440,"children":442},{"id":441},"optional",[443],{"type":57,"value":444},"Optional",{"type":51,"tag":248,"props":446,"children":448},{"start":447},4,[449,475,491,514],{"type":51,"tag":77,"props":450,"children":451},{},[452,457,459,465,467,473],{"type":51,"tag":93,"props":453,"children":454},{},[455],{"type":57,"value":456},"Ground truth zip",{"type":57,"value":458}," — ",{"type":51,"tag":106,"props":460,"children":462},{"className":461},[],[463],{"type":57,"value":464},"GT.zip",{"type":57,"value":466}," with ",{"type":51,"tag":106,"props":468,"children":470},{"className":469},[],[471],{"type":57,"value":472},"_World_Cameras_Camera_XX\u002F",{"type":57,"value":474}," folders (enables evaluation metrics)",{"type":51,"tag":77,"props":476,"children":477},{},[478,483,485],{"type":51,"tag":93,"props":479,"children":480},{},[481],{"type":57,"value":482},"Focal lengths",{"type":57,"value":484}," — one per camera, e.g. ",{"type":51,"tag":106,"props":486,"children":488},{"className":487},[],[489],{"type":57,"value":490},"1269.0, 1099.5, 1099.5",{"type":51,"tag":77,"props":492,"children":493},{},[494,499,500,505,507,512],{"type":51,"tag":93,"props":495,"children":496},{},[497],{"type":57,"value":498},"Detector type",{"type":57,"value":458},{"type":51,"tag":106,"props":501,"children":503},{"className":502},[],[504],{"type":57,"value":420},{"type":57,"value":506}," (default, fast) or ",{"type":51,"tag":106,"props":508,"children":510},{"className":509},[],[511],{"type":57,"value":428},{"type":57,"value":513}," (slower, better under occlusion)",{"type":51,"tag":77,"props":515,"children":516},{},[517,522],{"type":51,"tag":93,"props":518,"children":519},{},[520],{"type":57,"value":521},"Run VGGT refinement?",{"type":57,"value":523}," — if VGGT is ready after AMC completes, ask the user whether to run refinement (see setup skill)",{"type":51,"tag":67,"props":525,"children":526},{},[527,529,535],{"type":57,"value":528},"See root ",{"type":51,"tag":106,"props":530,"children":532},{"className":531},[],[533],{"type":57,"value":534},"README.md",{"type":57,"value":536}," \"Custom Dataset\" section for input-video guidelines and ground-truth format.",{"type":51,"tag":538,"props":539,"children":540},"hr",{},[],{"type":51,"tag":60,"props":542,"children":544},{"id":543},"instructions",[545],{"type":57,"value":546},"Instructions",{"type":51,"tag":67,"props":548,"children":549},{},[550,552,559],{"type":57,"value":551},"All endpoints below are implemented end-to-end in the ",{"type":51,"tag":553,"props":554,"children":556},"a",{"href":555},"#complete-python-script",[557],{"type":57,"value":558},"Complete Python Script",{"type":57,"value":560}," — the prose is the workflow plus the decisions the agent must make; the script is the authoritative runnable.",{"type":51,"tag":236,"props":562,"children":564},{"id":563},"step-1-create-project",[565],{"type":57,"value":566},"Step 1 — Create Project",{"type":51,"tag":67,"props":568,"children":569},{},[570,576,578,584,586,592],{"type":51,"tag":106,"props":571,"children":573},{"className":572},[],[574],{"type":57,"value":575},"POST \u002Fv1\u002Fcreate_project",{"type":57,"value":577}," (form field ",{"type":51,"tag":106,"props":579,"children":581},{"className":580},[],[582],{"type":57,"value":583},"project_name",{"type":57,"value":585},") → save the returned ",{"type":51,"tag":106,"props":587,"children":589},{"className":588},[],[590],{"type":57,"value":591},"project_id",{"type":57,"value":121},{"type":51,"tag":236,"props":594,"children":596},{"id":595},"step-2-upload-videos-required",[597],{"type":57,"value":598},"Step 2 — Upload Videos (required)",{"type":51,"tag":67,"props":600,"children":601},{},[602,608,610,616,618,623],{"type":51,"tag":106,"props":603,"children":605},{"className":604},[],[606],{"type":57,"value":607},"POST \u002Fv1\u002Fupload_video_files\u002F\u003Cproject_id>",{"type":57,"value":609}," (multipart ",{"type":51,"tag":106,"props":611,"children":613},{"className":612},[],[614],{"type":57,"value":615},"files",{"type":57,"value":617},"). ",{"type":51,"tag":93,"props":619,"children":620},{},[621],{"type":57,"value":622},"Upload sorted alphabetically",{"type":57,"value":624}," — the server assigns camera indices by upload order.",{"type":51,"tag":236,"props":626,"children":628},{"id":627},"step-3-resolve-local-files-auto-scan-ask-or-ui",[629],{"type":57,"value":630},"Step 3 — Resolve Local Files (Auto-Scan, Ask, or UI)",{"type":51,"tag":67,"props":632,"children":633},{},[634],{"type":57,"value":635},"For each of calibration-settings, alignment, and layout, run this resolution:",{"type":51,"tag":248,"props":637,"children":638},{},[639,672,684,695],{"type":51,"tag":77,"props":640,"children":641},{},[642,647,649,655,657,662,664,670],{"type":51,"tag":93,"props":643,"children":644},{},[645],{"type":57,"value":646},"Auto-scan",{"type":57,"value":648}," ",{"type":51,"tag":106,"props":650,"children":652},{"className":651},[],[653],{"type":57,"value":654},"VIDEO_DIR",{"type":57,"value":656},", one level of subdirectories under ",{"type":51,"tag":106,"props":658,"children":660},{"className":659},[],[661],{"type":57,"value":654},{"type":57,"value":663},", and ",{"type":51,"tag":106,"props":665,"children":667},{"className":666},[],[668],{"type":57,"value":669},"VIDEO_DIR.parent",{"type":57,"value":671}," for the candidate filenames (table above).",{"type":51,"tag":77,"props":673,"children":674},{},[675,677,682],{"type":57,"value":676},"If ",{"type":51,"tag":93,"props":678,"children":679},{},[680],{"type":57,"value":681},"exactly one match",{"type":57,"value":683},", use it and print what was found.",{"type":51,"tag":77,"props":685,"children":686},{},[687,688,693],{"type":57,"value":676},{"type":51,"tag":93,"props":689,"children":690},{},[691],{"type":57,"value":692},"zero or multiple matches",{"type":57,"value":694},", print the searched locations, then ask the user for an explicit path using the host's question mechanism; if none is available, ask in chat and wait. If they don't have the file, mark it for UI fallback.",{"type":51,"tag":77,"props":696,"children":697},{},[698,702,704,710],{"type":51,"tag":93,"props":699,"children":700},{},[701],{"type":57,"value":325},{"type":57,"value":703},": tell the user to complete the corresponding UI step; wait for confirmation; for alignment\u002Flayout also verify files landed in ",{"type":51,"tag":106,"props":705,"children":707},{"className":706},[],[708],{"type":57,"value":709},"projects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F",{"type":57,"value":121},{"type":51,"tag":236,"props":712,"children":714},{"id":713},"step-4-upload-resolved-files",[715],{"type":57,"value":716},"Step 4 — Upload Resolved Files",{"type":51,"tag":67,"props":718,"children":719},{},[720],{"type":57,"value":721},"Upload each file resolved locally:",{"type":51,"tag":299,"props":723,"children":724},{},[725,745],{"type":51,"tag":303,"props":726,"children":727},{},[728],{"type":51,"tag":307,"props":729,"children":730},{},[731,735,740],{"type":51,"tag":311,"props":732,"children":733},{},[734],{"type":57,"value":315},{"type":51,"tag":311,"props":736,"children":737},{},[738],{"type":57,"value":739},"Endpoint",{"type":51,"tag":311,"props":741,"children":742},{},[743],{"type":57,"value":744},"Notes",{"type":51,"tag":327,"props":746,"children":747},{},[748,771,799,826,855],{"type":51,"tag":307,"props":749,"children":750},{},[751,755,766],{"type":51,"tag":334,"props":752,"children":753},{},[754],{"type":57,"value":338},{"type":51,"tag":334,"props":756,"children":757},{},[758,764],{"type":51,"tag":106,"props":759,"children":761},{"className":760},[],[762],{"type":57,"value":763},"POST \u002Fv1\u002Fconfig\u002F\u003Cproject_id>",{"type":57,"value":765}," (JSON, posted as-is)",{"type":51,"tag":334,"props":767,"children":768},{},[769],{"type":57,"value":770},"Replaces UI Step 3 (rectification, bundle-adjustment, evaluation, detector, …). Non-2xx is surfaced — never silently fall back. Skip on the UI-fallback path.",{"type":51,"tag":307,"props":772,"children":773},{},[774,779,796],{"type":51,"tag":334,"props":775,"children":776},{},[777],{"type":57,"value":778},"Alignment",{"type":51,"tag":334,"props":780,"children":781},{},[782,788,790,795],{"type":51,"tag":106,"props":783,"children":785},{"className":784},[],[786],{"type":57,"value":787},"POST \u002Fv1\u002Fupload_alignment\u002F\u003Cproject_id>",{"type":57,"value":789}," (",{"type":51,"tag":106,"props":791,"children":793},{"className":792},[],[794],{"type":57,"value":383},{"type":57,"value":160},{"type":51,"tag":334,"props":797,"children":798},{},[],{"type":51,"tag":307,"props":800,"children":801},{},[802,807,823],{"type":51,"tag":334,"props":803,"children":804},{},[805],{"type":57,"value":806},"Layout",{"type":51,"tag":334,"props":808,"children":809},{},[810,816,817,822],{"type":51,"tag":106,"props":811,"children":813},{"className":812},[],[814],{"type":57,"value":815},"POST \u002Fv1\u002Fupload_layout\u002F\u003Cproject_id>",{"type":57,"value":789},{"type":51,"tag":106,"props":818,"children":820},{"className":819},[],[821],{"type":57,"value":405},{"type":57,"value":160},{"type":51,"tag":334,"props":824,"children":825},{},[],{"type":51,"tag":307,"props":827,"children":828},{},[829,834,850],{"type":51,"tag":334,"props":830,"children":831},{},[832],{"type":57,"value":833},"Ground truth (optional)",{"type":51,"tag":334,"props":835,"children":836},{},[837,843,844,849],{"type":51,"tag":106,"props":838,"children":840},{"className":839},[],[841],{"type":57,"value":842},"POST \u002Fv1\u002Fupload_gt_file\u002F\u003Cproject_id>",{"type":57,"value":789},{"type":51,"tag":106,"props":845,"children":847},{"className":846},[],[848],{"type":57,"value":464},{"type":57,"value":160},{"type":51,"tag":334,"props":851,"children":852},{},[853],{"type":57,"value":854},"Enables evaluation metrics",{"type":51,"tag":307,"props":856,"children":857},{},[858,863,881],{"type":51,"tag":334,"props":859,"children":860},{},[861],{"type":57,"value":862},"Focal lengths (optional)",{"type":51,"tag":334,"props":864,"children":865},{},[866,872,874,880],{"type":51,"tag":106,"props":867,"children":869},{"className":868},[],[870],{"type":57,"value":871},"POST \u002Fv1\u002Fupload_focal_length\u002F\u003Cproject_id>",{"type":57,"value":873}," (repeated ",{"type":51,"tag":106,"props":875,"children":877},{"className":876},[],[878],{"type":57,"value":879},"focal_length=",{"type":57,"value":160},{"type":51,"tag":334,"props":882,"children":883},{},[884],{"type":57,"value":885},"Overrides