[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-i4h-workflow":3,"mdc--9q5qp5-key":34,"related-repo-nvidia-i4h-workflow":1521,"related-org-nvidia-i4h-workflow":1623},{"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},"i4h-workflow","orchestrate i4h agentic workflows","Overview of `workflows\u002Fagentic\u002F` (IsaacLab-Arena + GR00T\u002Fopenpi). Use when the user asks what i4h workflow is, what's supported, or where to start.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Simulation","simulation",{"name":18,"slug":19,"type":13},"Agents","agents",{"name":21,"slug":22,"type":13},"Engineering","engineering",2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-23T06:06:13.692346","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\u002Fi4h-workflow","---\nname: i4h-workflow\nversion: \"0.6.0\"\ndescription: Overview of `workflows\u002Fagentic\u002F` (IsaacLab-Arena + GR00T\u002Fopenpi). Use when the user asks what i4h workflow is, what's supported, or where to start.\nlicense: Apache-2.0\nmetadata:\n  author: \"Isaac for Healthcare Team \u003Cisaac-for-healthcare-support@nvidia.com>\"\n  tags:\n    - isaac-for-healthcare\n    - i4h\n    - agentic-workflow\n    - robotics\n    - overview\n---\n\n# i4h Agentic Workflow\n\n## Purpose\n\nOrient on the agentic workflow before touching a specific stage: which envs\u002Frobots\u002Fpolicies are supported, how the `workflows\u002Fagentic\u002F` subprojects fit together, and which per-stage skill to invoke next. This skill routes — it runs no pipeline stage itself.\n\n## Base Code\n\nThese steps drive the i4h-workflows base code (the `workflows\u002Fagentic\u002F` tree). To reuse an existing checkout, set `I4H_WORKFLOWS` to its path (no clone happens). Otherwise this resolves the current repo, or clones to `~\u002Fi4h-workflows` — pick that default without prompting. Run every command below from the resolved root:\n\n```bash\n# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\nROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"\nif [ ! -d \"$ROOT\u002Fworkflows\u002Fagentic\" ]; then\n  ROOT=\"${I4H_WORKFLOWS:-$HOME\u002Fi4h-workflows}\"\n  [ -d \"$ROOT\u002Fworkflows\u002Fagentic\" ] || git clone https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows \"$ROOT\"\nfi\nexport I4H_WORKFLOWS=\"$ROOT\"; cd \"$ROOT\"\n```\n\n## Basics\n\n- Env YAMLs at `workflows\u002Fagentic\u002Fconfig\u002Fenvironments\u002F\u003Cenv>.yaml` are the source of truth.\n- Each pipeline stage has its own skill. Compose them or use [[i4h-workflow-e2e]] for full runs.\n- For env authoring or scene-edit source changes, load `skills\u002Fi4h-workflow\u002Freferences\u002Frepo-map.md` before generating code.\n\n## Supported Envs\n\nFallback when `--list-envs` fails (setup incomplete):\n\n| Env | Robot | Policy |\n|---|---|---|\n| `scissor_pick_and_place` | SO-ARM 101 | GR00T N1.5 (N1.7 alternative) |\n| `locomanip_tray_pick_and_place` | Unitree G1 | GR00T N1.6 (shared `policy.locomanip.*`) |\n| `locomanip_push_cart` | Unitree G1 | GR00T N1.6 (shared `policy.locomanip.*`) |\n| `assemble_trocar` | Unitree G1 + Dex hands | GR00T N1.5 (inference-only) |\n| `ultrasound_liver_scan` | Franka-style arm | openpi PI0 |\n| `surgical_reach_psm` | dVRK PSM | GR00T N1.5 or scripted state machine |\n| `surgical_reach_dual_psm` | dVRK dual PSM | GR00T N1.5 or scripted state machine |\n| `surgical_reach_star` | STAR | GR00T N1.5 or scripted state machine |\n| `surgical_lift_block` | dVRK PSM | GR00T N1.5 or scripted state machine |\n| `surgical_lift_needle` | dVRK PSM | GR00T N1.5 or scripted state machine |\n| `surgical_lift_needle_organs` | dVRK PSM | GR00T N1.5 or scripted state machine |\n\n## Run\n\nRun the step below before answering. Each step is a separate bash call; variables persist in the local agent's tmux session.\n\n### Step 1 — list supported envs\n\n```bash\nREPO_ROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"; [ -d \"$REPO_ROOT\u002Fworkflows\u002Fagentic\" ] || REPO_ROOT=\"$HOME\u002Fi4h-workflows\"\n\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Fpolicy\u002Frun.sh\" --list-envs\n```\n\nIf the command fails, use the **Supported Envs** fallback table above.\n\n## Subprojects\n\n| Directory | Purpose |\n|---|---|\n| `workflows\u002Fagentic\u002Farena\u002F` | IsaacLab-Arena envs, scenes, tasks, teleop, record, replay |\n| `workflows\u002Fagentic\u002Fpolicy\u002F` | Policy daemons and train dispatchers |\n| `workflows\u002Fagentic\u002Fdataset\u002F` | HDF5 → LeRobot conversion and visualization |\n| `workflows\u002Fagentic\u002Fmimic\u002F` | HDF5 trajectory expansion |\n| `workflows\u002Fagentic\u002Fannotator\u002F` | VLM success labels and filtering |\n| `workflows\u002Fagentic\u002Fcosmos\u002F` | Optional Cosmos Transfer video augmentation |\n| `workflows\u002Fagentic\u002Fcommon\u002F` | Shared config, messaging, robot constants |\n\n## Skill Index\n\n| Skill | Purpose |\n|---|---|\n| `i4h-workflow-setup` | Install \u002F sync \u002F check third-party deps |\n| `i4h-workflow-create` | Add a new env |\n| `i4h-workflow-scene-edit` | Edit an existing scene \u002F task \u002F camera |\n| `i4h-workflow-dataset-teleop` | Record human demos |\n| `i4h-workflow-dataset-replay` | Replay HDF5 episodes |\n| `i4h-workflow-dataset-mimic` | Expand HDF5 demos with noise |\n| `i4h-workflow-dataset-annotate` | VLM label \u002F filter episodes |\n| `i4h-workflow-dataset-convert` | Convert HDF5 to LeRobot |\n| `i4h-workflow-finetune` | Train supported envs |\n| `i4h-workflow-validate` | Roll out \u002F evaluate policy checkpoints |\n| `i4h-workflow-e2e` | Run the full pipeline |\n| `i4h-lerobot-viz` | Open the LeRobot HTML viewer |\n\n## Prerequisites\n\n- For any hands-on stage, set up the workflow first — see [[i4h-workflow-setup]] (component venvs and third-party checkouts present).\n- Env YAMLs at `workflows\u002Fagentic\u002Fconfig\u002Fenvironments\u002F\u003Cenv>.yaml` are the source of truth.\n\n## Limitations\n\n- Overview\u002Frouting only — each pipeline stage has its own skill; this one performs no recording, training, or rollout.