[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-deepnote-data-execution":3,"mdc--co776y-key":36,"related-repo-openai-deepnote-data-execution":1167,"related-org-openai-deepnote-data-execution":1289},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"deepnote-data-execution","execute and inspect Deepnote notebook runs","Use when running Deepnote notebooks, inspecting notebook inputs, reviewing integration references and cached table structure, listing run history, or interpreting run status and snapshot outputs through the Deepnote app tools.",{"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],{"name":13,"slug":14,"type":15},"Automation","automation","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":20,"slug":21,"type":15},"Notebooks","notebooks",{"name":23,"slug":24,"type":15},"Jupyter","jupyter",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-06-30T19:00:57.102",null,465,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fdeepnote\u002Fskills\u002Fdeepnote-data-execution","---\nname: deepnote-data-execution\ndescription: Use when running Deepnote notebooks, inspecting notebook inputs, reviewing integration references and cached table structure, listing run history, or interpreting run status and snapshot outputs through the Deepnote app tools.\n---\n\n# Deepnote Data And Execution\n\n## Available Context\n\nUse the connected Deepnote app tools for the execution and context they currently expose:\n\n- `get_notebook` for notebook blocks, input variables, last-run metadata, and integration references visible in blocks.\n- `list_integrations` for workspace integration names and types.\n- `get_integration` for integration details and cached table structure, optionally filtered by `databaseName`, `schemaName`, or exact `tableName`.\n- `list_integration_project_usages`, `list_integration_notebook_usages`, and `list_integration_block_usages` for direct integration usage mapping.\n- `create_run` to start full-notebook execution, optionally with input values.\n- `list_notebook_runs` for historical notebook runs, newest first, with `pageSize` and `pageToken` pagination.\n- `get_run` for run status, errors, completion time, and run snapshots. When `snapshotDelivery` is omitted, it returns a short-lived `snapshotDownloadUrl` when a snapshot is available; this is equivalent to `snapshotDelivery: \"downloadUrl\"`. Request `snapshotDelivery: \"inline\"` only when you need `snapshotContent` in the tool response.\n- `get_me` for the authenticated workspace, connected user, and caller access level when execution permissions or workspace identity matter.\n\nUse `get_integration` for cached table and column structure when the user asks about integration schemas, tables, columns, or whether a table exists. Do not claim live database introspection, table previews, query previews, file metadata, or environment configuration unless a current Deepnote app tool explicitly exposes that data.\n\n## Execution Workflow\n\n1. Read the notebook context first with `get_notebook`.\n2. Identify whether the user needs a fresh run, a specific run status, or notebook run history.\n3. If the notebook has inputs and the user supplied values, map values to the exact input `name` fields returned by `get_notebook`.\n4. Check whether execution may mutate data, call external services, trigger schedules, or consume significant compute.\n5. Use `create_run` only for full-notebook execution by `notebookId`; the Deepnote app does not currently expose single-block execution.\n6. If `create_run` returns a tool error, report that error and stop; do not call `get_run` unless a run ID was returned.\n7. Use `get_run` to inspect status, errors, completion time, and snapshot availability before reporting results. For routine status checks, omit `snapshotDelivery` so the default download URL delivery is used; request `snapshotDelivery: \"inline\"` when you need to inspect notebook outputs, snapshot errors, or result details.\n\nBefore starting a run, inspect the notebook for cells that print environment variables, secrets, credentials, or entire configuration objects. If found, warn the user and get explicit confirmation before running. Also warn before running notebooks that start servers, send bulk requests, call external services, or mutate data.\n\n## Run History\n\nUse `list_notebook_runs` when the user asks about recent runs, failed runs, run history, or anything older than the latest run metadata returned by `get_notebook`. The tool returns runs newest first with `runId`, `notebookId`, `status`, `createdAt`, `completedAt`, and `pagination`.