GeoCalib estimates",{"type":51,"tag":67,"props":887,"children":888},{},[889,891,897,899,905,907,913,915,921,923,928,930,936],{"type":57,"value":890},"After a successful settings POST, parse the file for ",{"type":51,"tag":106,"props":892,"children":894},{"className":893},[],[895],{"type":57,"value":896},"\"detector\"",{"type":57,"value":898}," \u002F ",{"type":51,"tag":106,"props":900,"children":902},{"className":901},[],[903],{"type":57,"value":904},"\"detector_type\"",{"type":57,"value":906}," — if it's ",{"type":51,"tag":106,"props":908,"children":910},{"className":909},[],[911],{"type":57,"value":912},"\"resnet\"",{"type":57,"value":914}," or ",{"type":51,"tag":106,"props":916,"children":918},{"className":917},[],[919],{"type":57,"value":920},"\"transformer\"",{"type":57,"value":922},", use that value for the ",{"type":51,"tag":106,"props":924,"children":926},{"className":925},[],[927],{"type":57,"value":436},{"type":57,"value":929}," call in Step 7 (detector is a separate API parameter, not consumed by ",{"type":51,"tag":106,"props":931,"children":933},{"className":932},[],[934],{"type":57,"value":935},"\u002Fconfig",{"type":57,"value":937},").",{"type":51,"tag":236,"props":939,"children":941},{"id":940},"step-5-ui-fallback-only-for-files-the-user-doesnt-have-locally",[942],{"type":57,"value":943},"Step 5 — UI Fallback (only for files the user doesn't have locally)",{"type":51,"tag":67,"props":945,"children":946},{},[947],{"type":57,"value":948},"If any of settings \u002F alignment \u002F layout was not resolved in Step 3, direct the user to the appropriate UI step:",{"type":51,"tag":73,"props":950,"children":951},{},[952,1004],{"type":51,"tag":77,"props":953,"children":954},{},[955,960,962,968,970,975,977,982,984,989,991,996,997,1002],{"type":51,"tag":93,"props":956,"children":957},{},[958],{"type":57,"value":959},"Settings missing",{"type":57,"value":961}," → \"Open UI project ",{"type":51,"tag":106,"props":963,"children":965},{"className":964},[],[966],{"type":57,"value":967},"\u003Cproject_id>",{"type":57,"value":969},", go to ",{"type":51,"tag":93,"props":971,"children":972},{},[973],{"type":57,"value":974},"Step 3: Parameters",{"type":57,"value":976},", tune via the settings dialog (or accept defaults), click Save.\" ",{"type":51,"tag":93,"props":978,"children":979},{},[980],{"type":57,"value":981},"Also",{"type":57,"value":983},": before the ",{"type":51,"tag":106,"props":985,"children":987},{"className":986},[],[988],{"type":57,"value":436},{"type":57,"value":990}," call, ask the user which detector to use (",{"type":51,"tag":106,"props":992,"children":994},{"className":993},[],[995],{"type":57,"value":420},{"type":57,"value":914},{"type":51,"tag":106,"props":998,"children":1000},{"className":999},[],[1001],{"type":57,"value":428},{"type":57,"value":1003},") using the host's question mechanism; if none is available, ask in chat and wait. UI Step 3 does not cover detector choice.",{"type":51,"tag":77,"props":1005,"children":1006},{},[1007,1012,1013,1018,1019,1024],{"type":51,"tag":93,"props":1008,"children":1009},{},[1010],{"type":57,"value":1011},"Alignment or layout missing",{"type":57,"value":961},{"type":51,"tag":106,"props":1014,"children":1016},{"className":1015},[],[1017],{"type":57,"value":967},{"type":57,"value":969},{"type":51,"tag":93,"props":1020,"children":1021},{},[1022],{"type":57,"value":1023},"Step 4: Alignment",{"type":57,"value":1025},", upload layout, mark correspondence points, click Save.\"",{"type":51,"tag":67,"props":1027,"children":1028},{},[1029],{"type":57,"value":1030},"Wait for user confirmation. For non-interactive script runs, provide the needed files up front; the script exits with a clear message rather than waiting on input. For alignment\u002Flayout, verify on disk before continuing:",{"type":51,"tag":1032,"props":1033,"children":1038},"pre",{"className":1034,"code":1035,"language":1036,"meta":1037,"style":1037},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight",": \"${REPO_ROOT:?set REPO_ROOT to the auto-magic-calib checkout. Run amc-setup-calibration-stack Step 0b first.}\"\ngrep -q \"AutoMagicCalib\" \"$REPO_ROOT\u002FREADME.md\" 2>\u002Fdev\u002Fnull && grep -q \"auto-magic-calib-ms\" \"$REPO_ROOT\u002Fcompose\u002Fms\u002Fcompose.yml\" 2>\u002Fdev\u002Fnull || { echo \"ERROR: REPO_ROOT is not an auto-magic-calib checkout: $REPO_ROOT\" >&2; exit 1; }\n# Resolve PROJECT_DIR from the Compose environment file (default: projects\u002F at repo root).\nCOMPOSE_ENV_BASENAME=\"env\"\nCOMPOSE_ENV_FILE=\"$REPO_ROOT\u002Fcompose\u002F.${COMPOSE_ENV_BASENAME}\"\nPROJECT_DIR_REL=$(grep ^PROJECT_DIR \"$COMPOSE_ENV_FILE\" 2>\u002Fdev\u002Fnull | cut -d= -f2 | tr -d '[:space:]')\nHOST_PROJECTS=$(cd \"$REPO_ROOT\u002Fcompose\" && realpath \"${PROJECT_DIR_REL:-..\u002F..\u002Fprojects}\")\n\nls \"$HOST_PROJECTS\u002Fproject_\u003Cproject_id>\u002Fmanual_adjustment\u002F\"\n# Expected: alignment_data.json, layout.png\n","bash","",[1039],{"type":51,"tag":106,"props":1040,"children":1041},{"__ignoreMap":1037},[1042,1141,1309,1319,1346,1385,1483,1571,1580,1607],{"type":51,"tag":1043,"props":1044,"children":1047},"span",{"class":1045,"line":1046},"line",1,[1048,1054,1060,1066,1071,1076,1081,1086,1091,1096,1101,1107,1112,1117,1122,1127,1132,1136],{"type":51,"tag":1043,"props":1049,"children":1051},{"style":1050},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[1052],{"type":57,"value":1053},":",{"type":51,"tag":1043,"props":1055,"children":1057},{"style":1056},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1058],{"type":57,"value":1059}," \"${",{"type":51,"tag":1043,"props":1061,"children":1063},{"style":1062},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[1064],{"type":57,"value":1065},"REPO_ROOT",{"type":51,"tag":1043,"props":1067,"children":1068},{"style":1056},[1069],{"type":57,"value":1070},":?",{"type":51,"tag":1043,"props":1072,"children":1073},{"style":1062},[1074],{"type":57,"value":1075},"set",{"type":51,"tag":1043,"props":1077,"children":1078},{"style":1062},[1079],{"type":57,"value":1080}," REPO_ROOT",{"type":51,"tag":1043,"props":1082,"children":1083},{"style":1062},[1084],{"type":57,"value":1085}," to",{"type":51,"tag":1043,"props":1087,"children":1088},{"style":1062},[1089],{"type":57,"value":1090}," the",{"type":51,"tag":1043,"props":1092,"children":1093},{"style":1062},[1094],{"type":57,"value":1095}," auto-magic-calib",{"type":51,"tag":1043,"props":1097,"children":1098},{"style":1062},[1099],{"type":57,"value":1100}," checkout",{"type":51,"tag":1043,"props":1102,"children":1104},{"style":1103},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1105],{"type":57,"value":1106},". ",{"type":51,"tag":1043,"props":1108,"children":1109},{"style":1062},[1110],{"type":57,"value":1111},"Run",{"type":51,"tag":1043,"props":1113,"children":1114},{"style":1062},[1115],{"type":57,"value":1116}," amc-setup-calibration-stack",{"type":51,"tag":1043,"props":1118,"children":1119},{"style":1062},[1120],{"type":57,"value":1121}," Step",{"type":51,"tag":1043,"props":1123,"children":1124},{"style":1062},[1125],{"type":57,"value":1126}," 0b",{"type":51,"tag":1043,"props":1128,"children":1129},{"style":1062},[1130],{"type":57,"value":1131}," first",{"type":51,"tag":1043,"props":1133,"children":1134},{"style":1103},[1135],{"type":57,"value":121},{"type":51,"tag":1043,"props":1137,"children":1138},{"style":1056},[1139],{"type":57,"value":1140},"}\"\n",{"type":51,"tag":1043,"props":1142,"children":1144},{"class":1045,"line":1143},2,[1145,1151,1156,1161,1166,1171,1175,1180,1185,1189,1194,1199,1204,1209,1213,1217,1222,1226,1230,1234,1239,1243,1247,1251,1256,1261,1266,1270,1275,1279,1283,1288,1293,1299,1304],{"type":51,"tag":1043,"props":1146,"children":1148},{"style":1147},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1149],{"type":57,"value":1150},"grep",{"type":51,"tag":1043,"props":1152,"children":1153},{"style":1103},[1154],{"type":57,"value":1155}," -q",{"type":51,"tag":1043,"props":1157,"children":1158},{"style":1056},[1159],{"type":57,"value":1160}," \"",{"type":51,"tag":1043,"props":1162,"children":1163},{"style":1103},[1164],{"type":57,"value":1165},"AutoMagicCalib",{"type":51,"tag":1043,"props":1167,"children":1168},{"style":1056},[1169],{"type":57,"value":1170},"\"",{"type":51,"tag":1043,"props":1172,"children":1173},{"style":1056},[1174],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1176,"children":1177},{"style":1062},[1178],{"type":57,"value":1179},"$REPO_ROOT",{"type":51,"tag":1043,"props":1181,"children":1182},{"style":1103},[1183],{"type":57,"value":1184},"\u002FREADME.md",{"type":51,"tag":1043,"props":1186,"children":1187},{"style":1056},[1188],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1190,"children":1191},{"style":1056},[1192],{"type":57,"value":1193}," 2>",{"type":51,"tag":1043,"props":1195,"children":1196},{"style":1103},[1197],{"type":57,"value":1198},"\u002Fdev\u002Fnull",{"type":51,"tag":1043,"props":1200,"children":1201},{"style":1056},[1202],{"type":57,"value":1203}," &&",{"type":51,"tag":1043,"props":1205,"children":1206},{"style":1147},[1207],{"type":57,"value":1208}," grep",{"type":51,"tag":1043,"props":1210,"children":1211},{"style":1103},[1212],{"type":57,"value":1155},{"type":51,"tag":1043,"props":1214,"children":1215},{"style":1056},[1216],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1218,"children":1219},{"style":1103},[1220],{"type":57,"value":1221},"auto-magic-calib-ms",{"type":51,"tag":1043,"props":1223,"children":1224},{"style":1056},[1225],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1227,"children":1228},{"style":1056},[1229],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1231,"children":1232},{"style":1062},[1233],{"type":57,"value":1179},{"type":51,"tag":1043,"props":1235,"children":1236},{"style":1103},[1237],{"type":57,"value":1238},"\u002Fcompose\u002Fms\u002Fcompose.yml",{"type":51,"tag":1043,"props":1240,"children":1241},{"style":1056},[1242],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1244,"children":1245},{"style":1056},[1246],{"type":57,"value":1193},{"type":51,"tag":1043,"props":1248,"children":1249},{"style":1103},[1250],{"type":57,"value":1198},{"type":51,"tag":1043,"props":1252,"children":1253},{"style":1056},[1254],{"type":57,"value":1255}," ||",{"type":51,"tag":1043,"props":1257,"children":1258},{"style":1056},[1259],{"type":57,"value":1260}," {",{"type":51,"tag":1043,"props":1262,"children":1263},{"style":1050},[1264],{"type":57,"value":1265}," echo",{"type":51,"tag":1043,"props":1267,"children":1268},{"style":1056},[1269],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1271,"children":1272},{"style":1103},[1273],{"type":57,"value":1274},"ERROR: REPO_ROOT is not an auto-magic-calib checkout: ",{"type":51,"tag":1043,"props":1276,"children":1277},{"style":1062},[1278],{"type":57,"value":1179},{"type":51,"tag":1043,"props":1280,"children":1281},{"style":1056},[1282],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1284,"children":1285},{"style":1056},[1286],{"type":57,"value":1287}," >&2;",{"type":51,"tag":1043,"props":1289,"children":1290},{"style":1050},[1291],{"type":57,"value":1292}," exit",{"type":51,"tag":1043,"props":1294,"children":1296},{"style":1295},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[1297],{"type":57,"value":1298}," 1",{"type":51,"tag":1043,"props":1300,"children":1301},{"style":1056},[1302],{"type":57,"value":1303},";",{"type":51,"tag":1043,"props":1305,"children":1306},{"style":1056},[1307],{"type":57,"value":1308}," }\n",{"type":51,"tag":1043,"props":1310,"children":1312},{"class":1045,"line":1311},3,[1313],{"type":51,"tag":1043,"props":1314,"children":1316},{"style":1315},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[1317],{"type":57,"value":1318},"# Resolve PROJECT_DIR from the Compose environment file (default: projects\u002F at repo root).