\n\n## Troubleshooting\n\n- **Error:** env not found \u002F unsupported — Cause: typo, unregistered env, or setup incomplete. Fix: run `workflows\u002Fagentic\u002Fpolicy\u002Frun.sh --list-envs`; if that fails, run [[i4h-workflow-setup]] first; otherwise check the **Supported Envs** table.\n\n## Final Response\n\nThe response is incomplete unless it includes all three parts below, each separated by a blank line. Do not reply with prose only or run sections together without spacing.\n\n1. **Orientation** — one short paragraph: env YAMLs, subprojects, sim-to-policy pipeline.\n\n2. **Supported envs** — heading plus markdown table from Step 1 (`--list-envs` output: env, stack, description) or the **Supported Envs** fallback table.\n\n3. **Available skills** — heading plus the full **Skill Index** table copied into the response.\n\nThen (after another blank line) recommend [[i4h-workflow-setup]] if setup is not done, and name one next stage skill matched to the user's goal.\n",{"data":35,"body":45},{"name":4,"version":36,"description":6,"license":26,"metadata":37},"0.6.0",{"author":38,"tags":39},"Isaac for Healthcare Team \u003Cisaac-for-healthcare-support@nvidia.com>",[40,41,42,43,44],"isaac-for-healthcare","i4h","agentic-workflow","robotics","overview",{"type":46,"children":47},"root",[48,57,64,79,85,113,455,461,497,503,516,794,800,805,812,986,998,1004,1144,1150,1375,1381,1399,1405,1413,1419,1446,1452,1457,1510,1515],{"type":49,"tag":50,"props":51,"children":53},"element","h1",{"id":52},"i4h-agentic-workflow",[54],{"type":55,"value":56},"text","i4h Agentic Workflow",{"type":49,"tag":58,"props":59,"children":61},"h2",{"id":60},"purpose",[62],{"type":55,"value":63},"Purpose",{"type":49,"tag":65,"props":66,"children":67},"p",{},[68,70,77],{"type":55,"value":69},"Orient on the agentic workflow before touching a specific stage: which envs\u002Frobots\u002Fpolicies are supported, how the ",{"type":49,"tag":71,"props":72,"children":74},"code",{"className":73},[],[75],{"type":55,"value":76},"workflows\u002Fagentic\u002F",{"type":55,"value":78}," subprojects fit together, and which per-stage skill to invoke next. This skill routes — it runs no pipeline stage itself.",{"type":49,"tag":58,"props":80,"children":82},{"id":81},"base-code",[83],{"type":55,"value":84},"Base Code",{"type":49,"tag":65,"props":86,"children":87},{},[88,90,95,97,103,105,111],{"type":55,"value":89},"These steps drive the i4h-workflows base code (the ",{"type":49,"tag":71,"props":91,"children":93},{"className":92},[],[94],{"type":55,"value":76},{"type":55,"value":96}," tree). To reuse an existing checkout, set ",{"type":49,"tag":71,"props":98,"children":100},{"className":99},[],[101],{"type":55,"value":102},"I4H_WORKFLOWS",{"type":55,"value":104}," to its path (no clone happens). Otherwise this resolves the current repo, or clones to ",{"type":49,"tag":71,"props":106,"children":108},{"className":107},[],[109],{"type":55,"value":110},"~\u002Fi4h-workflows",{"type":55,"value":112}," — pick that default without prompting. Run every command below from the resolved root:",{"type":49,"tag":114,"props":115,"children":120},"pre",{"className":116,"code":117,"language":118,"meta":119,"style":119},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\nROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"\nif [ ! -d \"$ROOT\u002Fworkflows\u002Fagentic\" ]; then\n  ROOT=\"${I4H_WORKFLOWS:-$HOME\u002Fi4h-workflows}\"\n  [ -d \"$ROOT\u002Fworkflows\u002Fagentic\" ] || git clone https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows \"$ROOT\"\nfi\nexport I4H_WORKFLOWS=\"$ROOT\"; cd \"$ROOT\"\n","bash","",[121],{"type":49,"tag":71,"props":122,"children":123},{"__ignoreMap":119},[124,136,226,281,324,392,401],{"type":49,"tag":125,"props":126,"children":129},"span",{"class":127,"line":128},"line",1,[130],{"type":49,"tag":125,"props":131,"children":133},{"style":132},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[134],{"type":55,"value":135},"# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\n",{"type":49,"tag":125,"props":137,"children":139},{"class":127,"line":138},2,[140,146,152,157,161,166,172,177,182,187,192,197,202,207,211,216,221],{"type":49,"tag":125,"props":141,"children":143},{"style":142},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[144],{"type":55,"value":145},"ROOT",{"type":49,"tag":125,"props":147,"children":149},{"style":148},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[150],{"type":55,"value":151},"=",{"type":49,"tag":125,"props":153,"children":154},{"style":148},[155],{"type":55,"value":156},"\"${",{"type":49,"tag":125,"props":158,"children":159},{"style":142},[160],{"type":55,"value":102},{"type":49,"tag":125,"props":162,"children":163},{"style":148},[164],{"type":55,"value":165},":-",{"type":49,"tag":125,"props":167,"children":169},{"style":168},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[170],{"type":55,"value":171},"$(",{"type":49,"tag":125,"props":173,"children":174},{"style":142},[175],{"type":55,"value":176},"git",{"type":49,"tag":125,"props":178,"children":179},{"style":142},[180],{"type":55,"value":181}," rev-parse",{"type":49,"tag":125,"props":183,"children":184},{"style":142},[185],{"type":55,"value":186}," --show-toplevel",{"type":49,"tag":125,"props":188,"children":189},{"style":142},[190],{"type":55,"value":191}," 