\n\nFor short history requests, call `list_notebook_runs` with the default `pageSize` of 20. For broader audits, use `pageSize: 100` and follow `pagination.nextPageToken` while `pagination.hasMore` is true, stopping once you have enough evidence for the user's question.\n\nUse `get_run` only after selecting a specific run that needs detail, snapshot availability, output inspection, or failure debugging. If the user asks \"why did the last run fail?\" and no run ID is provided, list recent runs first, pick the newest failed run, then call `get_run` for that run.\n\n## Cached Integration Structure\n\nUse `list_integrations` to resolve an integration name or type to an ID, then call `get_integration` for cached table structure. The response includes integration details plus `tables`, where each table has `name`, `schema`, optional `database`, and cached `columns` with names and database-native types.\n\nUse `databaseName`, `schemaName`, and `tableName` filters when the user asks about a specific database, schema, or exact table. These filters apply to cached structure rows; an empty table list means no matching cached structure is visible through the app tools, not proof that the live database has no such table.\n\nWhen reporting cached structure, say it is cached. Do not present it as a fresh live database scan, and do not claim access to row previews or query results unless you obtained them from a notebook run snapshot or another exposed app tool.\n\n## Notebook Run Inputs\n\n`create_run` accepts an optional `inputs` object. Keys must be notebook input names from `get_notebook`, not labels or block IDs. Values must match the input block type:\n\n- Text, textarea, file, date, slider, and single-select inputs use strings.\n- Checkbox inputs use booleans.\n- Multi-select inputs use arrays of strings.\n- Date-range inputs use a string or an array of exactly two strings.\n- Slider values must be numeric strings.\n\nIf the user provides a label instead of a name, inspect `get_notebook` inputs and map it to the closest input `name` only when the match is unambiguous. Otherwise ask for clarification. Run input values apply only to the new run and do not update the notebook's saved defaults.\n\n## Run Snapshots\n\nWhen `snapshotDelivery` is omitted, `get_run` returns `snapshotDownloadUrl` for available `.snapshot.deepnote` files and `snapshotContent: null`; this is equivalent to `snapshotDelivery: \"downloadUrl\"`. The URL is short-lived and grants access to the run snapshot, so do not paste it into the final answer unless the user asks for a download link or file handoff.\n\nUse `snapshotDelivery: \"inline\"` when the user asks you to inspect outputs, summarize results, diagnose a failed run from snapshot details, map visible references from the snapshot, or otherwise reason over the snapshot content. Inline snapshots can be large and sensitive, so summarize the relevant blocks, outputs, failures, or data shape instead of dumping raw content.\n\nIf the current Deepnote app tool schema does not expose `snapshotDelivery`, use the fields returned by `get_run` as-is and do not invent `snapshotContent` or `snapshotDownloadUrl`.\n\n## Sensitive Outputs\n\nWhen snapshot content, snapshot download URLs, or errors include sensitive, proprietary, personal, or production-like data, minimize exposure in the response. Summarize the result, shape, quality issues, aggregates, or failure mode instead of dumping raw records, presigned URLs, or long logs.\n\n## Environment Changes\n\nThe Deepnote app tools currently do not expose environment mutation tools. Do not claim to change package versions, environment images, hardware, integrations, credentials, secrets, scheduled runs, or shared app settings unless a current tool explicitly supports that action.\n\n## Reporting Results\n\nFor successful runs, include the executed notebook name or ID, run ID, status, any input overrides that are safe to mention, and the important result from inline snapshot content when you requested it. If you only have `snapshotDownloadUrl`, mention that a snapshot is available without exposing the URL by default. For failures, include concise error detail and the next fix to try. If a run fails before it starts, such as a workspace or parallel run limit, report the user-facing API error directly. Avoid pasting long logs unless the user asks for them.\n\nKeep run reports brief and information-dense unless the user asks for detail. Prefer one compact run table plus the most important result or first actionable error. Do not paste long logs, raw snapshots, or full notebook outputs by default.