\n",{"type":51,"tag":1043,"props":1320,"children":1321},{"class":1045,"line":447},[1322,1327,1332,1336,1341],{"type":51,"tag":1043,"props":1323,"children":1324},{"style":1062},[1325],{"type":57,"value":1326},"COMPOSE_ENV_BASENAME",{"type":51,"tag":1043,"props":1328,"children":1329},{"style":1056},[1330],{"type":57,"value":1331},"=",{"type":51,"tag":1043,"props":1333,"children":1334},{"style":1056},[1335],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1337,"children":1338},{"style":1103},[1339],{"type":57,"value":1340},"env",{"type":51,"tag":1043,"props":1342,"children":1343},{"style":1056},[1344],{"type":57,"value":1345},"\"\n",{"type":51,"tag":1043,"props":1347,"children":1349},{"class":1045,"line":1348},5,[1350,1355,1359,1363,1367,1372,1377,1381],{"type":51,"tag":1043,"props":1351,"children":1352},{"style":1062},[1353],{"type":57,"value":1354},"COMPOSE_ENV_FILE",{"type":51,"tag":1043,"props":1356,"children":1357},{"style":1056},[1358],{"type":57,"value":1331},{"type":51,"tag":1043,"props":1360,"children":1361},{"style":1056},[1362],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1364,"children":1365},{"style":1062},[1366],{"type":57,"value":1179},{"type":51,"tag":1043,"props":1368,"children":1369},{"style":1103},[1370],{"type":57,"value":1371},"\u002Fcompose\u002F.",{"type":51,"tag":1043,"props":1373,"children":1374},{"style":1056},[1375],{"type":57,"value":1376},"${",{"type":51,"tag":1043,"props":1378,"children":1379},{"style":1062},[1380],{"type":57,"value":1326},{"type":51,"tag":1043,"props":1382,"children":1383},{"style":1056},[1384],{"type":57,"value":1140},{"type":51,"tag":1043,"props":1386,"children":1388},{"class":1045,"line":1387},6,[1389,1394,1399,1403,1408,1412,1417,1421,1425,1429,1434,1439,1444,1449,1453,1458,1463,1468,1473,1478],{"type":51,"tag":1043,"props":1390,"children":1391},{"style":1062},[1392],{"type":57,"value":1393},"PROJECT_DIR_REL",{"type":51,"tag":1043,"props":1395,"children":1396},{"style":1056},[1397],{"type":57,"value":1398},"=$(",{"type":51,"tag":1043,"props":1400,"children":1401},{"style":1147},[1402],{"type":57,"value":1150},{"type":51,"tag":1043,"props":1404,"children":1405},{"style":1103},[1406],{"type":57,"value":1407}," ^PROJECT_DIR",{"type":51,"tag":1043,"props":1409,"children":1410},{"style":1056},[1411],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1413,"children":1414},{"style":1062},[1415],{"type":57,"value":1416},"$COMPOSE_ENV_FILE",{"type":51,"tag":1043,"props":1418,"children":1419},{"style":1056},[1420],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1422,"children":1423},{"style":1056},[1424],{"type":57,"value":1193},{"type":51,"tag":1043,"props":1426,"children":1427},{"style":1103},[1428],{"type":57,"value":1198},{"type":51,"tag":1043,"props":1430,"children":1431},{"style":1056},[1432],{"type":57,"value":1433}," |",{"type":51,"tag":1043,"props":1435,"children":1436},{"style":1147},[1437],{"type":57,"value":1438}," cut",{"type":51,"tag":1043,"props":1440,"children":1441},{"style":1103},[1442],{"type":57,"value":1443}," -d=",{"type":51,"tag":1043,"props":1445,"children":1446},{"style":1103},[1447],{"type":57,"value":1448}," -f2",{"type":51,"tag":1043,"props":1450,"children":1451},{"style":1056},[1452],{"type":57,"value":1433},{"type":51,"tag":1043,"props":1454,"children":1455},{"style":1147},[1456],{"type":57,"value":1457}," tr",{"type":51,"tag":1043,"props":1459,"children":1460},{"style":1103},[1461],{"type":57,"value":1462}," -d",{"type":51,"tag":1043,"props":1464,"children":1465},{"style":1056},[1466],{"type":57,"value":1467}," '",{"type":51,"tag":1043,"props":1469,"children":1470},{"style":1103},[1471],{"type":57,"value":1472},"[:space:]",{"type":51,"tag":1043,"props":1474,"children":1475},{"style":1056},[1476],{"type":57,"value":1477},"'",{"type":51,"tag":1043,"props":1479,"children":1480},{"style":1056},[1481],{"type":57,"value":1482},")\n",{"type":51,"tag":1043,"props":1484,"children":1486},{"class":1045,"line":1485},7,[1487,1492,1496,1501,1505,1509,1514,1518,1522,1527,1531,1535,1540,1545,1549,1553,1557,1562,1567],{"type":51,"tag":1043,"props":1488,"children":1489},{"style":1062},[1490],{"type":57,"value":1491},"HOST_PROJECTS",{"type":51,"tag":1043,"props":1493,"children":1494},{"style":1056},[1495],{"type":57,"value":1398},{"type":51,"tag":1043,"props":1497,"children":1498},{"style":1050},[1499],{"type":57,"value":1500},"cd",{"type":51,"tag":1043,"props":1502,"children":1503},{"style":1056},[1504],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1506,"children":1507},{"style":1062},[1508],{"type":57,"value":1179},{"type":51,"tag":1043,"props":1510,"children":1511},{"style":1103},[1512],{"type":57,"value":1513},"\u002Fcompose",{"type":51,"tag":1043,"props":1515,"children":1516},{"style":1056},[1517],{"type":57,"value":1170},{"type":51,"tag":1043,"props":1519,"children":1520},{"style":1056},[1521],{"type":57,"value":1203},{"type":51,"tag":1043,"props":1523,"children":1524},{"style":1147},[1525],{"type":57,"value":1526}," realpath",{"type":51,"tag":1043,"props":1528,"children":1529},{"style":1056},[1530],{"type":57,"value":1059},{"type":51,"tag":1043,"props":1532,"children":1533},{"style":1062},[1534],{"type":57,"value":1393},{"type":51,"tag":1043,"props":1536,"children":1537},{"style":1056},[1538],{"type":57,"value":1539},":-",{"type":51,"tag":1043,"props":1541,"children":1542},{"style":1103},[1543],{"type":57,"value":1544},"..",{"type":51,"tag":1043,"props":1546,"children":1547},{"style":1056},[1548],{"type":57,"value":422},{"type":51,"tag":1043,"props":1550,"children":1551},{"style":1103},[1552],{"type":57,"value":1544},{"type":51,"tag":1043,"props":1554,"children":1555},{"style":1056},[1556],{"type":57,"value":422},{"type":51,"tag":1043,"props":1558,"children":1559},{"style":1062},[1560],{"type":57,"value":1561},"projects",{"type":51,"tag":1043,"props":1563,"children":1564},{"style":1056},[1565],{"type":57,"value":1566},"}\"",{"type":51,"tag":1043,"props":1568,"children":1569},{"style":1056},[1570],{"type":57,"value":1482},{"type":51,"tag":1043,"props":1572,"children":1574},{"class":1045,"line":1573},8,[1575],{"type":51,"tag":1043,"props":1576,"children":1577},{"emptyLinePlaceholder":141},[1578],{"type":57,"value":1579},"\n",{"type":51,"tag":1043,"props":1581,"children":1583},{"class":1045,"line":1582},9,[1584,1589,1593,1598,1603],{"type":51,"tag":1043,"props":1585,"children":1586},{"style":1147},[1587],{"type":57,"value":1588},"ls",{"type":51,"tag":1043,"props":1590,"children":1591},{"style":1056},[1592],{"type":57,"value":1160},{"type":51,"tag":1043,"props":1594,"children":1595},{"style":1062},[1596],{"type":57,"value":1597},"$HOST_PROJECTS",{"type":51,"tag":1043,"props":1599,"children":1600},{"style":1103},[1601],{"type":57,"value":1602},"\u002Fproject_\u003Cproject_id>\u002Fmanual_adjustment\u002F",{"type":51,"tag":1043,"props":1604,"children":1605},{"style":1056},[1606],{"type":57,"value":1345},{"type":51,"tag":1043,"props":1608,"children":1610},{"class":1045,"line":1609},10,[1611],{"type":51,"tag":1043,"props":1612,"children":1613},{"style":1315},[1614],{"type":57,"value":1615},"# Expected: alignment_data.json, layout.png\n",{"type":51,"tag":236,"props":1617,"children":1619},{"id":1618},"step-6-verify-project",[1620],{"type":57,"value":1621},"Step 6 — Verify Project",{"type":51,"tag":67,"props":1623,"children":1624},{},[1625,1631,1633,1639],{"type":51,"tag":106,"props":1626,"children":1628},{"className":1627},[],[1629],{"type":57,"value":1630},"POST \u002Fv1\u002Fverify_project\u002F\u003Cproject_id>",{"type":57,"value":1632}," → must return ",{"type":51,"tag":106,"props":1634,"children":1636},{"className":1635},[],[1637],{"type":57,"value":1638},"{\"project_state\": \"READY\"}",{"type":57,"value":1640}," before calibrating.",{"type":51,"tag":236,"props":1642,"children":1644},{"id":1643},"step-7-start-calibration",[1645],{"type":57,"value":1646},"Step 7 — Start Calibration",{"type":51,"tag":67,"props":1648,"children":1649},{},[1650,1655,1657,1663],{"type":51,"tag":93,"props":1651,"children":1652},{},[1653],{"type":57,"value":1654},"Confirm the plan before calibrating.",{"type":57,"value":1656}," Whether the settings file and detector were auto-detected or asked, present a short summary and get explicit user confirmation before ",{"type":51,"tag":106,"props":1658,"children":1660},{"className":1659},[],[1661],{"type":57,"value":1662},"POST \u002Fcalibrate",{"type":57,"value":1664}," using the host's question mechanism; if none is available, ask in chat and wait. The resolved values are the defaults, so confirming is one click, but the user can switch the detector or skip an auto-detected settings file. The standalone Python script prints the same plan and prompts only when stdin is interactive. Summarize:",{"type":51,"tag":73,"props":1666,"children":1667},{},[1668,1690,1699],{"type":51,"tag":77,"props":1669,"children":1670},{},[1671,1676,1677,1682,1683,1688],{"type":51,"tag":93,"props":1672,"children":1673},{},[1674],{"type":57,"value":1675},"Detector",{"type":57,"value":458},{"type":51,"tag":106,"props":1678,"children":1680},{"className":1679},[],[1681],{"type":57,"value":420},{"type":57,"value":914},{"type":51,"tag":106,"props":1684,"children":1686},{"className":1685},[],[1687],{"type":57,"value":428},{"type":57,"value":1689}," (the