2",{"type":49,"tag":125,"props":193,"children":194},{"style":168},[195],{"type":55,"value":196},">",{"type":49,"tag":125,"props":198,"children":199},{"style":148},[200],{"type":55,"value":201},"\u002F",{"type":49,"tag":125,"props":203,"children":204},{"style":142},[205],{"type":55,"value":206},"dev",{"type":49,"tag":125,"props":208,"children":209},{"style":148},[210],{"type":55,"value":201},{"type":49,"tag":125,"props":212,"children":213},{"style":142},[214],{"type":55,"value":215},"null",{"type":49,"tag":125,"props":217,"children":218},{"style":168},[219],{"type":55,"value":220},")",{"type":49,"tag":125,"props":222,"children":223},{"style":148},[224],{"type":55,"value":225},"}\"\n",{"type":49,"tag":125,"props":227,"children":229},{"class":127,"line":228},3,[230,236,241,246,251,256,261,266,271,276],{"type":49,"tag":125,"props":231,"children":233},{"style":232},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[234],{"type":55,"value":235},"if",{"type":49,"tag":125,"props":237,"children":238},{"style":148},[239],{"type":55,"value":240}," [",{"type":49,"tag":125,"props":242,"children":243},{"style":148},[244],{"type":55,"value":245}," !",{"type":49,"tag":125,"props":247,"children":248},{"style":148},[249],{"type":55,"value":250}," -d",{"type":49,"tag":125,"props":252,"children":253},{"style":148},[254],{"type":55,"value":255}," \"",{"type":49,"tag":125,"props":257,"children":258},{"style":142},[259],{"type":55,"value":260},"$ROOT",{"type":49,"tag":125,"props":262,"children":263},{"style":168},[264],{"type":55,"value":265},"\u002Fworkflows\u002Fagentic",{"type":49,"tag":125,"props":267,"children":268},{"style":148},[269],{"type":55,"value":270},"\"",{"type":49,"tag":125,"props":272,"children":273},{"style":148},[274],{"type":55,"value":275}," ];",{"type":49,"tag":125,"props":277,"children":278},{"style":232},[279],{"type":55,"value":280}," then\n",{"type":49,"tag":125,"props":282,"children":284},{"class":127,"line":283},4,[285,290,294,298,302,306,311,315,320],{"type":49,"tag":125,"props":286,"children":287},{"style":142},[288],{"type":55,"value":289},"  ROOT",{"type":49,"tag":125,"props":291,"children":292},{"style":148},[293],{"type":55,"value":151},{"type":49,"tag":125,"props":295,"children":296},{"style":148},[297],{"type":55,"value":156},{"type":49,"tag":125,"props":299,"children":300},{"style":142},[301],{"type":55,"value":102},{"type":49,"tag":125,"props":303,"children":304},{"style":148},[305],{"type":55,"value":165},{"type":49,"tag":125,"props":307,"children":308},{"style":142},[309],{"type":55,"value":310},"$HOME",{"type":49,"tag":125,"props":312,"children":313},{"style":148},[314],{"type":55,"value":201},{"type":49,"tag":125,"props":316,"children":317},{"style":142},[318],{"type":55,"value":319},"i4h-workflows",{"type":49,"tag":125,"props":321,"children":322},{"style":148},[323],{"type":55,"value":225},{"type":49,"tag":125,"props":325,"children":327},{"class":127,"line":326},5,[328,333,337,341,345,349,353,358,363,369,374,379,383,387],{"type":49,"tag":125,"props":329,"children":330},{"style":148},[331],{"type":55,"value":332},"  [",{"type":49,"tag":125,"props":334,"children":335},{"style":148},[336],{"type":55,"value":250},{"type":49,"tag":125,"props":338,"children":339},{"style":148},[340],{"type":55,"value":255},{"type":49,"tag":125,"props":342,"children":343},{"style":142},[344],{"type":55,"value":260},{"type":49,"tag":125,"props":346,"children":347},{"style":168},[348],{"type":55,"value":265},{"type":49,"tag":125,"props":350,"children":351},{"style":148},[352],{"type":55,"value":270},{"type":49,"tag":125,"props":354,"children":355},{"style":148},[356],{"type":55,"value":357}," ]",{"type":49,"tag":125,"props":359,"children":360},{"style":148},[361],{"type":55,"value":362}," ||",{"type":49,"tag":125,"props":364,"children":366},{"style":365},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[367],{"type":55,"value":368}," git",{"type":49,"tag":125,"props":370,"children":371},{"style":168},[372],{"type":55,"value":373}," clone",{"type":49,"tag":125,"props":375,"children":376},{"style":168},[377],{"type":55,"value":378}," https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows",{"type":49,"tag":125,"props":380,"children":381},{"style":148},[382],{"type":55,"value":255},{"type":49,"tag":125,"props":384,"children":385},{"style":142},[386],{"type":55,"value":260},{"type":49,"tag":125,"props":388,"children":389},{"style":148},[390],{"type":55,"value":391},"\"\n",{"type":49,"tag":125,"props":393,"children":395},{"class":127,"line":394},6,[396],{"type":49,"tag":125,"props":397,"children":398},{"style":232},[399],{"type":55,"value":400},"fi\n",{"type":49,"tag":125,"props":402,"children":404},{"class":127,"line":403},7,[405,411,416,420,424,428,432,437,443,447,451],{"type":49,"tag":125,"props":406,"children":408},{"style":407},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[409],{"type":55,"value":410},"export",{"type":49,"tag":125,"props":412,"children":413},{"style":142},[414],{"type":55,"value":415}," I4H_WORKFLOWS",{"type":49,"tag":125,"props":417,"children":418},{"style":148},[419],{"type":55,"value":151},{"type":49,"tag":125,"props":421,"children":422},{"style":148},[423],{"type":55,"value":270},{"type":49,"tag":125,"props":425,"children":426},{"style":142},[427],{"type":55,"value":260},{"type":49,"tag":125,"props":429,"children":430},{"style":148},[431],{"type":55,"value":270},{"type":49,"tag":125,"props":433,"children":434},{"style":148},[435],{"type":55,"value":436},";",{"type":49,"tag":125,"props":438,"children":440},{"style":439},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[441],{"type":55,"value":442}," cd",{"type":49,"tag":125,"props":444,"children":445},{"style":148},[446],{"type":55,"value":255},{"type":49,"tag":125,"props":448,"children":449},{"style":142},[450],{"type":55,"value":260},{"type":49,"tag":125,"props":452,"children":453},{"style":148},[454],{"type":55,"value":391},{"type":49,"tag":58,"props":456,"children":458},{"id":457},"basics",[459],{"type":55,"value":460},"Basics",{"type":49,"tag":462,"props":463,"children":464},"ul",{},[465,479,484],{"type":49,"tag":466,"props":467,"children":468},"li",{},[469,471,477],{"type":55,"value":470},"Env YAMLs at ",{"type":49,"tag":71,"props":472,"children":474},{"className":473},[],[475],{"type":55,"value":476},"workflows\u002Fagentic\u002Fconfig\u002Fenvironments\u002F\u003Cenv>.yaml",{"type":55,"value":478}," are the source of truth.",{"type":49,"tag":466,"props":480,"children":481},{},[482],{"type":55,"value":483},"Each pipeline stage has its own skill. Compose them or use [[i4h-workflow-e2e]] for full runs.",{"type":49,"tag":466,"props":485,"children":486},{},[487,489,495],{"type":55,"value":488},"For env authoring or scene-edit source changes, load ",{"type":49,"tag":71,"props":490,"children":492},{"className":491},[],[493],{"type":55,"value":494},"skills\u002Fi4h-workflow\u002Freferences\u002Frepo-map.md",{"type":55,"value":496}," before