\n\nPrefer this run summary shape:\n\n| Field | Value |\n| --- | --- |\n| Notebook | `Notebook name` |\n| Run ID | `run-id` |\n| Status | `success`, `failed`, `pending`, or `running` |\n| Started | `YYYY-MM-DD HH:MM UTC` |\n| Completed | `YYYY-MM-DD HH:MM UTC` or `Still running` |\n| Inputs | `safe input summary` or `None` |\n| Result | `short result summary` |\n\nFor failed or stuck runs, use a debugging report:\n\n| Check | Finding |\n| --- | --- |\n| Run state | `failed`, `pending`, or `running for N minutes` |\n| First actionable error | `short error text` |\n| Likely cause | `missing input`, `missing file`, `server not listening`, `dependency failure`, or `unknown from app tools` |\n| Safe next step | `inspect notebook`, `rerun with inputs`, `start serving notebook`, or `manual Deepnote action needed` |\n\nWhen inspecting a large run snapshot, request inline delivery only when necessary, then summarize block counts, failed blocks, final outputs, and the first actionable error instead of pasting the snapshot.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,57,63,252,264,270,377,382,388,447,490,508,514,570,593,598,604,629,657,676,682,731,742,774,780,785,791,796,802,814,819,824,1006,1011,1162],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"deepnote-data-and-execution",[47],{"type":48,"value":49},"text","Deepnote Data And Execution",{"type":42,"tag":51,"props":52,"children":54},"h2",{"id":53},"available-context",[55],{"type":48,"value":56},"Available Context",{"type":42,"tag":58,"props":59,"children":60},"p",{},[61],{"type":48,"value":62},"Use the connected Deepnote app tools for the execution and context they currently expose:",{"type":42,"tag":64,"props":65,"children":66},"ul",{},[67,80,91,126,152,163,190,241],{"type":42,"tag":68,"props":69,"children":70},"li",{},[71,78],{"type":42,"tag":72,"props":73,"children":75},"code",{"className":74},[],[76],{"type":48,"value":77},"get_notebook",{"type":48,"value":79}," for notebook blocks, input variables, last-run metadata, and integration references visible in blocks.",{"type":42,"tag":68,"props":81,"children":82},{},[83,89],{"type":42,"tag":72,"props":84,"children":86},{"className":85},[],[87],{"type":48,"value":88},"list_integrations",{"type":48,"value":90}," for workspace integration names and types.",{"type":42,"tag":68,"props":92,"children":93},{},[94,100,102,108,110,116,118,124],{"type":42,"tag":72,"props":95,"children":97},{"className":96},[],[98],{"type":48,"value":99},"get_integration",{"type":48,"value":101}," for integration details and cached table structure, optionally filtered by ",{"type":42,"tag":72,"props":103,"children":105},{"className":104},[],[106],{"type":48,"value":107},"databaseName",{"type":48,"value":109},", ",{"type":42,"tag":72,"props":111,"children":113},{"className":112},[],[114],{"type":48,"value":115},"schemaName",{"type":48,"value":117},", or exact ",{"type":42,"tag":72,"props":119,"children":121},{"className":120},[],[122],{"type":48,"value":123},"tableName",{"type":48,"value":125},".",{"type":42,"tag":68,"props":127,"children":128},{},[129,135,136,142,144,150],{"type":42,"tag":72,"props":130,"children":132},{"className":131},[],[133],{"type":48,"value":134},"list_integration_project_usages",{"type":48,"value":109},{"type":42,"tag":72,"props":137,"children":139},{"className":138},[],[140],{"type":48,"value":141},"list_integration_notebook_usages",{"type":48,"value":143},", and ",{"type":42,"tag":72,"props":145,"children":147},{"className":146},[],[148],{"type":48,"value":149},"list_integration_block_usages",{"type":48,"value":151}," for direct integration usage mapping.",{"type":42,"tag":68,"props":153,"children":154},{},[155,161],{"type":42,"tag":72,"props":156,"children":158},{"className":157},[],[159],{"type":48,"value":160},"create_run",{"type":48,"value":162}," to start full-notebook execution, optionally with input values.",{"type":42,"tag":68,"props":164,"children":165},{},[166,172,174,180,182,188],{"type":42,"tag":72,"props":167,"children":169},{"className":168},[],[170],{"type":48,"value":171},"list_notebook_runs",{"type":48,"value":173}," for historical notebook runs, newest first, with ",{"type":42,"tag":72,"props":175,"children":177},{"className":176},[],[178],{"type":48,"value":179},"pageSize",{"type":48,"value":181}," and ",{"type":42,"tag":72,"props":183,"children":185},{"className":184},[],[186],{"type":48,"value":187},"pageToken",{"type":48,"value":189}," pagination.",{"type":42,"tag":68,"props":191,"children":192},{},[193,199,201,207,209,215,217,223,225,231,233,239],{"type":42,"tag":72,"props":194,"children":196},{"className":195},[],[197],{"type":48,"value":198},"get_run",{"type":48,"value":200}," for