value to be sent).",{"type":51,"tag":77,"props":1691,"children":1692},{},[1693,1697],{"type":51,"tag":93,"props":1694,"children":1695},{},[1696],{"type":57,"value":338},{"type":57,"value":1698}," — the file being applied (path), or \"defaults\" if none.",{"type":51,"tag":77,"props":1700,"children":1701},{},[1702,1707],{"type":51,"tag":93,"props":1703,"children":1704},{},[1705],{"type":57,"value":1706},"Optional overrides",{"type":57,"value":1708}," — ground-truth zip and focal lengths, if any.",{"type":51,"tag":1032,"props":1710,"children":1714},{"className":1711,"code":1713,"language":57},[1712],"language-text","POST \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n{\"detector_type\": \"resnet\"}\n",[1715],{"type":51,"tag":106,"props":1716,"children":1717},{"__ignoreMap":1037},[1718],{"type":57,"value":1713},{"type":51,"tag":236,"props":1720,"children":1722},{"id":1721},"step-8-poll-for-completion",[1723],{"type":57,"value":1724},"Step 8 — Poll for Completion",{"type":51,"tag":67,"props":1726,"children":1727},{},[1728,1734,1736,1742,1744,1750,1752,1758,1760,1766,1768,1773],{"type":51,"tag":106,"props":1729,"children":1731},{"className":1730},[],[1732],{"type":57,"value":1733},"GET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>",{"type":57,"value":1735}," every 10 s — ",{"type":51,"tag":106,"props":1737,"children":1739},{"className":1738},[],[1740],{"type":57,"value":1741},"project_info.project_state",{"type":57,"value":1743}," goes ",{"type":51,"tag":106,"props":1745,"children":1747},{"className":1746},[],[1748],{"type":57,"value":1749},"RUNNING",{"type":57,"value":1751}," → ",{"type":51,"tag":106,"props":1753,"children":1755},{"className":1754},[],[1756],{"type":57,"value":1757},"COMPLETED",{"type":57,"value":1759}," (or ",{"type":51,"tag":106,"props":1761,"children":1763},{"className":1762},[],[1764],{"type":57,"value":1765},"ERROR",{"type":57,"value":1767},", pull the log). Typical time: ",{"type":51,"tag":93,"props":1769,"children":1770},{},[1771],{"type":57,"value":1772},"10–60 min",{"type":57,"value":1774}," depending on video length and detector.",{"type":51,"tag":236,"props":1776,"children":1778},{"id":1777},"step-9-get-results",[1779],{"type":57,"value":1780},"Step 9 — Get Results",{"type":51,"tag":67,"props":1782,"children":1783},{},[1784,1790,1792,1798,1800,1806,1808,1814],{"type":51,"tag":106,"props":1785,"children":1787},{"className":1786},[],[1788],{"type":57,"value":1789},"GET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Fevaluation_statistics",{"type":57,"value":1791}," (only if GT was uploaded; includes ",{"type":51,"tag":106,"props":1793,"children":1795},{"className":1794},[],[1796],{"type":57,"value":1797},"Average L2 distance(m)",{"type":57,"value":1799}," and ",{"type":51,"tag":106,"props":1801,"children":1803},{"className":1802},[],[1804],{"type":57,"value":1805},"Average reprojection error 0(px)",{"type":57,"value":1807},"), and ",{"type":51,"tag":106,"props":1809,"children":1811},{"className":1810},[],[1812],{"type":57,"value":1813},"GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog",{"type":57,"value":1815}," for the calibration log.",{"type":51,"tag":236,"props":1817,"children":1819},{"id":1818},"status-fields-from-get_project_info",[1820,1822],{"type":57,"value":1821},"Status Fields from ",{"type":51,"tag":106,"props":1823,"children":1825},{"className":1824},[],[1826],{"type":57,"value":1827},"get_project_info",{"type":51,"tag":67,"props":1829,"children":1830},{},[1831,1836,1838,1843,1844,1849,1850,1855],{"type":51,"tag":106,"props":1832,"children":1834},{"className":1833},[],[1835],{"type":57,"value":1741},{"type":57,"value":1837}," is the AMC calibration lifecycle for the project: ",{"type":51,"tag":106,"props":1839,"children":1841},{"className":1840},[],[1842],{"type":57,"value":1749},{"type":57,"value":1751},{"type":51,"tag":106,"props":1845,"children":1847},{"className":1846},[],[1848],{"type":57,"value":1757},{"type":57,"value":1759},{"type":51,"tag":106,"props":1851,"children":1853},{"className":1852},[],[1854],{"type":57,"value":1765},{"type":57,"value":937},{"type":51,"tag":67,"props":1857,"children":1858},{},[1859,1865,1867,1872,1874,1880,1882,1888,1889,1895,1897,1902,1904,1909,1910,1915],{"type":51,"tag":106,"props":1860,"children":1862},{"className":1861},[],[1863],{"type":57,"value":1864},"project_info.vggt_state",{"type":57,"value":1866}," is also ",{"type":51,"tag":93,"props":1868,"children":1869},{},[1870],{"type":57,"value":1871},"per-project",{"type":57,"value":1873},", a project-scoped VGGT refinement lifecycle rather than a direct global service or model-load status. A newly created project can report ",{"type":51,"tag":106,"props":1875,"children":1877},{"className":1876},[],[1878],{"type":57,"value":1879},"vggt_state: \"INIT\"",{"type":57,"value":1881}," even when the VGGT model is present and mounted. The expected VGGT lifecycle is ",{"type":51,"tag":106,"props":1883,"children":1885},{"className":1884},[],[1886],{"type":57,"value":1887},"INIT",{"type":57,"value":1751},{"type":51,"tag":106,"props":1890,"children":1892},{"className":1891},[],[1893],{"type":57,"value":1894},"READY",{"type":57,"value":1896}," after AMC calibration completes → ",{"type":51,"tag":106,"props":1898,"children":1900},{"className":1899},[],[1901],{"type":57,"value":1749},{"type":57,"value":1903}," while VGGT refinement runs → ",{"type":51,"tag":106,"props":1905,"children":1907},{"className":1906},[],[1908],{"type":57,"value":1757},{"type":57,"value":1759},{"type":51,"tag":106,"props":1911,"children":1913},{"className":1912},[],[1914],{"type":57,"value":1765},{"type":57,"value":937},{"type":51,"tag":67,"props":1917,"children":1918},{},[1919,1921,1927,1929,1934],{"type":57,"value":1920},"Use ",{"type":51,"tag":106,"props":1922,"children":1924},{"className":1923},[],[1925],{"type":57,"value":1926},"vggt_state == \"READY\"",{"type":57,"value":1928}," only as the gate for optional VGGT refinement in Step 10. Interpret ",{"type":51,"tag":106,"props":1930,"children":1932},{"className":1931},[],[1933],{"type":57,"value":1887},{"type":57,"value":1935}," on a new or uncalibrated project as normal project state. If AMC calibration is complete and the project remains in a non-ready VGGT state, confirm VGGT setup and model availability with the setup skill checks and service logs.",{"type":51,"tag":236,"props":1937,"children":1939},{"id":1938},"step-10-optional-vggt-refinement",[1940],{"type":57,"value":1941},"Step 10 — (Optional) VGGT Refinement",{"type":51,"tag":67,"props":1943,"children":1944},{},[1945,1947,1953,1955,1960],{"type":57,"value":1946},"After AMC calibration completes, read ",{"type":51,"tag":106,"props":1948,"children":1950},{"className":1949},[],[1951],{"type":57,"value":1952},"vggt_state",{"type":57,"value":1954}," from ",{"type":51,"tag":106,"props":1956,"children":1958},{"className":1957},[],[1959],{"type":57,"value":1733},{"type":57,"value":121},{"type":51,"tag":73,"props":1962,"children":1963},{},[1964,1976,2010],{"type":51,"tag":77,"props":1965,"children":1966},{},[1967,1969,1974],{"type":57,"value":1968},"If the project reports ",{"type":51,"tag":106,"props":1970,"children":1972},{"className":1971},[],[1973],{"type":57,"value":1926},{"type":57,"value":1975},", ask the user whether to run VGGT refinement using the host's question mechanism; if none is available, ask in chat and wait.",{"type":51,"tag":77,"props":1977,"children":1978},{},[1979,1981,1987,1989,1994,1996,2001,2003,2009],{"type":57,"value":1980},"If the user confirms, ",{"type":51,"tag":106,"props":1982,"children":1984},{"className":1983},[],[1985],{"type":57,"value":1986},"POST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F\u003Cproject_id>",{"type":57,"value":1988},", poll ",{"type":51,"tag":106,"props":1990,"children":1992},{"className":1991},[],[1993],{"type":57,"value":1952},{"type":57,"value":1995}," via ",{"type":51,"tag":106,"props":1997,"children":1999},{"className":1998},[],[2000],{"type":57,"value":1827},{"type":57,"value":2002},", then ",{"type":51,"tag":106,"props":2004,"children":2006},{"className":2005},[],[2007],{"type":57,"value":2008},"GET \u002Fv1\u002Fvggt_results\u002F\u003Cproject_id>\u002Fevaluation_statistics",{"type":57,"value":121},{"type":51,"tag":77,"props":2011,"children":2012},{},[2013,2015,2021],{"type":57,"value":2014},"If VGGT is not ready, skip refinement and explain that the user can set up VGGT with ",{"type":51,"tag":106,"props":2016,"children":2018},{"className":2017},[],[2019],{"type":57,"value":2020},"amc-setup-calibration-stack",{"type":57,"value":2022}," and rerun this optional step later.",{"type":51,"tag":67,"props":2024,"children":2025},{},[2026,2028,2034],{"type":57,"value":2027},"The standalone Python script prompts only when stdin is interactive. In non-interactive runs, set ",{"type":51,"tag":106,"props":2029,"children":2031},{"className":2030},[],[2032],{"type":57,"value":2033},"RUN_VGGT = True",{"type":57,"value":2035}," to opt in; otherwise the script prints that VGGT is ready and continues without blocking.",{"type":51,"tag":538,"props":2037,"children":2038},{},[],{"type":51,"tag":60,"props":2040,"children":2042},{"id":2041},"complete-python-script",[2043],{"type":57,"value":558},{"type":51,"tag":67,"props":2045,"children":2046},{},[2047,2049,2054,2056,2061,2063,2069,2071,2077,2079,2085,2086,2092,2093,2098,2100,2106,2107,2113,2114,2120,2121,2127,2128,2134,2135,2141,2142,2148,2149,2154,2155,2161],{"type":57,"value":2048},"Use the bundled script from the ",{"type":51,"tag":106,"props":2050,"children":2052},{"className":2051},[],[2053],{"type":57,"value":4},{"type":57,"value":2055}," skill package, not from the ",{"type":51,"tag":106,"props":2057,"children":2059},{"className":2058},[],[2060],{"type":57,"value":37},{"type":57,"value":2062}," repo root. If the user points the agent at this skill folder directly instead of installing it, set ",{"type":51,"tag":106,"props":2064,"children":2066},{"className":2065},[],[2067],{"type":57,"value":2068},"AMC_VIDEO_SKILL_DIR",{"type":57,"value":2070}," to the directory containing this ",{"type":51,"tag":106,"props":2072,"children":2074},{"className":2073},[],[2075],{"type":57,"value":2076},"SKILL.md",{"type":57,"value":2078},", or