generating code.",{"type":49,"tag":58,"props":498,"children":500},{"id":499},"supported-envs",[501],{"type":55,"value":502},"Supported Envs",{"type":49,"tag":65,"props":504,"children":505},{},[506,508,514],{"type":55,"value":507},"Fallback when ",{"type":49,"tag":71,"props":509,"children":511},{"className":510},[],[512],{"type":55,"value":513},"--list-envs",{"type":55,"value":515}," fails (setup incomplete):",{"type":49,"tag":517,"props":518,"children":519},"table",{},[520,544],{"type":49,"tag":521,"props":522,"children":523},"thead",{},[524],{"type":49,"tag":525,"props":526,"children":527},"tr",{},[528,534,539],{"type":49,"tag":529,"props":530,"children":531},"th",{},[532],{"type":55,"value":533},"Env",{"type":49,"tag":529,"props":535,"children":536},{},[537],{"type":55,"value":538},"Robot",{"type":49,"tag":529,"props":540,"children":541},{},[542],{"type":55,"value":543},"Policy",{"type":49,"tag":545,"props":546,"children":547},"tbody",{},[548,571,600,626,648,670,692,713,734,754,774],{"type":49,"tag":525,"props":549,"children":550},{},[551,561,566],{"type":49,"tag":552,"props":553,"children":554},"td",{},[555],{"type":49,"tag":71,"props":556,"children":558},{"className":557},[],[559],{"type":55,"value":560},"scissor_pick_and_place",{"type":49,"tag":552,"props":562,"children":563},{},[564],{"type":55,"value":565},"SO-ARM 101",{"type":49,"tag":552,"props":567,"children":568},{},[569],{"type":55,"value":570},"GR00T N1.5 (N1.7 alternative)",{"type":49,"tag":525,"props":572,"children":573},{},[574,583,588],{"type":49,"tag":552,"props":575,"children":576},{},[577],{"type":49,"tag":71,"props":578,"children":580},{"className":579},[],[581],{"type":55,"value":582},"locomanip_tray_pick_and_place",{"type":49,"tag":552,"props":584,"children":585},{},[586],{"type":55,"value":587},"Unitree G1",{"type":49,"tag":552,"props":589,"children":590},{},[591,593,599],{"type":55,"value":592},"GR00T N1.6 (shared ",{"type":49,"tag":71,"props":594,"children":596},{"className":595},[],[597],{"type":55,"value":598},"policy.locomanip.*",{"type":55,"value":220},{"type":49,"tag":525,"props":601,"children":602},{},[603,612,616],{"type":49,"tag":552,"props":604,"children":605},{},[606],{"type":49,"tag":71,"props":607,"children":609},{"className":608},[],[610],{"type":55,"value":611},"locomanip_push_cart",{"type":49,"tag":552,"props":613,"children":614},{},[615],{"type":55,"value":587},{"type":49,"tag":552,"props":617,"children":618},{},[619,620,625],{"type":55,"value":592},{"type":49,"tag":71,"props":621,"children":623},{"className":622},[],[624],{"type":55,"value":598},{"type":55,"value":220},{"type":49,"tag":525,"props":627,"children":628},{},[629,638,643],{"type":49,"tag":552,"props":630,"children":631},{},[632],{"type":49,"tag":71,"props":633,"children":635},{"className":634},[],[636],{"type":55,"value":637},"assemble_trocar",{"type":49,"tag":552,"props":639,"children":640},{},[641],{"type":55,"value":642},"Unitree G1 + Dex hands",{"type":49,"tag":552,"props":644,"children":645},{},[646],{"type":55,"value":647},"GR00T N1.5 (inference-only)",{"type":49,"tag":525,"props":649,"children":650},{},[651,660,665],{"type":49,"tag":552,"props":652,"children":653},{},[654],{"type":49,"tag":71,"props":655,"children":657},{"className":656},[],[658],{"type":55,"value":659},"ultrasound_liver_scan",{"type":49,"tag":552,"props":661,"children":662},{},[663],{"type":55,"value":664},"Franka-style arm",{"type":49,"tag":552,"props":666,"children":667},{},[668],{"type":55,"value":669},"openpi PI0",{"type":49,"tag":525,"props":671,"children":672},{},[673,682,687],{"type":49,"tag":552,"props":674,"children":675},{},[676],{"type":49,"tag":71,"props":677,"children":679},{"className":678},[],[680],{"type":55,"value":681},"surgical_reach_psm",{"type":49,"tag":552,"props":683,"children":684},{},[685],{"type":55,"value":686},"dVRK PSM",{"type":49,"tag":552,"props":688,"children":689},{},[690],{"type":55,"value":691},"GR00T N1.5 or scripted state machine",{"type":49,"tag":525,"props":693,"children":694},{},[695,704,709],{"type":49,"tag":552,"props":696,"children":697},{},[698],{"type":49,"tag":71,"props":699,"children":701},{"className":700},[],[702],{"type":55,"value":703},"surgical_reach_dual_psm",{"type":49,"tag":552,"props":705,"children":706},{},[707],{"type":55,"value":708},"dVRK dual PSM",{"type":49,"tag":552,"props":710,"children":711},{},[712],{"type":55,"value":691},{"type":49,"tag":525,"props":714,"children":715},{},[716,725,730],{"type":49,"tag":552,"props":717,"children":718},{},[719],{"type":49,"tag":71,"props":720,"children":722},{"className":721},[],[723],{"type":55,"value":724},"surgical_reach_star",{"type":49,"tag":552,"props":726,"children":727},{},[728],{"type":55,"value":729},"STAR",{"type":49,"tag":552,"props":731,"children":732},{},[733],{"type":55,"value":691},{"type":49,"tag":525,"props":735,"children":736},{},[737,746,750],{"type":49,"tag":552,"props":738,"children":739},{},[740],{"type":49,"tag":71,"props":741,"children":743},{"className":742},[],[744],{"type":55,"value":745},"surgical_lift_block",{"type":49,"tag":552,"props":747,"children":748},{},[749],{"type":55,"value":686},{"type":49,"tag":552,"props":751,"children":752},{},[753],{"type":55,"value":691},{"type":49,"tag":525,"props":755,"children":756},{},[757,766,770],{"type":49,"tag":552,"props":758,"children":759},{},[760],{"type":49,"tag":71,"props":761,"children":763},{"className":762},[],[764],{"type":55,"value":765},"surgical_lift_needle",{"type":49,"tag":552,"props":767,"children":768},{},[769],{"type":55,"value":686},{"type":49,"tag":552,"props":771,"children":772},{},[773],{"type":55,"value":691},{"type":49,"tag":525,"props":775,"children":776},{},[777,786,790],{"type":49,"tag":552,"props":778,"children":779},{},[780],{"type":49,"tag":71,"props":781,"children":783},{"className":782},[],[784],{"type":55,"value":785},"surgical_lift_needle_organs",{"type":49,"tag":552,"props":787,"children":788},{},[789],{"type":55,"value":686},{"type":49,"tag":552,"props":791,"children":792},{},[793],{"type":55,"value":691},{"type":49,"tag":58,"props":795,"children":797},{"id":796},"run",[798],{"type":55,"value":799},"Run",{"type":49,"tag":65,"props":801,"children":802},{},[803],{"type":55,"value":804},"Run