[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-huggingface-trackio":3,"mdc-b7ooad-key":39,"related-repo-openai-huggingface-trackio":977,"related-org-openai-huggingface-trackio":1101},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":34,"sourceUrl":37,"mdContent":38},"huggingface-trackio","track ML training experiments with Trackio","Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving\u002Fanalyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Trackio","trackio","tag",{"name":17,"slug":18,"type":15},"Observability","observability",{"name":20,"slug":21,"type":15},"Hugging Face","hugging-face",{"name":23,"slug":24,"type":15},"Deep Learning","deep-learning",{"name":26,"slug":27,"type":15},"Analytics","analytics",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-06T18:41:42.898397",null,465,[],{"repoUrl":29,"stars":28,"forks":32,"topics":35,"description":36},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fhugging-face\u002Fskills\u002Ftrackio","---\nname: huggingface-trackio\ndescription: Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving\u002Fanalyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.\n---\n\n# Trackio - Experiment Tracking for ML Training\n\nTrackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards.\n\n## Three Interfaces\n\n| Task | Interface | Reference |\n|------|-----------|-----------|\n| **Logging metrics** during training | Python API | [references\u002Flogging_metrics.md](references\u002Flogging_metrics.md) |\n| **Firing alerts** for training diagnostics | Python API | [references\u002Falerts.md](references\u002Falerts.md) |\n| **Retrieving metrics & alerts** after\u002Fduring training | CLI | [references\u002Fretrieving_metrics.md](references\u002Fretrieving_metrics.md) |\n\n## When to Use Each\n\n### Python API → Logging\n\nUse `import trackio` in your training scripts to log metrics:\n\n- Initialize tracking with `trackio.init()`\n- Log metrics with `trackio.log()` or use TRL's `report_to=\"trackio\"`\n- Finalize with `trackio.finish()`\n\n**Key concept**: For remote\u002Fcloud training, pass `space_id` — metrics sync to a Space dashboard so they persist after the instance terminates.\n\n→ See [references\u002Flogging_metrics.md](references\u002Flogging_metrics.md) for setup, TRL integration, and configuration options.\n\n### Python API → Alerts\n\nInsert `trackio.alert()` calls in training code to flag important events — like inserting print statements for debugging, but structured and queryable:\n\n- `trackio.alert(title=\"...\", level=trackio.AlertLevel.WARN)` — fire an alert\n- Three severity levels: `INFO`, `WARN`, `ERROR`\n- Alerts are printed to terminal, stored in the database, shown in the dashboard, and optionally sent to webhooks (Slack\u002FDiscord)\n\n**Key concept for LLM agents**: Alerts are the primary mechanism for autonomous experiment iteration. An agent should insert alerts into training code for diagnostic conditions (loss spikes, NaN gradients, low accuracy, training stalls). Since alerts are printed to the terminal, an agent that is watching the training script's output will see them automatically. For background or detached runs, the agent can poll via CLI instead.\n\n→ See [references\u002Falerts.md](references\u002Falerts.md) for the full alerts API, webhook setup, and autonomous agent workflows.\n\n### CLI → Retrieving\n\nUse the `trackio` command to query logged metrics and alerts:\n\n- `trackio list projects\u002Fruns\u002Fmetrics` — discover what's available\n- `trackio get project\u002Frun\u002Fmetric` — retrieve summaries and values\n- `trackio list alerts --project \u003Cname> --json` — retrieve alerts\n- `trackio show` — launch the dashboard\n- `trackio sync` — sync to HF Space\n\n**Key concept**: Add `--json` for programmatic output suitable for automation and LLM agents.\n\n→ See [references\u002Fretrieving_metrics.md](references\u002Fretrieving_metrics.md) for all commands, workflows, and JSON output formats.\n\n## Minimal Logging Setup\n\n```python\nimport trackio\n\ntrackio.init(project=\"my-project\", space_id=\"username\u002Ftrackio\")\ntrackio.log({\"loss\": 0.1, \"accuracy\": 0.9})\ntrackio.log({\"loss\": 0.09, \"accuracy\": 0.91})\ntrackio.finish()\n```\n\n### Minimal Retrieval\n\n```bash\ntrackio list projects --json\ntrackio get metric --project my-project --run my-run --metric loss --json\n```\n\n## Autonomous ML Experiment Workflow\n\nWhen running experiments autonomously as an LLM agent, the recommended workflow is:\n\n1. **Set up training with alerts** — insert `trackio.alert()` calls for diagnostic conditions\n2. **Launch training** — run the script in the background\n3. **Poll for alerts** — use `trackio list alerts --project \u003Cname> --json --since \u003Ctimestamp>` to check for new alerts\n4. **Read metrics** — use `trackio get metric ...