run the command from that directory. Set ",{"type":51,"tag":106,"props":2080,"children":2082},{"className":2081},[],[2083],{"type":57,"value":2084},"BASE_URL",{"type":57,"value":194},{"type":51,"tag":106,"props":2087,"children":2089},{"className":2088},[],[2090],{"type":57,"value":2091},"PROJECT_NAME",{"type":57,"value":663},{"type":51,"tag":106,"props":2094,"children":2096},{"className":2095},[],[2097],{"type":57,"value":654},{"type":57,"value":2099},"; optional env vars are ",{"type":51,"tag":106,"props":2101,"children":2103},{"className":2102},[],[2104],{"type":57,"value":2105},"CONFIG_FILE",{"type":57,"value":194},{"type":51,"tag":106,"props":2108,"children":2110},{"className":2109},[],[2111],{"type":57,"value":2112},"ALIGNMENT_JSON",{"type":57,"value":194},{"type":51,"tag":106,"props":2115,"children":2117},{"className":2116},[],[2118],{"type":57,"value":2119},"LAYOUT_PNG",{"type":57,"value":194},{"type":51,"tag":106,"props":2122,"children":2124},{"className":2123},[],[2125],{"type":57,"value":2126},"GT_ZIP",{"type":57,"value":194},{"type":51,"tag":106,"props":2129,"children":2131},{"className":2130},[],[2132],{"type":57,"value":2133},"FOCAL_LENGTHS",{"type":57,"value":194},{"type":51,"tag":106,"props":2136,"children":2138},{"className":2137},[],[2139],{"type":57,"value":2140},"DETECTOR_TYPE",{"type":57,"value":194},{"type":51,"tag":106,"props":2143,"children":2145},{"className":2144},[],[2146],{"type":57,"value":2147},"RUN_VGGT",{"type":57,"value":194},{"type":51,"tag":106,"props":2150,"children":2152},{"className":2151},[],[2153],{"type":57,"value":1065},{"type":57,"value":663},{"type":51,"tag":106,"props":2156,"children":2158},{"className":2157},[],[2159],{"type":57,"value":2160},"PROJECTS_DIR",{"type":57,"value":2162},". The script implements UI fallback, plan confirmation, VGGT prompt\u002Fopt-in behavior, polling, and refined statistics retrieval.",{"type":51,"tag":1032,"props":2164,"children":2166},{"className":1034,"code":2165,"language":1036,"meta":1037,"style":1037},"# Optional but recommended: REPO_ROOT points to the auto-magic-calib checkout.\n# PROJECTS_DIR can be set explicitly when project outputs live elsewhere.\nif [ -z \"${DEEPSTREAM_REPO_ROOT:-}\" ] && [ -n \"${REPO_ROOT:-}\" ] && [ -d \"$REPO_ROOT\u002F..\u002F..\u002Fskills\u002Famc-run-video-calibration\" ]; then\n  DEEPSTREAM_REPO_ROOT=\"$(cd \"$REPO_ROOT\u002F..\u002F..\" && pwd)\"\nfi\n\nSCRIPT_PATH=\"\"\nfor candidate in \\\n  \"${AMC_VIDEO_SKILL_DIR:+$AMC_VIDEO_SKILL_DIR\u002Fscripts\u002Frun_video_calibration.py}\" \\\n  \"$PWD\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"${DEEPSTREAM_REPO_ROOT:+$DEEPSTREAM_REPO_ROOT\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py}\" \\\n  \"$PWD\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.claude\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.codex\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" \\\n  \"$HOME\u002F.cursor\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\"; do\n  if [ -f \"$candidate\" ]; then\n    SCRIPT_PATH=\"$candidate\"\n    break\n  fi\ndone\n\n[ -n \"$SCRIPT_PATH\" ] || {\n  echo \"ERROR: could not find amc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py\" >&2\n  echo \"Set AMC_VIDEO_SKILL_DIR to the amc-run-video-calibration skill directory, or run this block from that directory.\" >&2\n  exit 1\n}\n\npython3 \"$SCRIPT_PATH\"\n",[2167],{"type":51,"tag":106,"props":2168,"children":2169},{"__ignoreMap":1037},[2170,2178,2186,2292,2344,2352,2359,2376,2399,2460,2486,2560,2585,2611,2636,2666,2705,2730,2739,2748,2757,2765,2804,2831,2856,2870,2879,2887],{"type":51,"tag":1043,"props":2171,"children":2172},{"class":1045,"line":1046},[2173],{"type":51,"tag":1043,"props":2174,"children":2175},{"style":1315},[2176],{"type":57,"value":2177},"# Optional but recommended: REPO_ROOT points to the auto-magic-calib checkout.\n",{"type":51,"tag":1043,"props":2179,"children":2180},{"class":1045,"line":1143},[2181],{"type":51,"tag":1043,"props":2182,"children":2183},{"style":1315},[2184],{"type":57,"value":2185},"# PROJECTS_DIR can be set explicitly when project outputs live elsewhere.\n",{"type":51,"tag":1043,"props":2187,"children":2188},{"class":1045,"line":1311},[2189,2195,2200,2205,2209,2214,2219,2224,2228,2232,2237,2241,2245,2249,2253,2257,2261,2265,2269,2273,2278,2282,2287],{"type":51,"tag":1043,"props":2190,"children":2192},{"style":2191},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[2193],{"type":57,"value":2194},"if",{"type":51,"tag":1043,"props":2196,"children":2197},{"style":1056},[2198],{"type":57,"value":2199}," [",{"type":51,"tag":1043,"props":2201,"children":2202},{"style":1056},[2203],{"type":57,"value":2204}," -z",{"type":51,"tag":1043,"props":2206,"children":2207},{"style":1056},[2208],{"type":57,"value":1059},{"type":51,"tag":1043,"props":2210,"children":2211},{"style":1062},[2212],{"type":57,"value":2213},"DEEPSTREAM_REPO_ROOT",{"type":51,"tag":1043,"props":2215,"children":2216},{"style":1056},[2217],{"type":57,"value":2218},":-}\"",{"type":51,"tag":1043,"props":2220,"children":2221},{"style":1056},[2222],{"type":57,"value":2223}," ]",{"type":51,"tag":1043,"props":2225,"children":2226},{"style":1056},[2227],{"type":57,"value":1203},{"type":51,"tag":1043,"props":2229,"children":2230},{"style":1056},[2231],{"type":57,"value":2199},{"type":51,"tag":1043,"props":2233,"children":2234},{"style":1056},[2235],{"type":57,"value":2236}," -n",{"type":51,"tag":1043,"props":2238,"children":2239},{"style":1056},[2240],{"type":57,"value":1059},{"type":51,"tag":1043,"props":2242,"children":2243},{"style":1062},[2244],{"type":57,"value":1065},{"type":51,"tag":1043,"props":2246,"children":2247},{"style":1056},[2248],{"type":57,"value":2218},{"type":51,"tag":1043,"props":2250,"children":2251},{"style":1056},[2252],{"type":57,"value":2223},{"type":51,"tag":1043,"props":2254,"children":2255},{"style":1056},[2256],{"type":57,"value":1203},{"type":51,"tag":1043,"props":2258,"children":2259},{"style":1056},[2260],{"type":57,"value":2199},{"type":51,"tag":1043,"props":2262,"children":2263},{"style":1056},[2264],{"type":57,"value":1462},{"type":51,"tag":1043,"props":2266,"children":2267},{"style":1056},[2268],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2270,"children":2271},{"style":1062},[2272],{"type":57,"value":1179},{"type":51,"tag":1043,"props":2274,"children":2275},{"style":1103},[2276],{"type":57,"value":2277},"\u002F..\u002F..\u002Fskills\u002Famc-run-video-calibration",{"type":51,"tag":1043,"props":2279,"children":2280},{"style":1056},[2281],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2283,"children":2284},{"style":1056},[2285],{"type":57,"value":2286}," ];",{"type":51,"tag":1043,"props":2288,"children":2289},{"style":2191},[2290],{"type":57,"value":2291}," then\n",{"type":51,"tag":1043,"props":2293,"children":2294},{"class":1045,"line":447},[2295,2300,2304,2309,2313,2317,2321,2326,2330,2334,2339],{"type":51,"tag":1043,"props":2296,"children":2297},{"style":1062},[2298],{"type":57,"value":2299},"  DEEPSTREAM_REPO_ROOT",{"type":51,"tag":1043,"props":2301,"children":2302},{"style":1056},[2303],{"type":57,"value":1331},{"type":51,"tag":1043,"props":2305,"children":2306},{"style":1056},[2307],{"type":57,"value":2308},"\"$(",{"type":51,"tag":1043,"props":2310,"children":2311},{"style":1050},[2312],{"type":57,"value":1500},{"type":51,"tag":1043,"props":2314,"children":2315},{"style":1056},[2316],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2318,"children":2319},{"style":1062},[2320],{"type":57,"value":1179},{"type":51,"tag":1043,"props":2322,"children":2323},{"style":1103},[2324],{"type":57,"value":2325},"\u002F..\u002F..",{"type":51,"tag":1043,"props":2327,"children":2328},{"style":1056},[2329],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2331,"children":2332},{"style":1056},[2333],{"type":57,"value":1203},{"type":51,"tag":1043,"props":2335,"children":2336},{"style":1050},[2337],{"type":57,"value":2338}," pwd",{"type":51,"tag":1043,"props":2340,"children":2341},{"style":1056},[2342],{"type":57,"value":2343},")\"\n",{"type":51,"tag":1043,"props":2345,"children":2346},{"class":1045,"line":1348},[2347],{"type":51,"tag":1043,"props":2348,"children":2349},{"style":2191},[2350],{"type":57,"value":2351},"fi\n",{"type":51,"tag":1043,"props":2353,"children":2354},{"class":1045,"line":1387},[2355],{"type":51,"tag":1043,"props":2356,"children":2357},{"emptyLinePlaceholder":141},[2358],{"type":57,"value":1579},{"type":51,"tag":1043,"props":2360,"children":2361},{"class":1045,"line":1485},[2362,2367,2371],{"type":51,"tag":1043,"props":2363,"children":2364},{"style":1062},[2365],{"type":57,"value":2366},"SCRIPT_PATH",{"type":51,"tag":1043,"props":2368,"children":2369},{"style":1056},[2370],{"type":57,"value":1331},{"type":51,"tag":1043,"props":2372,"children":2373},{"style":1056},[2374],{"type":57,"value":2375},"\"\"\n",{"type":51,"tag":1043,"props":2377,"children":2378},{"class":1045,"line":1573},[2379,2384,2389,2394],{"type":51,"tag":1043,"props":2380,"children":2381},{"style":2191},[2382],{"type":57,"value":2383},"for",{"type":51,"tag":1043,"props":2385,"children":2386},{"style":1062},[2387],{"type":57,"value":2388}," candidate ",{"type":51,"tag":1043,"props":2390,"children":2391},{"style":2191},[2392],{"type":57,"value":2393},"in",{"type":51,"tag":1043,"props":2395,"children":2396},{"style":1062},[2397],{"type":57,"value":2398}," \\\n",{"type":51,"tag":1043,"props":2400,"children":2401},{"class":1045,"line":1582},[2402,2407,2411,2415,2420,2425,2429,2434,2438,2443,2447,2452,2456],{"type":51,"tag":1043,"props":2403,"children":2404},{"style":1056},[2405],{"type":57,"value":2406},"  \"${",{"type":51,"tag":1043,"props":2408,"children":2409},{"style":1062},[2410],{"type":57,"value":2068},{"type":51,"tag":1043,"props":2412,"children":2413},{"style":1056},[2414],{"type":57,"value":1053},{"type":51,"tag":1043,"props":2416,"children":2417},{"style":1103},[2418],{"type":57,"value":2419},"+",{"type":51,"tag":1043,"props":2421,"children":2422},{"style":1062},[2423],{"type":57,"value":2424},"$AMC_VIDEO_SKILL_DIR",{"type":51,"tag":1043,"props":2426,"children":2427},{"style":1056},[2428],{"type":57,"value":422},{"type":51,"tag":1043,"props":2430,"children":2431},{"style":1062},[2432],{"type":57,"value":2433},"scripts",{"type":51,"tag":1043,"props":2435,"children":2436},{"style":1056},[2437],{"type":57,"value":422},{"type":51,"tag":1043,"props":2439,"children":2440},{"style":1062},[2441],{"type":57,"value":2442},"run_video_calibration",{"type":51,"tag":1043,"props":2444,"children":2445},{"style":1103},[2446],{"type":57,"value":121},{"type":51,"tag":1043,"props":2448,"children":2449},{"style":1062},[2450],{"type":57,"value":2451},"py",{"type":51,"tag":1043,"props":2453,"children":2454},{"style":1056},[2455],{"type":57,"value":1566},{"type":51,"tag":1043,"props":2457,"children":2458},{"style":1062},[2459],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2461,"children":2462},{"class":1045,"line":1609},[2463,2468,2473,2478,2482],{"type":51,"tag":1043,"props":2464,"children":2465},{"style":1056},[2466],{"type":57,"value":2467},"  \"",{"type":51,"tag":1043,"props":2469,"children":2470},{"style":1062},[2471],{"type":57,"value":2472},"$PWD",{"type":51,"tag":1043,"props":2474,"children":2475},{"style":1103},[2476],{"type":57,"value":2477},"\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2479,"children":2480},{"style":1056},[2481],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2483,"children":2484},{"style":1062},[2485],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2487,"children":2489},{"class":1045,"line":2488},11,[2490,2494,2498,2502,2506,2511,2515,2520,2524,2528,2532,2536,2540,2544,2548,2552,2556],{"type":51,"tag":1043,"props":2491,"children":2492},{"style":1056},[2493],{"type":57,"value":2406},{"type":51,"tag":1043,"props":2495,"children":2496},{"style":1062},[2497],{"type":57,"value":2213},{"type":51,"tag":1043,"props":2499,"children":2500},{"style":1056},[2501],{"type":57,"value":1053},{"type":51,"tag":1043,"props":2503,"children":2504},{"style":1103},[2505],{"type":57,"value":2419},{"type":51,"tag":1043,"props":2507,"children":2508},{"style":1062},[2509],{"type":57,"value":2510},"$DEEPSTREAM_REPO_ROOT",{"type":51,"tag":1043,"props":2512,"children":2513},{"style":1056},[2514],{"type":57,"value":422},{"type":51,"tag":1043,"props":2516,"children":2517},{"style":1062},[2518],{"type":57,"value":2519},"skills",{"type":51,"tag":1043,"props":2521,"children":2522},{"style":1056},[2523],{"type":57,"value":422},{"type":51,"tag":1043,"props":2525,"children":2526},{"style":1062},[2527],{"type":57,"value":4},{"type":51,"tag":1043,"props":2529,"children":2530},{"style":1056},[2531],{"type":57,"value":422},{"type":51,"tag":1043,"props":2533,"children":2534},{"style":1062},[2535],{"type":57,"value":2433},{"type":51,"tag":1043,"props":2537,"children":2538},{"style":1056},[2539],{"type":57,"value":422},{"type":51,"tag":1043,"props":2541,"children":2542},{"style":1062},[2543],{"type":57,"value":2442},{"type":51,"tag":1043,"props":2545,"children":2546},{"style":1103},[2547],{"type":57,"value":121},{"type":51,"tag":1043,"props":2549,"children":2550},{"style":1062},[2551],{"type":57,"value":2451},{"type":51,"tag":1043,"props":2553,"children":2554},{"style":1056},[2555],{"type":57,"value":1566},{"type":51,"tag":1043,"props":2557,"children":2558},{"style":1062},[2559],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2561,"children":2563},{"class":1045,"line":2562},12,[2564,2568,2572,2577,2581],{"type":51,"tag":1043,"props":2565,"children":2566},{"style":1056},[2567],{"type":57,"value":2467},{"type":51,"tag":1043,"props":2569,"children":2570},{"style":1062},[2571],{"type":57,"value":2472},{"type":51,"tag":1043,"props":2573,"children":2574},{"style":1103},[2575],{"type":57,"value":2576},"\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2578,"children":2579},{"style":1056},[2580],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2582,"children":2583},{"style":1062},[2584],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2586,"children":2588},{"class":1045,"line":2587},13,[2589,2593,2598,2603,2607],{"type":51,"tag":1043,"props":2590,"children":2591},{"style":1056},[2592],{"type":57,"value":2467},{"type":51,"tag":1043,"props":2594,"children":2595},{"style":1062},[2596],{"type":57,"value":2597},"$HOME",{"type":51,"tag":1043,"props":2599,"children":2600},{"style":1103},[2601],{"type":57,"value":2602},"\u002F.claude\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2604,"children":2605},{"style":1056},[2606],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2608,"children":2609},{"style":1062},[2610],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2612,"children":2614},{"class":1045,"line":2613},14,[2615,2619,2623,2628,2632],{"type":51,"tag":1043,"props":2616,"children":2617},{"style":1056},[2618],{"type":57,"value":2467},{"type":51,"tag":1043,"props":2620,"children":2621},{"style":1062},[2622],{"type":57,"value":2597},{"type":51,"tag":1043,"props":2624,"children":2625},{"style":1103},[2626],{"type":57,"value":2627},"\u002F.codex\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2629,"children":2630},{"style":1056},[2631],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2633,"children":2634},{"style":1062},[2635],{"type":57,"value":2398},{"type":51,"tag":1043,"props":2637,"children":2639},{"class":1045,"line":2638},15,[2640,2644,2648,2653,2657,2661],{"type":51,"tag":1043,"props":2641,"children":2642},{"style":1056},[2643],{"type":57,"value":2467},{"type":51,"tag":1043,"props":2645,"children":2646},{"style":1062},[2647],{"type":57,"value":2597},{"type":51,"tag":1043,"props":2649,"children":2650},{"style":1103},[2651],{"type":57,"value":2652},"\u002F.cursor\u002Fskills\u002Famc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2654,"children":2655},{"style":1056},[2656],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2658,"children":2659},{"style":1056},[2660],{"type":57,"value":1303},{"type":51,"tag":1043,"props":2662,"children":2663},{"style":2191},[2664],{"type":57,"value":2665}," do\n",{"type":51,"tag":1043,"props":2667,"children":2669},{"class":1045,"line":2668},16,[2670,2675,2679,2684,2688,2693,2697,2701],{"type":51,"tag":1043,"props":2671,"children":2672},{"style":2191},[2673],{"type":57,"value":2674},"  if",{"type":51,"tag":1043,"props":2676,"children":2677},{"style":1056},[2678],{"type":57,"value":2199},{"type":51,"tag":1043,"props":2680,"children":2681},{"style":1056},[2682],{"type":57,"value":2683}," -f",{"type":51,"tag":1043,"props":2685,"children":2686},{"style":1056},[2687],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2689,"children":2690},{"style":1062},[2691],{"type":57,"value":2692},"$candidate",{"type":51,"tag":1043,"props":2694,"children":2695},{"style":1056},[2696],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2698,"children":2699},{"style":1056},[2700],{"type":57,"value":2286},{"type":51,"tag":1043,"props":2702,"children":2703},{"style":2191},[2704],{"type":57,"value":2291},{"type":51,"tag":1043,"props":2706,"children":2708},{"class":1045,"line":2707},17,[2709,2714,2718,2722,2726],{"type":51,"tag":1043,"props":2710,"children":2711},{"style":1062},[2712],{"type":57,"value":2713},"    SCRIPT_PATH",{"type":51,"tag":1043,"props":2715,"children":2716},{"style":1056},[2717],{"type":57,"value":1331},{"type":51,"tag":1043,"props":2719,"children":2720},{"style":1056},[2721],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2723,"children":2724},{"style":1062},[2725],{"type":57,"value":2692},{"type":51,"tag":1043,"props":2727,"children":2728},{"style":1056},[2729],{"type":57,"value":1345},{"type":51,"tag":1043,"props":2731,"children":2733},{"class":1045,"line":2732},18,[2734],{"type":51,"tag":1043,"props":2735,"children":2736},{"style":2191},[2737],{"type":57,"value":2738},"    break\n",{"type":51,"tag":1043,"props":2740,"children":2742},{"class":1045,"line":2741},19,[2743],{"type":51,"tag":1043,"props":2744,"children":2745},{"style":2191},[2746],{"type":57,"value":2747},"  fi\n",{"type":51,"tag":1043,"props":2749,"children":2751},{"class":1045,"line":2750},20,[2752],{"type":51,"tag":1043,"props":2753,"children":2754},{"style":2191},[2755],{"type":57,"value":2756},"done\n",{"type":51,"tag":1043,"props":2758,"children":2760},{"class":1045,"line":2759},21,[2761],{"type":51,"tag":1043,"props":2762,"children":2763},{"emptyLinePlaceholder":141},[2764],{"type":57,"value":1579},{"type":51,"tag":1043,"props":2766,"children":2768},{"class":1045,"line":2767},22,[2769,2774,2778,2782,2787,2791,2795,2799],{"type":51,"tag":1043,"props":2770,"children":2771},{"style":1056},[2772],{"type":57,"value":2773},"[",{"type":51,"tag":1043,"props":2775,"children":2776},{"style":1056},[2777],{"type":57,"value":2236},{"type":51,"tag":1043,"props":2779,"children":2780},{"style":1056},[2781],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2783,"children":2784},{"style":1062},[2785],{"type":57,"value":2786},"$SCRIPT_PATH",{"type":51,"tag":1043,"props":2788,"children":2789},{"style":1056},[2790],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2792,"children":2793},{"style":1056},[2794],{"type":57,"value":2223},{"type":51,"tag":1043,"props":2796,"children":2797},{"style":1056},[2798],{"type":57,"value":1255},{"type":51,"tag":1043,"props":2800,"children":2801},{"style":1056},[2802],{"type":57,"value":2803}," {\n",{"type":51,"tag":1043,"props":2805,"children":2807},{"class":1045,"line":2806},23,[2808,2813,2817,2822,2826],{"type":51,"tag":1043,"props":2809,"children":2810},{"style":1050},[2811],{"type":57,"value":2812},"  echo",{"type":51,"tag":1043,"props":2814,"children":2815},{"style":1056},[2816],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2818,"children":2819},{"style":1103},[2820],{"type":57,"value":2821},"ERROR: could not find amc-run-video-calibration\u002Fscripts\u002Frun_video_calibration.py",{"type":51,"tag":1043,"props":2823,"children":2824},{"style":1056},[2825],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2827,"children":2828},{"style":1056},[2829],{"type":57,"value":2830}," >&2\n",{"type":51,"tag":1043,"props":2832,"children":2834},{"class":1045,"line":2833},24,[2835,2839,2843,2848,2852],{"type":51,"tag":1043,"props":2836,"children":2837},{"style":1050},[2838],{"type":57,"value":2812},{"type":51,"tag":1043,"props":2840,"children":2841},{"style":1056},[2842],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2844,"children":2845},{"style":1103},[2846],{"type":57,"value":2847},"Set AMC_VIDEO_SKILL_DIR to the amc-run-video-calibration skill directory, or run this block from that directory.",{"type":51,"tag":1043,"props":2849,"children":2850},{"style":1056},[2851],{"type":57,"value":1170},{"type":51,"tag":1043,"props":2853,"children":2854},{"style":1056},[2855],{"type":57,"value":2830},{"type":51,"tag":1043,"props":2857,"children":2859},{"class":1045,"line":2858},25,[2860,2865],{"type":51,"tag":1043,"props":2861,"children":2862},{"style":1050},[2863],{"type":57,"value":2864},"  