the step below before answering. Each step is a separate bash call; variables persist in the local agent's tmux session.",{"type":49,"tag":806,"props":807,"children":809},"h3",{"id":808},"step-1-list-supported-envs",[810],{"type":55,"value":811},"Step 1 — list supported envs",{"type":49,"tag":114,"props":813,"children":815},{"className":116,"code":814,"language":118,"meta":119,"style":119},"REPO_ROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"; [ -d \"$REPO_ROOT\u002Fworkflows\u002Fagentic\" ] || REPO_ROOT=\"$HOME\u002Fi4h-workflows\"\n\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Fpolicy\u002Frun.sh\" --list-envs\n",[816],{"type":49,"tag":71,"props":817,"children":818},{"__ignoreMap":119},[819,955],{"type":49,"tag":125,"props":820,"children":821},{"class":127,"line":128},[822,827,831,835,839,843,847,851,855,859,863,867,871,875,879,883,887,892,896,900,904,908,913,917,921,925,929,934,938,942,946,951],{"type":49,"tag":125,"props":823,"children":824},{"style":142},[825],{"type":55,"value":826},"REPO_ROOT",{"type":49,"tag":125,"props":828,"children":829},{"style":148},[830],{"type":55,"value":151},{"type":49,"tag":125,"props":832,"children":833},{"style":148},[834],{"type":55,"value":156},{"type":49,"tag":125,"props":836,"children":837},{"style":142},[838],{"type":55,"value":102},{"type":49,"tag":125,"props":840,"children":841},{"style":148},[842],{"type":55,"value":165},{"type":49,"tag":125,"props":844,"children":845},{"style":168},[846],{"type":55,"value":171},{"type":49,"tag":125,"props":848,"children":849},{"style":142},[850],{"type":55,"value":176},{"type":49,"tag":125,"props":852,"children":853},{"style":142},[854],{"type":55,"value":181},{"type":49,"tag":125,"props":856,"children":857},{"style":142},[858],{"type":55,"value":186},{"type":49,"tag":125,"props":860,"children":861},{"style":142},[862],{"type":55,"value":191},{"type":49,"tag":125,"props":864,"children":865},{"style":168},[866],{"type":55,"value":196},{"type":49,"tag":125,"props":868,"children":869},{"style":148},[870],{"type":55,"value":201},{"type":49,"tag":125,"props":872,"children":873},{"style":142},[874],{"type":55,"value":206},{"type":49,"tag":125,"props":876,"children":877},{"style":148},[878],{"type":55,"value":201},{"type":49,"tag":125,"props":880,"children":881},{"style":142},[882],{"type":55,"value":215},{"type":49,"tag":125,"props":884,"children":885},{"style":168},[886],{"type":55,"value":220},{"type":49,"tag":125,"props":888,"children":889},{"style":148},[890],{"type":55,"value":891},"}\"",{"type":49,"tag":125,"props":893,"children":894},{"style":148},[895],{"type":55,"value":436},{"type":49,"tag":125,"props":897,"children":898},{"style":148},[899],{"type":55,"value":240},{"type":49,"tag":125,"props":901,"children":902},{"style":148},[903],{"type":55,"value":250},{"type":49,"tag":125,"props":905,"children":906},{"style":148},[907],{"type":55,"value":255},{"type":49,"tag":125,"props":909,"children":910},{"style":142},[911],{"type":55,"value":912},"$REPO_ROOT",{"type":49,"tag":125,"props":914,"children":915},{"style":168},[916],{"type":55,"value":265},{"type":49,"tag":125,"props":918,"children":919},{"style":148},[920],{"type":55,"value":270},{"type":49,"tag":125,"props":922,"children":923},{"style":148},[924],{"type":55,"value":357},{"type":49,"tag":125,"props":926,"children":927},{"style":148},[928],{"type":55,"value":362},{"type":49,"tag":125,"props":930,"children":931},{"style":142},[932],{"type":55,"value":933}," REPO_ROOT",{"type":49,"tag":125,"props":935,"children":936},{"style":148},[937],{"type":55,"value":151},{"type":49,"tag":125,"props":939,"children":940},{"style":148},[941],{"type":55,"value":270},{"type":49,"tag":125,"props":943,"children":944},{"style":142},[945],{"type":55,"value":310},{"type":49,"tag":125,"props":947,"children":948},{"style":168},[949],{"type":55,"value":950},"\u002Fi4h-workflows",{"type":49,"tag":125,"props":952,"children":953},{"style":148},[954],{"type":55,"value":391},{"type":49,"tag":125,"props":956,"children":957},{"class":127,"line":138},[958,962,967,971,976,981],{"type":49,"tag":125,"props":959,"children":960},{"style":365},[961],{"type":55,"value":270},{"type":49,"tag":125,"props":963,"children":964},{"style":148},[965],{"type":55,"value":966},"${",{"type":49,"tag":125,"props":968,"children":969},{"style":142},[970],{"type":55,"value":826},{"type":49,"tag":125,"props":972,"children":973},{"style":148},[974],{"type":55,"value":975},"}",{"type":49,"tag":125,"props":977,"children":978},{"style":365},[979],{"type":55,"value":980},"\u002Fworkflows\u002Fagentic\u002Fpolicy\u002Frun.sh\"",{"type":49,"tag":125,"props":982,"children":983},{"style":168},[984],{"type":55,"value":985}," --list-envs\n",{"type":49,"tag":65,"props":987,"children":988},{},[989,991,996],{"type":55,"value":990},"If the command fails, use the ",{"type":49,"tag":992,"props":993,"children":994},"strong",{},[995],{"type":55,"value":502},{"type":55,"value":997}," fallback table above.",{"type":49,"tag":58,"props":999,"children":1001},{"id":1000},"subprojects",[1002],{"type":55,"value":1003},"Subprojects",{"type":49,"tag":517,"props":1005,"children":1006},{},[1007,1022],{"type":49,"tag":521,"props":1008,"children":1009},{},[1010],{"type":49,"tag":525,"props":1011,"children":1012},{},[1013,1018],{"type":49,"tag":529,"props":1014,"children":1015},{},[1016],{"type":55,"value":1017},"Directory",{"type":49,"tag":529,"props":1019,"children":1020},{},[1021],{"type":55,"value":63},{"type":49,"tag":545,"props":1023,"children":1024},{},[1025,1042,1059,1076,1093,1110,1127],{"type":49,"tag":525,"props":1026,"children":1027},{},[1028,1037],{"type":49,"tag":552,"props":1029,"children":1030},{},[1031],{"type":49,"tag":71,"props":1032,"children":1034},{"className":1033},[],[1035],{"type":55,"value":1036},"workflows\u002Fagentic\u002Farena\u002F",{"type":49,"tag":552,"props":1038,"children":1039},{},[1040],{"type":55,"value":1041},"IsaacLab-Arena