` to inspect specific values\n5. **Iterate** — based on alerts and metrics, stop the run, adjust hyperparameters, and launch a new run\n\n```python\nimport trackio\n\ntrackio.init(project=\"my-project\", config={\"lr\": 1e-4})\n\nfor step in range(num_steps):\n    loss = train_step()\n    trackio.log({\"loss\": loss, \"step\": step})\n\n    if step > 100 and loss > 5.0:\n        trackio.alert(\n            title=\"Loss divergence\",\n            text=f\"Loss {loss:.4f} still high after {step} steps\",\n            level=trackio.AlertLevel.ERROR,\n        )\n    if step > 0 and abs(loss) \u003C 1e-8:\n        trackio.alert(\n            title=\"Vanishing loss\",\n            text=\"Loss near zero — possible gradient collapse\",\n            level=trackio.AlertLevel.WARN,\n        )\n\ntrackio.finish()\n```\n\nThen poll from a separate terminal\u002Fprocess:\n\n```bash\ntrackio list alerts --project my-project --json --since \"2025-01-01T00:00:00\"\n```\n",{"data":40,"body":41},{"name":4,"description":6},{"type":42,"children":43},"root",[44,53,59,66,178,184,191,205,251,269,280,286,299,344,354,364,370,382,440,457,467,473,541,547,631,637,642,718,909,914,971],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"trackio-experiment-tracking-for-ml-training",[50],{"type":51,"value":52},"text","Trackio - Experiment Tracking for ML Training",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Trackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards.",{"type":45,"tag":60,"props":61,"children":63},"h2",{"id":62},"three-interfaces",[64],{"type":51,"value":65},"Three Interfaces",{"type":45,"tag":67,"props":68,"children":69},"table",{},[70,94],{"type":45,"tag":71,"props":72,"children":73},"thead",{},[74],{"type":45,"tag":75,"props":76,"children":77},"tr",{},[78,84,89],{"type":45,"tag":79,"props":80,"children":81},"th",{},[82],{"type":51,"value":83},"Task",{"type":45,"tag":79,"props":85,"children":86},{},[87],{"type":51,"value":88},"Interface",{"type":45,"tag":79,"props":90,"children":91},{},[92],{"type":51,"value":93},"Reference",{"type":45,"tag":95,"props":96,"children":97},"tbody",{},[98,127,152],{"type":45,"tag":75,"props":99,"children":100},{},[101,113,118],{"type":45,"tag":102,"props":103,"children":104},"td",{},[105,111],{"type":45,"tag":106,"props":107,"children":108},"strong",{},[109],{"type":51,"value":110},"Logging metrics",{"type":51,"value":112}," during training",{"type":45,"tag":102,"props":114,"children":115},{},[116],{"type":51,"value":117},"Python API",{"type":45,"tag":102,"props":119,"children":120},{},[121],{"type":45,"tag":122,"props":123,"children":125},"a",{"href":124},"references\u002Flogging_metrics.md",[126],{"type":51,"value":124},{"type":45,"tag":75,"props":128,"children":129},{},[130,140,144],{"type":45,"tag":102,"props":131,"children":132},{},[133,138],{"type":45,"tag":106,"props":134,"children":135},{},[136],{"type":51,"value":137},"Firing alerts",{"type":51,"value":139}," for training diagnostics",{"type":45,"tag":102,"props":141,"children":142},{},[143],{"type":51,"value":117},{"type":45,"tag":102,"props":145,"children":146},{},[147],{"type":45,"tag":122,"props":148,"children":150},{"href":149},"references\u002Falerts.md",[151],{"type":51,"value":149},{"type":45,"tag":75,"props":153,"children":154},{},[155,165,170],{"type":45,"tag":102,"props":156,"children":157},{},[158,163],{"type":45,"tag":106,"props":159,"children":160},{},[161],{"type":51,"value":162},"Retrieving metrics & alerts",{"type":51,"value":164}," after\u002Fduring training",{"type":45,"tag":102,"props":166,"children":167},{},[168],{"type":51,"value":169},"CLI",{"type":45,"tag":102,"props":171,"children":172},{},[173],{"type":45,"tag":122,"props":174,"children":176},{"href":175},"references\u002Fretrieving_metrics.md",[177],{"type":51,"value":175},{"type":45,"tag":60,"props":179,"children":181},{"id":180},"when-to-use-each",[182],{"type":51,"value":183},"When to Use Each",{"type":45,"tag":185,"props":186,"children":188},"h3",{"id":187},"python-api-logging",[189],{"type":51,"value":190},"Python API → Logging",{"type":45,"tag":54,"props":192,"children":193},{},[194,196,203],{"type":51,"value":195},"Use ",{"type":45,"tag":197,"props":198,"children":200},"code",{"className":199},[],[201],{"type":51,"value":202},"import trackio",{"type":51,"value":204}," in your training scripts to log metrics:",{"type":45,"tag":206,"props":207,"children":208},"ul",{},[209,221,240],{"type":45,"tag":210,"props":211,"children":212},"li",{},[213,215],{"type":51,"value":214},"Initialize