exit",{"type":51,"tag":1043,"props":2866,"children":2867},{"style":1295},[2868],{"type":57,"value":2869}," 1\n",{"type":51,"tag":1043,"props":2871,"children":2873},{"class":1045,"line":2872},26,[2874],{"type":51,"tag":1043,"props":2875,"children":2876},{"style":1056},[2877],{"type":57,"value":2878},"}\n",{"type":51,"tag":1043,"props":2880,"children":2882},{"class":1045,"line":2881},27,[2883],{"type":51,"tag":1043,"props":2884,"children":2885},{"emptyLinePlaceholder":141},[2886],{"type":57,"value":1579},{"type":51,"tag":1043,"props":2888,"children":2890},{"class":1045,"line":2889},28,[2891,2896,2900,2904],{"type":51,"tag":1043,"props":2892,"children":2893},{"style":1147},[2894],{"type":57,"value":2895},"python3",{"type":51,"tag":1043,"props":2897,"children":2898},{"style":1056},[2899],{"type":57,"value":1160},{"type":51,"tag":1043,"props":2901,"children":2902},{"style":1062},[2903],{"type":57,"value":2786},{"type":51,"tag":1043,"props":2905,"children":2906},{"style":1056},[2907],{"type":57,"value":1345},{"type":51,"tag":60,"props":2909,"children":2911},{"id":2910},"success-criteria",[2912],{"type":57,"value":2913},"Success Criteria",{"type":51,"tag":73,"props":2915,"children":2916},{},[2917,2928,2953,2981],{"type":51,"tag":77,"props":2918,"children":2919},{},[2920,2926],{"type":51,"tag":106,"props":2921,"children":2923},{"className":2922},[],[2924],{"type":57,"value":2925},"project_state == \"COMPLETED\"",{"type":57,"value":2927}," after polling.",{"type":51,"tag":77,"props":2929,"children":2930},{},[2931,2933,2938,2940,2945,2947,2952],{"type":57,"value":2932},"If manual alignment was used: ",{"type":51,"tag":106,"props":2934,"children":2936},{"className":2935},[],[2937],{"type":57,"value":709},{"type":57,"value":2939}," contains ",{"type":51,"tag":106,"props":2941,"children":2943},{"className":2942},[],[2944],{"type":57,"value":383},{"type":57,"value":2946}," + ",{"type":51,"tag":106,"props":2948,"children":2950},{"className":2949},[],[2951],{"type":57,"value":405},{"type":57,"value":121},{"type":51,"tag":77,"props":2954,"children":2955},{},[2956,2958],{"type":57,"value":2957},"If GT was uploaded: evaluation returns typical thresholds:\n",{"type":51,"tag":73,"props":2959,"children":2960},{},[2961,2971],{"type":51,"tag":77,"props":2962,"children":2963},{},[2964,2969],{"type":51,"tag":106,"props":2965,"children":2967},{"className":2966},[],[2968],{"type":57,"value":1797},{"type":57,"value":2970}," \u003C 1.5",{"type":51,"tag":77,"props":2972,"children":2973},{},[2974,2979],{"type":51,"tag":106,"props":2975,"children":2977},{"className":2976},[],[2978],{"type":57,"value":1805},{"type":57,"value":2980}," \u003C 5",{"type":51,"tag":77,"props":2982,"children":2983},{},[2984,2986,2991],{"type":57,"value":2985},"No ",{"type":51,"tag":106,"props":2987,"children":2989},{"className":2988},[],[2990],{"type":57,"value":1765},{"type":57,"value":2992}," state.",{"type":51,"tag":60,"props":2994,"children":2996},{"id":2995},"key-output-files-on-server",[2997],{"type":57,"value":2998},"Key Output Files (on server)",{"type":51,"tag":1032,"props":3000,"children":3003},{"className":3001,"code":3002,"language":57},[1712],"projects\u002Fproject_\u003Cproject_id>\u002F\n├── manual_adjustment\u002F\n│   ├── alignment_data.json\n│   └── layout.png\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba\u002F\n│       ├── initial\u002FcamInfo_XX.yaml\n│       └── refined\u002FcamInfo_XX.yaml          # ← final calibration\n└── calibration.log\n",[3004],{"type":51,"tag":106,"props":3005,"children":3006},{"__ignoreMap":1037},[3007],{"type":57,"value":3002},{"type":51,"tag":60,"props":3009,"children":3011},{"id":3010},"troubleshooting",[3012],{"type":57,"value":3013},"Troubleshooting",{"type":51,"tag":299,"props":3015,"children":3016},{},[3017,3033],{"type":51,"tag":303,"props":3018,"children":3019},{},[3020],{"type":51,"tag":307,"props":3021,"children":3022},{},[3023,3028],{"type":51,"tag":311,"props":3024,"children":3025},{},[3026],{"type":57,"value":3027},"Issue",{"type":51,"tag":311,"props":3029,"children":3030},{},[3031],{"type":57,"value":3032},"Fix",{"type":51,"tag":327,"props":3034,"children":3035},{},[3036,3060,3080,3106,3139,3160,3199],{"type":51,"tag":307,"props":3037,"children":3038},{},[3039,3055],{"type":51,"tag":334,"props":3040,"children":3041},{},[3042,3048,3050],{"type":51,"tag":106,"props":3043,"children":3045},{"className":3044},[],[3046],{"type":57,"value":3047},"verify_project",{"type":57,"value":3049}," state not ",{"type":51,"tag":106,"props":3051,"children":3053},{"className":3052},[],[3054],{"type":57,"value":1894},{"type":51,"tag":334,"props":3056,"children":3057},{},[3058],{"type":57,"value":3059},"Confirm videos uploaded and alignment + layout are present (either via API or via UI manual alignment)",{"type":51,"tag":307,"props":3061,"children":3062},{},[3063,3068],{"type":51,"tag":334,"props":3064,"children":3065},{},[3066],{"type":57,"value":3067},"Manual alignment files missing after UI step",{"type":51,"tag":334,"props":3069,"children":3070},{},[3071,3073,3078],{"type":57,"value":3072},"User didn't click Save; also verify ",{"type":51,"tag":106,"props":3074,"children":3076},{"className":3075},[],[3077],{"type":57,"value":709},{"type":57,"value":3079}," exists",{"type":51,"tag":307,"props":3081,"children":3082},{},[3083,3095],{"type":51,"tag":334,"props":3084,"children":3085},{},[3086,3088,3093],{"type":57,"value":3087},"Calibration stuck ",{"type":51,"tag":106,"props":3089,"children":3091},{"className":3090},[],[3092],{"type":57,"value":1749},{"type":57,"value":3094}," > 90 min",{"type":51,"tag":334,"props":3096,"children":3097},{},[3098,3104],{"type":51,"tag":106,"props":3099,"children":3101},{"className":3100},[],[3102],{"type":57,"value":3103},"GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog",{"type":57,"value":3105}," — usually insufficient tracklets (scene too static). See \"Custom Dataset\" guidelines in root README.",{"type":51,"tag":307,"props":3107,"children":3108},{},[3109,3121],{"type":51,"tag":334,"props":3110,"children":3111},{},[3112,3114,3119],{"type":57,"value":3113},"Immediate ",{"type":51,"tag":106,"props":3115,"children":3117},{"className":3116},[],[3118],{"type":57,"value":1765},{"type":57,"value":3120}," state",{"type":51,"tag":334,"props":3122,"children":3123},{},[3124,3126,3131,3132,3137],{"type":57,"value":3125},"Check video naming: must be ",{"type":51,"tag":106,"props":3127,"children":3129},{"className":3128},[],[3130],{"type":57,"value":192},{"type":57,"value":194},{"type":51,"tag":106,"props":3133,"children":3135},{"className":3134},[],[3136],{"type":57,"value":200},{"type":57,"value":3138},", … contiguous",{"type":51,"tag":307,"props":3140,"children":3141},{},[3142,3147],{"type":51,"tag":334,"props":3143,"children":3144},{},[3145],{"type":57,"value":3146},"Low L2 but high reprojection",{"type":51,"tag":334,"props":3148,"children":3149},{},[3150,3152,3158],{"type":57,"value":3151},"Provide explicit ",{"type":51,"tag":106,"props":3153,"children":3155},{"className":3154},[],[3156],{"type":57,"value":3157},"focal_length",{"type":57,"value":3159}," override via Step 3",{"type":51,"tag":307,"props":3161,"children":3162},{},[3163,3168],{"type":51,"tag":334,"props":3164,"children":3165},{},[3166],{"type":57,"value":3167},"VGGT stays non-ready after AMC completes",{"type":51,"tag":334,"props":3169,"children":3170},{},[3171,3176,3178,3183,3185,3190,3192,3197],{"type":51,"tag":106,"props":3172,"children":3174},{"className":3173},[],[3175],{"type":57,"value":1887},{"type":57,"value":3177}," is expected for a new project. After AMC calibration reaches ",{"type":51,"tag":106,"props":3179,"children":3181},{"className":3180},[],[3182],{"type":57,"value":1757},{"type":57,"value":3184},", the project should transition to ",{"type":51,"tag":106,"props":3186,"children":3188},{"className":3187},[],[3189],{"type":57,"value":1894},{"type":57,"value":3191}," before optional VGGT refinement when VGGT is configured. If refinement is required and the state remains ",{"type":51,"tag":106,"props":3193,"children":3195},{"className":3194},[],[3196],{"type":57,"value":1887},{"type":57,"value":3198}," or otherwise non-ready, confirm VGGT setup and model availability with setup skill Step 2 and MS logs.",{"type":51,"tag":307,"props":3200,"children":3201},{},[3202,3207],{"type":51,"tag":334,"props":3203,"children":3204},{},[3205],{"type":57,"value":3206},"Upload timeout",{"type":51,"tag":334,"props":3208,"children":3209},{},[3210,3212,3218,3220,3226],{"type":57,"value":3211},"Large videos — bump ",{"type":51,"tag":106,"props":3213,"children":3215},{"className":3214},[],[3216],{"type":57,"value":3217},"timeout=300",{"type":57,"value":3219}," to e.g. ",{"type":51,"tag":106,"props":3221,"children":3223},{"className":3222},[],[3224],{"type":57,"value":3225},"600",{"type":57,"value":3227}," in the script",{"type":51,"tag":60,"props":3229,"children":3231},{"id":3230},"for-downstream-skills-mv3dt-export",[3232],{"type":57,"value":3233},"For Downstream Skills — MV3DT Export",{"type":51,"tag":67,"props":3235,"children":3236},{},[3237,3239,3244,3246,3251,3253,3258],{"type":57,"value":3238},"A downstream Multi-View 3D Tracking skill fetches the MV3DT-format calibration directly from the microservice (this skill does ",{"type":51,"tag":93,"props":3240,"children":3241},{},[3242],{"type":57,"value":3243},"not",{"type":57,"value":3245}," download it; it returns the ",{"type":51,"tag":106,"props":3247,"children":3249},{"className":3248},[],[3250],{"type":57,"value":591},{"type":57,"value":3252},"). After this skill reports ",{"type":51,"tag":106,"props":3254,"children":3256},{"className":3255},[],[3257],{"type":57,"value":1757},{"type":57,"value":1053},{"type":51,"tag":73,"props":3260,"children":3261},{},[3262,3287],{"type":51,"tag":77,"props":3263,"children":3264},{},[3265,3271,3272,3278,3280,3286],{"type":51,"tag":106,"props":3266,"children":3268},{"className":3267},[],[3269],{"type":57,"value":3270},"GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc",{"type":57,"value":1751},{"type":51,"tag":106,"props":3273,"children":3275},{"className":3274},[],[3276],{"type":57,"value":3277},"mv3dt_output.zip",{"type":57,"value":3279}," (contains ",{"type":51,"tag":106,"props":3281,"children":3283},{"className":3282},[],[3284],{"type":57,"value":3285},"transforms.yml",{"type":57,"value":937},{"type":51,"tag":77,"props":3288,"children":3289},{},[3290,3292,3297,3299,3305,3306,3312],{"type":57,"value":3291},"If