envs, scenes, tasks, teleop, record, replay",{"type":49,"tag":525,"props":1043,"children":1044},{},[1045,1054],{"type":49,"tag":552,"props":1046,"children":1047},{},[1048],{"type":49,"tag":71,"props":1049,"children":1051},{"className":1050},[],[1052],{"type":55,"value":1053},"workflows\u002Fagentic\u002Fpolicy\u002F",{"type":49,"tag":552,"props":1055,"children":1056},{},[1057],{"type":55,"value":1058},"Policy daemons and train dispatchers",{"type":49,"tag":525,"props":1060,"children":1061},{},[1062,1071],{"type":49,"tag":552,"props":1063,"children":1064},{},[1065],{"type":49,"tag":71,"props":1066,"children":1068},{"className":1067},[],[1069],{"type":55,"value":1070},"workflows\u002Fagentic\u002Fdataset\u002F",{"type":49,"tag":552,"props":1072,"children":1073},{},[1074],{"type":55,"value":1075},"HDF5 → LeRobot conversion and visualization",{"type":49,"tag":525,"props":1077,"children":1078},{},[1079,1088],{"type":49,"tag":552,"props":1080,"children":1081},{},[1082],{"type":49,"tag":71,"props":1083,"children":1085},{"className":1084},[],[1086],{"type":55,"value":1087},"workflows\u002Fagentic\u002Fmimic\u002F",{"type":49,"tag":552,"props":1089,"children":1090},{},[1091],{"type":55,"value":1092},"HDF5 trajectory expansion",{"type":49,"tag":525,"props":1094,"children":1095},{},[1096,1105],{"type":49,"tag":552,"props":1097,"children":1098},{},[1099],{"type":49,"tag":71,"props":1100,"children":1102},{"className":1101},[],[1103],{"type":55,"value":1104},"workflows\u002Fagentic\u002Fannotator\u002F",{"type":49,"tag":552,"props":1106,"children":1107},{},[1108],{"type":55,"value":1109},"VLM success labels and filtering",{"type":49,"tag":525,"props":1111,"children":1112},{},[1113,1122],{"type":49,"tag":552,"props":1114,"children":1115},{},[1116],{"type":49,"tag":71,"props":1117,"children":1119},{"className":1118},[],[1120],{"type":55,"value":1121},"workflows\u002Fagentic\u002Fcosmos\u002F",{"type":49,"tag":552,"props":1123,"children":1124},{},[1125],{"type":55,"value":1126},"Optional Cosmos Transfer video augmentation",{"type":49,"tag":525,"props":1128,"children":1129},{},[1130,1139],{"type":49,"tag":552,"props":1131,"children":1132},{},[1133],{"type":49,"tag":71,"props":1134,"children":1136},{"className":1135},[],[1137],{"type":55,"value":1138},"workflows\u002Fagentic\u002Fcommon\u002F",{"type":49,"tag":552,"props":1140,"children":1141},{},[1142],{"type":55,"value":1143},"Shared config, messaging, robot constants",{"type":49,"tag":58,"props":1145,"children":1147},{"id":1146},"skill-index",[1148],{"type":55,"value":1149},"Skill Index",{"type":49,"tag":517,"props":1151,"children":1152},{},[1153,1168],{"type":49,"tag":521,"props":1154,"children":1155},{},[1156],{"type":49,"tag":525,"props":1157,"children":1158},{},[1159,1164],{"type":49,"tag":529,"props":1160,"children":1161},{},[1162],{"type":55,"value":1163},"Skill",{"type":49,"tag":529,"props":1165,"children":1166},{},[1167],{"type":55,"value":63},{"type":49,"tag":545,"props":1169,"children":1170},{},[1171,1188,1205,1222,1239,1256,1273,1290,1307,1324,1341,1358],{"type":49,"tag":525,"props":1172,"children":1173},{},[1174,1183],{"type":49,"tag":552,"props":1175,"children":1176},{},[1177],{"type":49,"tag":71,"props":1178,"children":1180},{"className":1179},[],[1181],{"type":55,"value":1182},"i4h-workflow-setup",{"type":49,"tag":552,"props":1184,"children":1185},{},[1186],{"type":55,"value":1187},"Install \u002F sync \u002F check third-party deps",{"type":49,"tag":525,"props":1189,"children":1190},{},[1191,1200],{"type":49,"tag":552,"props":1192,"children":1193},{},[1194],{"type":49,"tag":71,"props":1195,"children":1197},{"className":1196},[],[1198],{"type":55,"value":1199},"i4h-workflow-create",{"type":49,"tag":552,"props":1201,"children":1202},{},[1203],{"type":55,"value":1204},"Add a new env",{"type":49,"tag":525,"props":1206,"children":1207},{},[1208,1217],{"type":49,"tag":552,"props":1209,"children":1210},{},[1211],{"type":49,"tag":71,"props":1212,"children":1214},{"className":1213},[],[1215],{"type":55,"value":1216},"i4h-workflow-scene-edit",{"type":49,"tag":552,"props":1218,"children":1219},{},[1220],{"type":55,"value":1221},"Edit an existing scene \u002F task \u002F camera",{"type":49,"tag":525,"props":1223,"children":1224},{},[1225,1234],{"type":49,"tag":552,"props":1226,"children":1227},{},[1228],{"type":49,"tag":71,"props":1229,"children":1231},{"className":1230},[],[1232],{"type":55,"value":1233},"i4h-workflow-dataset-teleop",{"type":49,"tag":552,"props":1235,"children":1236},{},[1237],{"type":55,"value":1238},"Record human demos",{"type":49,"tag":525,"props":1240,"children":1241},{},[1242,1251],{"type":49,"tag":552,"props":1243,"children":1244},{},[1245],{"type":49,"tag":71,"props":1246,"children":1248},{"className":1247},[],[1249],{"type":55,"value":1250},"i4h-workflow-dataset-replay",{"type":49,"tag":552,"props":1252,"children":1253},{},[1254],{"type":55,"value":1255},"Replay HDF5 episodes",{"type":49,"tag":525,"props":1257,"children":1258},{},[1259,1268],{"type":49,"tag":552,"props":1260,"children":1261},{},[1262],{"type":49,"tag":71,"props":1263,"children":1265},{"className":1264},[],[1266],{"type":55,"value":1267},"i4h-workflow-dataset-mimic",{"type":49,"tag":552,"props":1269,"children":1270},{},[1271],{"type":55,"value":1272},"Expand HDF5 demos with noise",{"type":49,"tag":525,"props":1274,"children":1275},{},[1276,1285],{"type":49,"tag":552,"props":1277,"children":1278},{},[1279],{"type":49,"tag":71,"props":1280,"children":1282},{"className":1281},[],[1283],{"type":55,"value":1284},"i4h-workflow-dataset-annotate",{"type":49,"tag":552,"props":1286,"children":1287},{},[1288],{"type":55,"value":1289},"VLM label \u002F filter episodes",{"type":49,"tag":525,"props":1291,"children":1292},{},[1293,1302],{"type":49,"tag":552,"props":1294,"children":1295},{},[1296],{"type":49,"tag":71,"props":1297,"children":1299},{"className":1298},[],[1300],{"type":55,"value":1301},"i4h-workflow-dataset-convert",{"type":49,"tag":552,"props":1303,"children":1304},{},[1305],{"type":55,"value":1306},"Convert HDF5 to