tracking with ",{"type":45,"tag":197,"props":216,"children":218},{"className":217},[],[219],{"type":51,"value":220},"trackio.init()",{"type":45,"tag":210,"props":222,"children":223},{},[224,226,232,234],{"type":51,"value":225},"Log metrics with ",{"type":45,"tag":197,"props":227,"children":229},{"className":228},[],[230],{"type":51,"value":231},"trackio.log()",{"type":51,"value":233}," or use TRL's ",{"type":45,"tag":197,"props":235,"children":237},{"className":236},[],[238],{"type":51,"value":239},"report_to=\"trackio\"",{"type":45,"tag":210,"props":241,"children":242},{},[243,245],{"type":51,"value":244},"Finalize with ",{"type":45,"tag":197,"props":246,"children":248},{"className":247},[],[249],{"type":51,"value":250},"trackio.finish()",{"type":45,"tag":54,"props":252,"children":253},{},[254,259,261,267],{"type":45,"tag":106,"props":255,"children":256},{},[257],{"type":51,"value":258},"Key concept",{"type":51,"value":260},": For remote\u002Fcloud training, pass ",{"type":45,"tag":197,"props":262,"children":264},{"className":263},[],[265],{"type":51,"value":266},"space_id",{"type":51,"value":268}," — metrics sync to a Space dashboard so they persist after the instance terminates.",{"type":45,"tag":54,"props":270,"children":271},{},[272,274,278],{"type":51,"value":273},"→ See ",{"type":45,"tag":122,"props":275,"children":276},{"href":124},[277],{"type":51,"value":124},{"type":51,"value":279}," for setup, TRL integration, and configuration options.",{"type":45,"tag":185,"props":281,"children":283},{"id":282},"python-api-alerts",[284],{"type":51,"value":285},"Python API → Alerts",{"type":45,"tag":54,"props":287,"children":288},{},[289,291,297],{"type":51,"value":290},"Insert ",{"type":45,"tag":197,"props":292,"children":294},{"className":293},[],[295],{"type":51,"value":296},"trackio.alert()",{"type":51,"value":298}," calls in training code to flag important events — like inserting print statements for debugging, but structured and queryable:",{"type":45,"tag":206,"props":300,"children":301},{},[302,313,339],{"type":45,"tag":210,"props":303,"children":304},{},[305,311],{"type":45,"tag":197,"props":306,"children":308},{"className":307},[],[309],{"type":51,"value":310},"trackio.alert(title=\"...\", level=trackio.AlertLevel.WARN)",{"type":51,"value":312}," — fire an alert",{"type":45,"tag":210,"props":314,"children":315},{},[316,318,324,326,332,333],{"type":51,"value":317},"Three severity levels: ",{"type":45,"tag":197,"props":319,"children":321},{"className":320},[],[322],{"type":51,"value":323},"INFO",{"type":51,"value":325},", ",{"type":45,"tag":197,"props":327,"children":329},{"className":328},[],[330],{"type":51,"value":331},"WARN",{"type":51,"value":325},{"type":45,"tag":197,"props":334,"children":336},{"className":335},[],[337],{"type":51,"value":338},"ERROR",{"type":45,"tag":210,"props":340,"children":341},{},[342],{"type":51,"value":343},"Alerts are printed to terminal, stored in the database, shown in the dashboard, and optionally sent to webhooks (Slack\u002FDiscord)",{"type":45,"tag":54,"props":345,"children":346},{},[347,352],{"type":45,"tag":106,"props":348,"children":349},{},[350],{"type":51,"value":351},"Key concept for LLM agents",{"type":51,"value":353},": Alerts are the primary mechanism for autonomous experiment iteration. An agent should insert alerts into training code for diagnostic conditions (loss spikes, NaN gradients, low accuracy, training stalls). Since alerts are printed to the terminal, an agent that is watching the training script's output will see them automatically. For background or detached runs, the agent can poll via CLI instead.",{"type":45,"tag":54,"props":355,"children":356},{},[357,358,362],{"type":51,"value":273},{"type":45,"tag":122,"props":359,"children":360},{"href":149},[361],{"type":51,"value":149},{"type":51,"value":363}," for the full alerts API, webhook setup, and autonomous agent workflows.",{"type":45,"tag":185,"props":365,"children":367},{"id":366},"cli-retrieving",[368],{"type":51,"value":369},"CLI → Retrieving",{"type":45,"tag":54,"props":371,"children":372},{},[373,375,380],{"type":51,"value":374},"Use the ",{"type":45,"tag":197,"props":376,"children":378},{"className":377},[],[379],{"type":51,"value":14},{"type":51,"value":381}," command to query logged metrics and alerts:",{"type":45,"tag":206,"props":383,"children":384},{},[385,396,407,418,429],{"type":45,"tag":210,"props":386,"children":387},{},[388,394],{"type":45,"tag":197,"props":389,"children":391},{"className":390},[],[392],{"type":51,"value":393},"trackio list