VGGT ran to ",{"type":51,"tag":106,"props":3293,"children":3295},{"className":3294},[],[3296],{"type":57,"value":1757},{"type":57,"value":3298}," (Step 10): ",{"type":51,"tag":106,"props":3300,"children":3302},{"className":3301},[],[3303],{"type":57,"value":3304},"?result_type=vggt",{"type":57,"value":1751},{"type":51,"tag":106,"props":3307,"children":3309},{"className":3308},[],[3310],{"type":57,"value":3311},"vggt_mv3dt_output.zip",{"type":57,"value":121},{"type":51,"tag":60,"props":3314,"children":3316},{"id":3315},"related-skills",[3317],{"type":57,"value":3318},"Related Skills",{"type":51,"tag":73,"props":3320,"children":3321},{},[3322,3332,3343],{"type":51,"tag":77,"props":3323,"children":3324},{},[3325,3330],{"type":51,"tag":106,"props":3326,"children":3328},{"className":3327},[],[3329],{"type":57,"value":158},{"type":57,"value":3331}," — start MS + UI first.",{"type":51,"tag":77,"props":3333,"children":3334},{},[3335,3341],{"type":51,"tag":106,"props":3336,"children":3338},{"className":3337},[],[3339],{"type":57,"value":3340},"skills\u002Famc-run-sample-calibration\u002FSKILL.md",{"type":57,"value":3342}," — verify the stack with the bundled sample before trying your own.",{"type":51,"tag":77,"props":3344,"children":3345},{},[3346,3351],{"type":51,"tag":106,"props":3347,"children":3349},{"className":3348},[],[3350],{"type":57,"value":119},{"type":57,"value":3352}," — same calibration tail, but sourcing footage from live RTSP streams through VIOS.",{"type":51,"tag":67,"props":3354,"children":3355},{},[3356,3358,3363],{"type":57,"value":3357},"Root ",{"type":51,"tag":106,"props":3359,"children":3361},{"className":3360},[],[3362],{"type":57,"value":534},{"type":57,"value":3364}," \"Custom Dataset\" and \"Calibration Workflow (UI)\" sections document input-video guidelines and the UI-driven alternative to this API flow.",{"type":51,"tag":3366,"props":3367,"children":3368},"style",{},[3369],{"type":57,"value":3370},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":3372,"total":3465},[3373,3390,3404,3418,3430,3437,3451],{"slug":3374,"name":3374,"fn":3375,"description":3376,"org":3377,"tags":3378,"stars":23,"repoUrl":24,"updatedAt":3389},"accelerated-computing-cudf","accelerate data processing with cuDF","Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV\u002FParquet I\u002FO, nullable semantics, and multi-GPU DataFrame workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3379,3382,3385,3386],{"name":3380,"slug":3381,"type":15},"Data Analysis","data-analysis",{"name":3383,"slug":3384,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":3387,"slug":3388,"type":15},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":3391,"name":3391,"fn":3392,"description":3393,"org":3394,"tags":3395,"stars":23,"repoUrl":24,"updatedAt":3403},"aiq-deploy","deploy and manage NVIDIA AI-Q infrastructure","Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3396,3399,3402],{"name":3397,"slug":3398,"type":15},"Deployment","deployment",{"name":3400,"slug":3401,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-14T05:29:06.667109",{"slug":3405,"name":3405,"fn":3406,"description":3407,"org":3408,"tags":3409,"stars":23,"repoUrl":24,"updatedAt":3417},"aiq-research","conduct deep research with AI-Q","Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3410,3413,3414],{"name":3411,"slug":3412,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":3415,"slug":3416,"type":15},"Research","research","2026-07-14T05:28:06.816956",{"slug":3419,"name":3419,"fn":3420,"description":3421,"org":3422,"tags":3423,"stars":23,"repoUrl":24,"updatedAt":3429},"amc-run-sample-calibration","run AMC sample dataset calibration","Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3424,3425,3426],{"name":3380,"slug":3381,"type":15},{"name":9,"slug":8,"type":15},{"name":3427,"slug":3428,"type":15},"Testing","testing","2026-07-17T05:29:03.913266",{"slug":4,"name":4,"fn":5,"description":6,"org":3431,"tags":3432,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3433,3434,3435,3436],{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":2020,"name":2020,"fn":3438,"description":3439,"org":3440,"tags":3441,"stars":23,"repoUrl":24,"updatedAt":3450},"deploy AutoMagicCalib microservice with Docker","Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3442,3443,3446,3447],{"name":3397,"slug":3398,"type":15},{"name":3444,"slug":3445,"type":15},"Docker","docker",{"name":9,"slug":8,"type":15},{"name":3448,"slug":3449,"type":15},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":3452,"name":3452,"fn":3453,"description":3454,"org":3455,"tags":3456,"stars":23,"repoUrl":24,"updatedAt":3464},"cudaq-guide","develop quantum applications with CUDA-Q","CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3457,3458,3461],{"name":9,"slug":8,"type":15},{"name":3459,"slug":3460,"type":15},"Quantum Computing","quantum-computing",{"name":3462,"slug":3463,"type":15},"Simulation","simulation","2026-07-14T05:26:58.898253",305,{"items":3467,"total":3617},[3468,3486,3501,3512,3524,3538,3551,3565,3576,3585,3599,3608],{"slug":3469,"name":3469,"fn":3470,"description":3471,"org":3472,"tags":3473,"stars":3483,"repoUrl":3484,"updatedAt":3485},"nemoclaw-user-guide","retrieve NemoClaw documentation and configuration","Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3474,3477,3480],{"name":3475,"slug":3476,"type":15},"Documentation","documentation",{"name":3478,"slug":3479,"type":15},"MCP","mcp",{"name":3481,"slug":3482,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":3487,"name":3487,"fn":3488,"description":3489,"org":3490,"tags":3491,"stars":3498,"repoUrl":3499,"updatedAt":3500},"mcore-build-and-dependency","manage Megatron-LM development environments","Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3492,3495,3496],{"name":3493,"slug":3494,"type":15},"Containers","containers",{"name":3397,"slug":3398,"type":15},{"name":3497,"slug":46,"type":15},"Python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":3502,"name":3502,"fn":3503,"description":3504,"org":3505,"tags":3506,"stars":3498,"repoUrl":3499,"updatedAt":3511},"mcore-bump-base-image","update NVIDIA PyTorch base images","Bump the NVIDIA PyTorch base image (`nvcr.io\u002Fnvidia\u002Fpytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker\u002F.ngc_version.dev` and GitLab CI in `.gitlab\u002Fstages\u002F01.build.yml`), the post-bump CI loop (re-run functional tests, refresh golden values, mark broken tests), and the gotchas that bit PRs",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3507,3510],{"name":3508,"slug":3509,"type":15},"CI\u002FCD","ci-cd",{"name":3397,"slug":3398,"type":15},"2026-07-14T05:25:59.97109",{"slug":3513,"name":3513,"fn":3514,"description":3515,"org":3516,"tags":3517,"stars":3498,"repoUrl":3499,"updatedAt":3523},"mcore-cicd","manage CI\u002FCD pipelines for Megatron-LM","CI\u002FCD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request\u002FBRANCH ref — always dry-run and verify the destination first; never run against shared or protected branches), and CI failure investigation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3518,3519,3520],{"name":3508,"slug":3509,"type":15},{"name":3397,"slug":3398,"type":15},{"name":3521,"slug":3522,"type":15},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":3525,"name":3525,"fn":3526,"description":3527,"org":3528,"tags":3529,"stars":3498,"repoUrl":3499,"updatedAt":3537},"mcore-create-issue","investigate CI failures and create issues","Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3530,3533,3534],{"name":3531,"slug":3532,"type":15},"Debugging","debugging",{"name":3521,"slug":3522,"type":15},{"name":3535,"slug":3536,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":3539,"name":3539,"fn":3540,"description":3541,"org":3542,"tags":3543,"stars":3498,"repoUrl":3499,"updatedAt":3550},"mcore-linting-and-formatting","lint and format Megatron-LM code","Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3544,3547],{"name":3545,"slug":3546,"type":15},"Best Practices","best-practices",{"name":3548,"slug":3549,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":3552,"name":3552,"fn":3553,"description":3554,"org":3555,"tags":3556,"stars":3498,"repoUrl":3499,"updatedAt":3564},"mcore-migrate-gpt-to-hybrid","migrate Megatron-LM models to HybridModel","Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3557,3560,3563],{"name":3558,"slug":3559,"type":15},"Machine Learning","machine-learning",{"name":3561,"slug":3562,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:11.777011",{"slug":3566,"name":3566,"fn":3567,"description":3568,"org":3569,"tags":3570,"stars":3498,"repoUrl":3499,"updatedAt":3575},"mcore-onboard-gb200-1node-tests","onboard functional tests for GB200","Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3571,3574],{"name":3572,"slug":3573,"type":15},"QA","qa",{"name":3427,"slug":3428,"type":15},"2026-07-14T05:25:53.673039",{"slug":3577,"name":3577,"fn":3578,"description":3579,"org":3580,"tags":3581,"stars":3498,"repoUrl":3499,"updatedAt":3584},"mcore-run-on-slurm","launch distributed training jobs on SLURM","How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3582,3583],{"name":3397,"slug":3398,"type":15},{"name":3400,"slug":3401,"type":15},"2026-07-14T05:25:49.362534",{"slug":3586,"name":3586,"fn":3587,"description":3588,"org":3589,"tags":3590,"stars":3498,"repoUrl":3499,"updatedAt":3598},"mcore-split-pr","split pull requests to reduce review load","Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3591,3594,3595],{"name":3592,"slug":3593,"type":15},"Code Review","code-review",{"name":3521,"slug":3522,"type":15},{"name":3596,"slug":3597,"type":15},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":3600,"name":3600,"fn":3601,"description":3602,"org":3603,"tags":3604,"stars":3498,"repoUrl":3499,"updatedAt":3607},"mcore-testing","run and manage Megatron-LM tests","Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3605,3606],{"name":3572,"slug":3573,"type":15},{"name":3427,"slug":3428,"type":15},"2026-07-14T05:25:54.928983",{"slug":3609,"name":3609,"fn":3610,"description":3611,"org":3612,"tags":3613,"stars":3498,"repoUrl":3499,"updatedAt":3616},"nightly-sync","manage nightly main-to-dev sync workflows","Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[3614,3615],{"name":13,"slug":14,"type":15},{"name":3508,"slug":3509,"type":15},"2026-07-30T05:29:03.275638",496]