LeRobot",{"type":49,"tag":525,"props":1308,"children":1309},{},[1310,1319],{"type":49,"tag":552,"props":1311,"children":1312},{},[1313],{"type":49,"tag":71,"props":1314,"children":1316},{"className":1315},[],[1317],{"type":55,"value":1318},"i4h-workflow-finetune",{"type":49,"tag":552,"props":1320,"children":1321},{},[1322],{"type":55,"value":1323},"Train supported envs",{"type":49,"tag":525,"props":1325,"children":1326},{},[1327,1336],{"type":49,"tag":552,"props":1328,"children":1329},{},[1330],{"type":49,"tag":71,"props":1331,"children":1333},{"className":1332},[],[1334],{"type":55,"value":1335},"i4h-workflow-validate",{"type":49,"tag":552,"props":1337,"children":1338},{},[1339],{"type":55,"value":1340},"Roll out \u002F evaluate policy checkpoints",{"type":49,"tag":525,"props":1342,"children":1343},{},[1344,1353],{"type":49,"tag":552,"props":1345,"children":1346},{},[1347],{"type":49,"tag":71,"props":1348,"children":1350},{"className":1349},[],[1351],{"type":55,"value":1352},"i4h-workflow-e2e",{"type":49,"tag":552,"props":1354,"children":1355},{},[1356],{"type":55,"value":1357},"Run the full pipeline",{"type":49,"tag":525,"props":1359,"children":1360},{},[1361,1370],{"type":49,"tag":552,"props":1362,"children":1363},{},[1364],{"type":49,"tag":71,"props":1365,"children":1367},{"className":1366},[],[1368],{"type":55,"value":1369},"i4h-lerobot-viz",{"type":49,"tag":552,"props":1371,"children":1372},{},[1373],{"type":55,"value":1374},"Open the LeRobot HTML viewer",{"type":49,"tag":58,"props":1376,"children":1378},{"id":1377},"prerequisites",[1379],{"type":55,"value":1380},"Prerequisites",{"type":49,"tag":462,"props":1382,"children":1383},{},[1384,1389],{"type":49,"tag":466,"props":1385,"children":1386},{},[1387],{"type":55,"value":1388},"For any hands-on stage, set up the workflow first — see [[i4h-workflow-setup]] (component venvs and third-party checkouts present).",{"type":49,"tag":466,"props":1390,"children":1391},{},[1392,1393,1398],{"type":55,"value":470},{"type":49,"tag":71,"props":1394,"children":1396},{"className":1395},[],[1397],{"type":55,"value":476},{"type":55,"value":478},{"type":49,"tag":58,"props":1400,"children":1402},{"id":1401},"limitations",[1403],{"type":55,"value":1404},"Limitations",{"type":49,"tag":462,"props":1406,"children":1407},{},[1408],{"type":49,"tag":466,"props":1409,"children":1410},{},[1411],{"type":55,"value":1412},"Overview\u002Frouting only — each pipeline stage has its own skill; this one performs no recording, training, or rollout.",{"type":49,"tag":58,"props":1414,"children":1416},{"id":1415},"troubleshooting",[1417],{"type":55,"value":1418},"Troubleshooting",{"type":49,"tag":462,"props":1420,"children":1421},{},[1422],{"type":49,"tag":466,"props":1423,"children":1424},{},[1425,1430,1432,1438,1440,1444],{"type":49,"tag":992,"props":1426,"children":1427},{},[1428],{"type":55,"value":1429},"Error:",{"type":55,"value":1431}," env not found \u002F unsupported — Cause: typo, unregistered env, or setup incomplete. Fix: run ",{"type":49,"tag":71,"props":1433,"children":1435},{"className":1434},[],[1436],{"type":55,"value":1437},"workflows\u002Fagentic\u002Fpolicy\u002Frun.sh --list-envs",{"type":55,"value":1439},"; if that fails, run [[i4h-workflow-setup]] first; otherwise check the ",{"type":49,"tag":992,"props":1441,"children":1442},{},[1443],{"type":55,"value":502},{"type":55,"value":1445}," table.",{"type":49,"tag":58,"props":1447,"children":1449},{"id":1448},"final-response",[1450],{"type":55,"value":1451},"Final Response",{"type":49,"tag":65,"props":1453,"children":1454},{},[1455],{"type":55,"value":1456},"The response is incomplete unless it includes all three parts below, each separated by a blank line. Do not reply with prose only or run sections together without spacing.",{"type":49,"tag":1458,"props":1459,"children":1460},"ol",{},[1461,1471,1494],{"type":49,"tag":466,"props":1462,"children":1463},{},[1464,1469],{"type":49,"tag":992,"props":1465,"children":1466},{},[1467],{"type":55,"value":1468},"Orientation",{"type":55,"value":1470}," — one short paragraph: env YAMLs, subprojects, sim-to-policy pipeline.",{"type":49,"tag":466,"props":1472,"children":1473},{},[1474,1479,1481,1486,1488,1492],{"type":49,"tag":992,"props":1475,"children":1476},{},[1477],{"type":55,"value":1478},"Supported envs",{"type":55,"value":1480}," — heading plus markdown table from Step 1 (",{"type":49,"tag":71,"props":1482,"children":1484},{"className":1483},[],[1485],{"type":55,"value":513},{"type":55,"value":1487}," output: env, stack, description) or the ",{"type":49,"tag":992,"props":1489,"children":1490},{},[1491],{"type":55,"value":502},{"type":55,"value":1493}," fallback table.",{"type":49,"tag":466,"props":1495,"children":1496},{},[1497,1502,1504,1508],{"type":49,"tag":992,"props":1498,"children":1499},{},[1500],{"type":55,"value":1501},"Available skills",{"type":55,"value":1503}," — heading plus the full ",{"type":49,"tag":992,"props":1505,"children":1506},{},[1507],{"type":55,"value":1149},{"type":55,"value":1509}," table copied into the response.",{"type":49,"tag":65,"props":1511,"children":1512},{},[1513],{"type":55,"value":1514},"Then (after another blank line) recommend [[i4h-workflow-setup]] if setup is not done, and name one next stage skill matched to the user's goal.",{"type":49,"tag":1516,"props":1517,"children":1518},"style",{},[1519],{"type":55,"value":1520},"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":1522,"total":1622},[1523,1540,1554,1566,1578,1595,1610],{"slug":1524,"name":1524,"fn":1525,"description":1526,"org":1527,"tags":1528,"stars":23,"repoUrl":24,"updatedAt":1539},"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},[1529,1532,1535,1536],{"name":1530,"slug":1531,"type":13},"Data