projects\u002Fruns\u002Fmetrics",{"type":51,"value":395}," — discover what's available",{"type":45,"tag":210,"props":397,"children":398},{},[399,405],{"type":45,"tag":197,"props":400,"children":402},{"className":401},[],[403],{"type":51,"value":404},"trackio get project\u002Frun\u002Fmetric",{"type":51,"value":406}," — retrieve summaries and values",{"type":45,"tag":210,"props":408,"children":409},{},[410,416],{"type":45,"tag":197,"props":411,"children":413},{"className":412},[],[414],{"type":51,"value":415},"trackio list alerts --project \u003Cname> --json",{"type":51,"value":417}," — retrieve alerts",{"type":45,"tag":210,"props":419,"children":420},{},[421,427],{"type":45,"tag":197,"props":422,"children":424},{"className":423},[],[425],{"type":51,"value":426},"trackio show",{"type":51,"value":428}," — launch the dashboard",{"type":45,"tag":210,"props":430,"children":431},{},[432,438],{"type":45,"tag":197,"props":433,"children":435},{"className":434},[],[436],{"type":51,"value":437},"trackio sync",{"type":51,"value":439}," — sync to HF Space",{"type":45,"tag":54,"props":441,"children":442},{},[443,447,449,455],{"type":45,"tag":106,"props":444,"children":445},{},[446],{"type":51,"value":258},{"type":51,"value":448},": Add ",{"type":45,"tag":197,"props":450,"children":452},{"className":451},[],[453],{"type":51,"value":454},"--json",{"type":51,"value":456}," for programmatic output suitable for automation and LLM agents.",{"type":45,"tag":54,"props":458,"children":459},{},[460,461,465],{"type":51,"value":273},{"type":45,"tag":122,"props":462,"children":463},{"href":175},[464],{"type":51,"value":175},{"type":51,"value":466}," for all commands, workflows, and JSON output formats.",{"type":45,"tag":60,"props":468,"children":470},{"id":469},"minimal-logging-setup",[471],{"type":51,"value":472},"Minimal Logging Setup",{"type":45,"tag":474,"props":475,"children":480},"pre",{"className":476,"code":477,"language":478,"meta":479,"style":479},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","import trackio\n\ntrackio.init(project=\"my-project\", space_id=\"username\u002Ftrackio\")\ntrackio.log({\"loss\": 0.1, \"accuracy\": 0.9})\ntrackio.log({\"loss\": 0.09, \"accuracy\": 0.91})\ntrackio.finish()\n","python","",[481],{"type":45,"tag":197,"props":482,"children":483},{"__ignoreMap":479},[484,495,505,514,523,532],{"type":45,"tag":485,"props":486,"children":489},"span",{"class":487,"line":488},"line",1,[490],{"type":45,"tag":485,"props":491,"children":492},{},[493],{"type":51,"value":494},"import trackio\n",{"type":45,"tag":485,"props":496,"children":498},{"class":487,"line":497},2,[499],{"type":45,"tag":485,"props":500,"children":502},{"emptyLinePlaceholder":501},true,[503],{"type":51,"value":504},"\n",{"type":45,"tag":485,"props":506,"children":508},{"class":487,"line":507},3,[509],{"type":45,"tag":485,"props":510,"children":511},{},[512],{"type":51,"value":513},"trackio.init(project=\"my-project\", space_id=\"username\u002Ftrackio\")\n",{"type":45,"tag":485,"props":515,"children":517},{"class":487,"line":516},4,[518],{"type":45,"tag":485,"props":519,"children":520},{},[521],{"type":51,"value":522},"trackio.log({\"loss\": 0.1, \"accuracy\": 0.9})\n",{"type":45,"tag":485,"props":524,"children":526},{"class":487,"line":525},5,[527],{"type":45,"tag":485,"props":528,"children":529},{},[530],{"type":51,"value":531},"trackio.log({\"loss\": 0.09, \"accuracy\": 0.91})\n",{"type":45,"tag":485,"props":533,"children":535},{"class":487,"line":534},6,[536],{"type":45,"tag":485,"props":537,"children":538},{},[539],{"type":51,"value":540},"trackio.finish()\n",{"type":45,"tag":185,"props":542,"children":544},{"id":543},"minimal-retrieval",[545],{"type":51,"value":546},"Minimal Retrieval",{"type":45,"tag":474,"props":548,"children":552},{"className":549,"code":550,"language":551,"meta":479,"style":479},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","trackio list projects --json\ntrackio get metric --project my-project --run my-run --metric loss --json\n","bash",[553],{"type":45,"tag":197,"props":554,"children":555},{"__ignoreMap":479},[556,580],{"type":45,"tag":485,"props":557,"children":558},{"class":487,"line":488},[559,564,570,575],{"type":45,"tag":485,"props":560,"children":562},{"style":561},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[563],{"type":51,"value":14},{"type":45,"tag":485,"props":565,"children":567},{"style":566},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[568],{"type":51,"value":569}," list",{"type":45,"tag":485,"props":571,"children":572},{"style":566},[573],{"type":51,"value":574}," projects",{"type":45,"tag":485,"props":576,"children":577},{"style":566},[578],{"type":51,"value":579}," --json\n",{"type":45,"tag":485,"props":581,"children":582},{"class":487,"line":497},[583,587,592,597,602,607,612,617,622,627],{"type":45,"tag":485,"props":584,"children":585},{"style":561},[586],{"type":51,"value":14},{"type":45,"tag":485,"props":588,"children":589},{"style":566},[590],{"type":51,"value":591}," get",{"type":45,"tag":485,"props":593,"children":594},{"style":566},[595],{"type":51,"value":596}," metric",{"type":45,"tag":485,"props":598,"children":599},{"style":566},[600],{"type":51,"value":601}," --project",{"type":45,"tag":485,"props":603,"children":604},{"style":566},[605],{"type":51,"value":606}," my-project",{"type":45,"tag":485,"props":608,"children":609},{"style":566},[610],{"type":51,"value":611}," --run",{"type":45,"tag":485,"props":613,"children":614},{"style":566},[615],{"type":51,"value":616}," my-run",{"type":45,"tag":485,"props":618,"children":619},{"style":566},[620],{"type":51,"value":621}," --metric",{"type":45,"tag":485,"props":623,"children":624},{"style":566},[625],{"type":51,"value":626}," loss",{"type":45,"tag":485,"props":628,"children":629},{"style":566},[630],{"type":51,"value":579},{"type":45,"tag":60,"props":632,"children":634},{"id":633},"autonomous-ml-experiment-workflow",[635],{"type":51,"value":636},"Autonomous ML Experiment Workflow",{"type":45,"tag":54,"props":638,"children":639},{},[640],{"type":51,"value":641},"When running experiments autonomously as an LLM agent, the recommended workflow is:",{"type":45,"tag":643,"props":644,"children":645},"ol",{},[646,663,673,691,708],{"type":45,"tag":210,"props":647,"children":648},{},[649,654,656,661],{"type":45,"tag":106,"props":650,"children":651},{},[652],{"type":51,"value":653},"Set up training with alerts",{"type":51,"value":655}," — insert ",{"type":45,"tag":197,"props":657,"children":659},{"className":658},[],[660],{"type":51,"value":296},{"type":51,"value":662}," calls for diagnostic conditions",{"type":45,"tag":210,"props":664,"children":665},{},[666,671],{"type":45,"tag":106,"props":667,"children":668},{},[669],{"type":51,"value":670},"Launch training",{"type":51,"value":672}," — run the script in the background",{"type":45,"tag":210,"props":674,"children":675},{},[676,681,683,689],{"type":45,"tag":106,"props":677,"children":678},{},[679],{"type":51,"value":680},"Poll for alerts",{"type":51,"value":682}," — use ",{"type":45,"tag":197,"props":684,"children":686},{"className":685},[],[687],{"type":51,"value":688},"trackio list alerts --project \u003Cname> --json --since \u003Ctimestamp>",{"type":51,"value":690}," to check for new alerts",{"type":45,"tag":210,"props":692,"children":693},{},[694,699,700,706],{"type":45,"tag":106,"props":695,"children":696},{},[697],{"type":51,"value":698},"Read metrics",{"type":51,"value":682},{"type":45,"tag":197,"props":701,"children":703},{"className":702},[],[704],{"type":51,"value":705},"trackio get metric ...",{"type":51,"value":707}," to inspect specific values",{"type":45,"tag":210,"props":709,"children":710},{},[711,716],{"type":45,"tag":106,"props":712,"children":713},{},[714],{"type":51,"value":715},"Iterate",{"type":51,"value":717}," — based on alerts and metrics, stop the run, adjust hyperparameters, and launch a new run",{"type":45,"tag":474,"props":719,"children":721},{"className":476,"code":720,"language":478,"meta":479,"style":479},"import trackio\n\ntrackio.init(project=\"my-project\", config={\"lr\": 1e-4})\n\nfor step in range(num_steps):\n    loss = train_step()\n    trackio.log({\"loss\": loss, \"step\": step})\n\n    if step > 100 and loss > 5.0:\n        trackio.alert(\n            title=\"Loss divergence\",\n            text=f\"Loss {loss:.4f} still high after {step} steps\",\n            level=trackio.AlertLevel.ERROR,\n        )\n    if step > 0 and abs(loss) \u003C 1e-8:\n        trackio.alert(\n            title=\"Vanishing loss\",\n            text=\"Loss near zero — possible gradient collapse\",\n            level=trackio.AlertLevel.WARN,\n        )\n\ntrackio.finish()\n",[722],{"type":45,"tag":197,"props":723,"children":724},{"__ignoreMap":479},[725,732,739,747,754,762,770,779,787,796,805,814,823,832,841,850,858,867,876,885,893,901],{"type":45,"tag":485,"props":726,"children":727},{"class":487,"line":488},[728],{"type":45,"tag":485,"props":729,"children":730},{},[731],{"type":51,"value":494},{"type":45,"tag":485,"props":733,"children":734},{"class":487,"line":497},[735],{"type":45,"tag":485,"props":736,"children":737},{"emptyLinePlaceholder":501},[738],{"type":51,"value":504},{"type":45,"tag":485,"props":740,"children":741},{"class":487,"line":507},[742],{"type":45,"tag":485,"props":743,"children":744},{},[745],{"type":51,"value":746},"trackio.init(project=\"my-project\", config={\"lr\": 