Analysis","data-analysis",{"name":1533,"slug":1534,"type":13},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":13},{"name":1537,"slug":1538,"type":13},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":1541,"name":1541,"fn":1542,"description":1543,"org":1544,"tags":1545,"stars":23,"repoUrl":24,"updatedAt":1553},"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},[1546,1549,1552],{"name":1547,"slug":1548,"type":13},"Deployment","deployment",{"name":1550,"slug":1551,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-14T05:29:06.667109",{"slug":1555,"name":1555,"fn":1556,"description":1557,"org":1558,"tags":1559,"stars":23,"repoUrl":24,"updatedAt":1565},"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},[1560,1561,1562],{"name":18,"slug":19,"type":13},{"name":9,"slug":8,"type":13},{"name":1563,"slug":1564,"type":13},"Research","research","2026-07-14T05:28:06.816956",{"slug":1567,"name":1567,"fn":1568,"description":1569,"org":1570,"tags":1571,"stars":23,"repoUrl":24,"updatedAt":1577},"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},[1572,1573,1574],{"name":1530,"slug":1531,"type":13},{"name":9,"slug":8,"type":13},{"name":1575,"slug":1576,"type":13},"Testing","testing","2026-07-17T05:29:03.913266",{"slug":1579,"name":1579,"fn":1580,"description":1581,"org":1582,"tags":1583,"stars":23,"repoUrl":24,"updatedAt":1594},"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},[1584,1587,1590,1591],{"name":1585,"slug":1586,"type":13},"Automation","automation",{"name":1588,"slug":1589,"type":13},"Imaging","imaging",{"name":9,"slug":8,"type":13},{"name":1592,"slug":1593,"type":13},"Video","video","2026-07-17T05:28:53.905004",{"slug":1596,"name":1596,"fn":1597,"description":1598,"org":1599,"tags":1600,"stars":23,"repoUrl":24,"updatedAt":1609},"amc-setup-calibration-stack","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},[1601,1602,1605,1606],{"name":1547,"slug":1548,"type":13},{"name":1603,"slug":1604,"type":13},"Docker","docker",{"name":9,"slug":8,"type":13},{"name":1607,"slug":1608,"type":13},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":1611,"name":1611,"fn":1612,"description":1613,"org":1614,"tags":1615,"stars":23,"repoUrl":24,"updatedAt":1621},"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},[1616,1617,1620],{"name":9,"slug":8,"type":13},{"name":1618,"slug":1619,"type":13},"Quantum Computing","quantum-computing",{"name":15,"slug":16,"type":13},"2026-07-14T05:26:58.898253",305,{"items":1624,"total":1775},[1625,1643,1659,1670,1682,1696,1709,1723,1734,1743,1757,1766],{"slug":1626,"name":1626,"fn":1627,"description":1628,"org":1629,"tags":1630,"stars":1640,"repoUrl":1641,"updatedAt":1642},"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},[1631,1634,1637],{"name":1632,"slug":1633,"type":13},"Documentation","documentation",{"name":1635,"slug":1636,"type":13},"MCP","mcp",{"name":1638,"slug":1639,"type":13},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":1644,"name":1644,"fn":1645,"description":1646,"org":1647,"tags":1648,"stars":1656,"repoUrl":1657,"updatedAt":1658},"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},[1649,1652,1653],{"name":1650,"slug":1651,"type":13},"Containers","containers",{"name":1547,"slug":1548,"type":13},{"name":1654,"slug":1655,"type":13},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":1660,"name":1660,"fn":1661,"description":1662,"org":1663,"tags":1664,"stars":1656,"repoUrl":1657,"updatedAt":1669},"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},[1665,1668],{"name":1666,"slug":1667,"type":13},"CI\u002FCD","ci-cd",{"name":1547,"slug":1548,"type":13},"2026-07-14T05:25:59.97109",{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1674,"tags":1675,"stars":1656,"repoUrl":1657,"updatedAt":1681},"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},[1676,1677,1678],{"name":1666,"slug":1667,"type":13},{"name":1547,"slug":1548,"type":13},{"name":1679,"slug":1680,"type":13},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":1683,"name":1683,"fn":1684,"description":1685,"org":1686,"tags":1687,"stars":1656,"repoUrl":1657,"updatedAt":1695},"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},[1688,1691,1692],{"name":1689,"slug":1690,"type":13},"Debugging","debugging",{"name":1679,"slug":1680,"type":13},{"name":1693,"slug":1694,"type":13},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":1697,"name":1697,"fn":1698,"description":1699,"org":1700,"tags":1701,"stars":1656,"repoUrl":1657,"updatedAt":1708},"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},[1702,1705],{"name":1703,"slug":1704,"type":13},"Best Practices","best-practices",{"name":1706,"slug":1707,"type":13},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":1710,"name":1710,"fn":1711,"description":1712,"org":1713,"tags":1714,"stars":1656,"repoUrl":1657,"updatedAt":1722},"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},[1715,1718,1721],{"name":1716,"slug":1717,"type":13},"Machine Learning","machine-learning",{"name":1719,"slug":1720,"type":13},"Migration","migration",{"name":9,"slug":8,"type":13},"2026-07-17T06:07:11.777011",{"slug":1724,"name":1724,"fn":1725,"description":1726,"org":1727,"tags":1728,"stars":1656,"repoUrl":1657,"updatedAt":1733},"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},[1729,1732],{"name":1730,"slug":1731,"type":13},"QA","qa",{"name":1575,"slug":1576,"type":13},"2026-07-14T05:25:53.673039",{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1738,"tags":1739,"stars":1656,"repoUrl":1657,"updatedAt":1742},"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},[1740,1741],{"name":1547,"slug":1548,"type":13},{"name":1550,"slug":1551,"type":13},"2026-07-14T05:25:49.362534",{"slug":1744,"name":1744,"fn":1745,"description":1746,"org":1747,"tags":1748,"stars":1656,"repoUrl":1657,"updatedAt":1756},"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},[1749,1752,1753],{"name":1750,"slug":1751,"type":13},"Code Review","code-review",{"name":1679,"slug":1680,"type":13},{"name":1754,"slug":1755,"type":13},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":1758,"name":1758,"fn":1759,"description":1760,"org":1761,"tags":1762,"stars":1656,"repoUrl":1657,"updatedAt":1765},"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},[1763,1764],{"name":1730,"slug":1731,"type":13},{"name":1575,"slug":1576,"type":13},"2026-07-14T05:25:54.928983",{"slug":1767,"name":1767,"fn":1768,"description":1769,"org":1770,"tags":1771,"stars":1656,"repoUrl":1657,"updatedAt":1774},"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},[1772,1773],{"name":1585,"slug":1586,"type":13},{"name":1666,"slug":1667,"type":13},"2026-07-30T05:29:03.275638",496]