1e-4})\n",{"type":45,"tag":485,"props":748,"children":749},{"class":487,"line":516},[750],{"type":45,"tag":485,"props":751,"children":752},{"emptyLinePlaceholder":501},[753],{"type":51,"value":504},{"type":45,"tag":485,"props":755,"children":756},{"class":487,"line":525},[757],{"type":45,"tag":485,"props":758,"children":759},{},[760],{"type":51,"value":761},"for step in range(num_steps):\n",{"type":45,"tag":485,"props":763,"children":764},{"class":487,"line":534},[765],{"type":45,"tag":485,"props":766,"children":767},{},[768],{"type":51,"value":769},"    loss = train_step()\n",{"type":45,"tag":485,"props":771,"children":773},{"class":487,"line":772},7,[774],{"type":45,"tag":485,"props":775,"children":776},{},[777],{"type":51,"value":778},"    trackio.log({\"loss\": loss, \"step\": step})\n",{"type":45,"tag":485,"props":780,"children":782},{"class":487,"line":781},8,[783],{"type":45,"tag":485,"props":784,"children":785},{"emptyLinePlaceholder":501},[786],{"type":51,"value":504},{"type":45,"tag":485,"props":788,"children":790},{"class":487,"line":789},9,[791],{"type":45,"tag":485,"props":792,"children":793},{},[794],{"type":51,"value":795},"    if step > 100 and loss > 5.0:\n",{"type":45,"tag":485,"props":797,"children":799},{"class":487,"line":798},10,[800],{"type":45,"tag":485,"props":801,"children":802},{},[803],{"type":51,"value":804},"        trackio.alert(\n",{"type":45,"tag":485,"props":806,"children":808},{"class":487,"line":807},11,[809],{"type":45,"tag":485,"props":810,"children":811},{},[812],{"type":51,"value":813},"            title=\"Loss divergence\",\n",{"type":45,"tag":485,"props":815,"children":817},{"class":487,"line":816},12,[818],{"type":45,"tag":485,"props":819,"children":820},{},[821],{"type":51,"value":822},"            text=f\"Loss {loss:.4f} still high after {step} steps\",\n",{"type":45,"tag":485,"props":824,"children":826},{"class":487,"line":825},13,[827],{"type":45,"tag":485,"props":828,"children":829},{},[830],{"type":51,"value":831},"            level=trackio.AlertLevel.ERROR,\n",{"type":45,"tag":485,"props":833,"children":835},{"class":487,"line":834},14,[836],{"type":45,"tag":485,"props":837,"children":838},{},[839],{"type":51,"value":840},"        )\n",{"type":45,"tag":485,"props":842,"children":844},{"class":487,"line":843},15,[845],{"type":45,"tag":485,"props":846,"children":847},{},[848],{"type":51,"value":849},"    if step > 0 and abs(loss) \u003C 1e-8:\n",{"type":45,"tag":485,"props":851,"children":853},{"class":487,"line":852},16,[854],{"type":45,"tag":485,"props":855,"children":856},{},[857],{"type":51,"value":804},{"type":45,"tag":485,"props":859,"children":861},{"class":487,"line":860},17,[862],{"type":45,"tag":485,"props":863,"children":864},{},[865],{"type":51,"value":866},"            title=\"Vanishing loss\",\n",{"type":45,"tag":485,"props":868,"children":870},{"class":487,"line":869},18,[871],{"type":45,"tag":485,"props":872,"children":873},{},[874],{"type":51,"value":875},"            text=\"Loss near zero — possible gradient collapse\",\n",{"type":45,"tag":485,"props":877,"children":879},{"class":487,"line":878},19,[880],{"type":45,"tag":485,"props":881,"children":882},{},[883],{"type":51,"value":884},"            level=trackio.AlertLevel.WARN,\n",{"type":45,"tag":485,"props":886,"children":888},{"class":487,"line":887},20,[889],{"type":45,"tag":485,"props":890,"children":891},{},[892],{"type":51,"value":840},{"type":45,"tag":485,"props":894,"children":896},{"class":487,"line":895},21,[897],{"type":45,"tag":485,"props":898,"children":899},{"emptyLinePlaceholder":501},[900],{"type":51,"value":504},{"type":45,"tag":485,"props":902,"children":904},{"class":487,"line":903},22,[905],{"type":45,"tag":485,"props":906,"children":907},{},[908],{"type":51,"value":540},{"type":45,"tag":54,"props":910,"children":911},{},[912],{"type":51,"value":913},"Then poll from a separate terminal\u002Fprocess:",{"type":45,"tag":474,"props":915,"children":917},{"className":549,"code":916,"language":551,"meta":479,"style":479},"trackio list alerts --project my-project --json --since \"2025-01-01T00:00:00\"\n",[918],{"type":45,"tag":197,"props":919,"children":920},{"__ignoreMap":479},[921],{"type":45,"tag":485,"props":922,"children":923},{"class":487,"line":488},[924,928,932,937,941,945,950,955,961,966],{"type":45,"tag":485,"props":925,"children":926},{"style":561},[927],{"type":51,"value":14},{"type":45,"tag":485,"props":929,"children":930},{"style":566},[931],{"type":51,"value":569},{"type":45,"tag":485,"props":933,"children":934},{"style":566},[935],{"type":51,"value":936}," alerts",{"type":45,"tag":485,"props":938,"children":939},{"style":566},[940],{"type":51,"value":601},{"type":45,"tag":485,"props":942,"children":943},{"style":566},[944],{"type":51,"value":606},{"type":45,"tag":485,"props":946,"children":947},{"style":566},[948],{"type":51,"value":949}," --json",{"type":45,"tag":485,"props":951,"children":952},{"style":566},[953],{"type":51,"value":954}," --since",{"type":45,"tag":485,"props":956,"children":958},{"style":957},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[959],{"type":51,"value":960}," \"",{"type":45,"tag":485,"props":962,"children":963},{"style":566},[964],{"type":51,"value":965},"2025-01-01T00:00:00",{"type":45,"tag":485,"props":967,"children":968},{"style":957},[969],{"type":51,"value":970},"\"\n",{"type":45,"tag":972,"props":973,"children":974},"style",{},[975],{"type":51,"value":976},"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":978,"total":1100},[979,998,1014,1026,1046,1068,1088],{"slug":980,"name":980,"fn":981,"description":982,"org":983,"tags":984,"stars":28,"repoUrl":29,"updatedAt":997},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[985,988,991,994],{"name":986,"slug":987,"type":15},"Accessibility","accessibility",{"name":989,"slug":990,"type":15},"Charts","charts",{"name":992,"slug":993,"type":15},"Data Visualization","data-visualization",{"name":995,"slug":996,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":999,"name":999,"fn":1000,"description":1001,"org":1002,"tags":1003,"stars":28,"repoUrl":29,"updatedAt":1013},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1004,1007,1010],{"name":1005,"slug":1006,"type":15},"Agents","agents",{"name":1008,"slug":1009,"type":15},"Browser Automation","browser-automation",{"name":1011,"slug":1012,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1015,"name":1015,"fn":1016,"description":1017,"org":1018,"tags":1019,"stars":28,"repoUrl":29,"updatedAt":1025},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1020,1021,1024],{"name":1008,"slug":1009,"type":15},{"name":1022,"slug":1023,"type":15},"Local Development","local-development",{"name":1011,"slug":1012,"type":15},"2026-04-06T18:41:17.526867",{"slug":1027,"name":1027,"fn":1028,"description":1029,"org":1030,"tags":1031,"stars":28,"repoUrl":29,"updatedAt":1045},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1032,1033,1036,1039,1042],{"name":1005,"slug":1006,"type":15},{"name":1034,"slug":1035,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1037,"slug":1038,"type":15},"SDK","sdk",{"name":1040,"slug":1041,"type":15},"Serverless","serverless",{"name":1043,"slug":1044,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1047,"name":1047,"fn":1048,"description":1049,"org":1050,"tags":1051,"stars":28,"repoUrl":29,"updatedAt":1067},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1052,1055,1058,1061,1064],{"name":1053,"slug":1054,"type":15},"Frontend","frontend",{"name":1056,"slug":1057,"type":15},"React","react",{"name":1059,"slug":1060,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1062,"slug":1063,"type":15},"UI Components","ui-components",{"name":1065,"slug":1066,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1069,"name":1069,"fn":1070,"description":1071,"org":1072,"tags":1073,"stars":28,"repoUrl":29,"updatedAt":1087},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1074,1077,1080,1083,1086],{"name":1075,"slug":1076,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1078,"slug":1079,"type":15},"Cost Optimization","cost-optimization",{"name":1081,"slug":1082,"type":15},"LLM","llm",{"name":1084,"slug":1085,"type":15},"Performance","performance",{"name":1065,"slug":1066,"type":15},"2026-04-06T18:40:44.377464",{"slug":1089,"name":1089,"fn":1090,"description":1091,"org":1092,"tags":1093,"stars":28,"repoUrl":29,"updatedAt":1099},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1094,1095,1098],{"name":1078,"slug":1079,"type":15},{"name":1096,"slug":1097,"type":15},"Database","database",{"name":1081,"slug":1082,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1102,"total":1298},[1103,1124,1147,1164,1179,1196,1215,1227,1241,1255,1267,1282],{"slug":1104,"name":1104,"fn":1105,"description":1106,"org":1107,"tags":1108,"stars":1121,"repoUrl":1122,"updatedAt":1123},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1109,1112,1115,1118],{"name":1110,"slug":1111,"type":15},"Documents","documents",{"name":1113,"slug":1114,"type":15},"Healthcare","healthcare",{"name":1116,"slug":1117,"type":15},"Insurance","insurance",{"name":1119,"slug":1120,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1125,"name":1125,"fn":1126,"description":1127,"org":1128,"tags":1129,"stars":1144,"repoUrl":1145,"updatedAt":1146},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1130,1133,1135,1138,1141],{"name":1131,"slug":1132,"type":15},".NET","dotnet",{"name":1134,"slug":1125,"type":15},"ASP.NET Core",{"name":1136,"slug":1137,"type":15},"Blazor","blazor",{"name":1139,"slug":1140,"type":15},"C#","csharp",{"name":1142,"slug":1143,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1148,"name":1148,"fn":1149,"description":1150,"org":1151,"tags":1152,"stars":1144,"repoUrl":1145,"updatedAt":1163},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1153,1156,1159,1162],{"name":1154,"slug":1155,"type":15},"Apps SDK","apps-sdk",{"name":1157,"slug":1158,"type":15},"ChatGPT","chatgpt",{"name":1160,"slug":1161,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1165,"name":1165,"fn":1166,"description":1167,"org":1168,"tags":1169,"stars":1144,"repoUrl":1145,"updatedAt":1178},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1170,1173,1175],{"name":1171,"slug":1172,"type":15},"API Development","api-development",{"name":169,"slug":1174,"type":15},"cli",{"name":1176,"slug":1177,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1180,"name":1180,"fn":1181,"description":1182,"org":1183,"tags":1184,"stars":1144,"repoUrl":1145,"updatedAt":1195},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1185,1188,1191,1192],{"name":1186,"slug":1187,"type":15},"Cloudflare","cloudflare",{"name":1189,"slug":1190,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1034,"slug":1035,"type":15},{"name":1193,"slug":1194,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1197,"name":1197,"fn":1198,"description":1199,"org":1200,"tags":1201,"stars":1144,"repoUrl":1145,"updatedAt":1214},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1202,1205,1208,1211],{"name":1203,"slug":1204,"type":15},"Productivity","productivity",{"name":1206,"slug":1207,"type":15},"Project Management","project-management",{"name":1209,"slug":1210,"type":15},"Strategy","strategy",{"name":1212,"slug":1213,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1216,"name":1216,"fn":1217,"description":1218,"org":1219,"tags":1220,"stars":1144,"repoUrl":1145,"updatedAt":1226},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1221,1222,1224,1225],{"name":995,"slug":996,"type":15},{"name":1223,"slug":1216,"type":15},"Figma",{"name":1053,"slug":1054,"type":15},{"name":1160,"slug":1161,"type":15},"2026-04-12T05:06:47.939943",{"slug":1228,"name":1228,"fn":1229,"description":1230,"org":1231,"tags":1232,"stars":1144,"repoUrl":1145,"updatedAt":1240},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1233,1234,1237,1238,1239],{"name":995,"slug":996,"type":15},{"name":1235,"slug":1236,"type":15},"Design System","design-system",{"name":1223,"slug":1216,"type":15},{"name":1053,"slug":1054,"type":15},{"name":1062,"slug":1063,"type":15},"2026-05-10T05:59:52.971881",{"slug":1242,"name":1242,"fn":1243,"description":1244,"org":1245,"tags":1246,"stars":1144,"repoUrl":1145,"updatedAt":1254},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1247,1248,1249,1252,1253],{"name":995,"slug":996,"type":15},{"name":1235,"slug":1236,"type":15},{"name":1250,"slug":1251,"type":15},"Documentation","documentation",{"name":1223,"slug":1216,"type":15},{"name":1053,"slug":1054,"type":15},"2026-05-16T06:07:47.821474",{"slug":1256,"name":1256,"fn":1257,"description":1258,"org":1259,"tags":1260,"stars":1144,"repoUrl":1145,"updatedAt":1266},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1261,1262,1263,1264,1265],{"name":995,"slug":996,"type":15},{"name":1223,"slug":1216,"type":15},{"name":1053,"slug":1054,"type":15},{"name":1062,"slug":1063,"type":15},{"name":1142,"slug":1143,"type":15},"2026-05-16T06:07:40.583615",{"slug":1268,"name":1268,"fn":1269,"description":1270,"org":1271,"tags":1272,"stars":1144,"repoUrl":1145,"updatedAt":1281},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1273,1276,1277,1280],{"name":1274,"slug":1275,"type":15},"Animation","animation",{"name":1176,"slug":1177,"type":15},{"name":1278,"slug":1279,"type":15},"Creative","creative",{"name":995,"slug":996,"type":15},"2026-05-02T05:31:48.48485",{"slug":1283,"name":1283,"fn":1284,"description":1285,"org":1286,"tags":1287,"stars":1144,"repoUrl":1145,"updatedAt":1297},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1288,1289,1290,1293,1296],{"name":1278,"slug":1279,"type":15},{"name":995,"slug":996,"type":15},{"name":1291,"slug":1292,"type":15},"Image Generation","image-generation",{"name":1294,"slug":1295,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]