run status, errors, completion time, and run snapshots. When ",{"type":42,"tag":72,"props":202,"children":204},{"className":203},[],[205],{"type":48,"value":206},"snapshotDelivery",{"type":48,"value":208}," is omitted, it returns a short-lived ",{"type":42,"tag":72,"props":210,"children":212},{"className":211},[],[213],{"type":48,"value":214},"snapshotDownloadUrl",{"type":48,"value":216}," when a snapshot is available; this is equivalent to ",{"type":42,"tag":72,"props":218,"children":220},{"className":219},[],[221],{"type":48,"value":222},"snapshotDelivery: \"downloadUrl\"",{"type":48,"value":224},". Request ",{"type":42,"tag":72,"props":226,"children":228},{"className":227},[],[229],{"type":48,"value":230},"snapshotDelivery: \"inline\"",{"type":48,"value":232}," only when you need ",{"type":42,"tag":72,"props":234,"children":236},{"className":235},[],[237],{"type":48,"value":238},"snapshotContent",{"type":48,"value":240}," in the tool response.",{"type":42,"tag":68,"props":242,"children":243},{},[244,250],{"type":42,"tag":72,"props":245,"children":247},{"className":246},[],[248],{"type":48,"value":249},"get_me",{"type":48,"value":251}," for the authenticated workspace, connected user, and caller access level when execution permissions or workspace identity matter.",{"type":42,"tag":58,"props":253,"children":254},{},[255,257,262],{"type":48,"value":256},"Use ",{"type":42,"tag":72,"props":258,"children":260},{"className":259},[],[261],{"type":48,"value":99},{"type":48,"value":263}," for cached table and column structure when the user asks about integration schemas, tables, columns, or whether a table exists. Do not claim live database introspection, table previews, query previews, file metadata, or environment configuration unless a current Deepnote app tool explicitly exposes that data.",{"type":42,"tag":51,"props":265,"children":267},{"id":266},"execution-workflow",[268],{"type":48,"value":269},"Execution Workflow",{"type":42,"tag":271,"props":272,"children":273},"ol",{},[274,285,290,309,314,333,352],{"type":42,"tag":68,"props":275,"children":276},{},[277,279,284],{"type":48,"value":278},"Read the notebook context first with ",{"type":42,"tag":72,"props":280,"children":282},{"className":281},[],[283],{"type":48,"value":77},{"type":48,"value":125},{"type":42,"tag":68,"props":286,"children":287},{},[288],{"type":48,"value":289},"Identify whether the user needs a fresh run, a specific run status, or notebook run history.",{"type":42,"tag":68,"props":291,"children":292},{},[293,295,301,303,308],{"type":48,"value":294},"If the notebook has inputs and the user supplied values, map values to the exact input ",{"type":42,"tag":72,"props":296,"children":298},{"className":297},[],[299],{"type":48,"value":300},"name",{"type":48,"value":302}," fields returned by ",{"type":42,"tag":72,"props":304,"children":306},{"className":305},[],[307],{"type":48,"value":77},{"type":48,"value":125},{"type":42,"tag":68,"props":310,"children":311},{},[312],{"type":48,"value":313},"Check whether execution may mutate data, call external services, trigger schedules, or consume significant compute.",{"type":42,"tag":68,"props":315,"children":316},{},[317,318,323,325,331],{"type":48,"value":256},{"type":42,"tag":72,"props":319,"children":321},{"className":320},[],[322],{"type":48,"value":160},{"type":48,"value":324}," only for full-notebook execution by ",{"type":42,"tag":72,"props":326,"children":328},{"className":327},[],[329],{"type":48,"value":330},"notebookId",{"type":48,"value":332},"; the Deepnote app does not currently expose single-block execution.",{"type":42,"tag":68,"props":334,"children":335},{},[336,338,343,345,350],{"type":48,"value":337},"If ",{"type":42,"tag":72,"props":339,"children":341},{"className":340},[],[342],{"type":48,"value":160},{"type":48,"value":344}," returns a tool error, report that error and stop; do not call ",{"type":42,"tag":72,"props":346,"children":348},{"className":347},[],[349],{"type":48,"value":198},{"type":48,"value":351}," unless a run ID was returned.",{"type":42,"tag":68,"props":353,"children":354},{},[355,356,361,363,368,370,375],{"type":48,"value":256},{"type":42,"tag":72,"props":357,"children":359},{"className":358},[],[360],{"type":48,"value":198},{"type":48,"value":362}," to inspect status, errors, completion time, and snapshot availability before reporting results. For routine status checks, omit ",{"type":42,"tag":72,"props":364,"children":366},{"className":365},[],[367],{"type":48,"value":206},{"type":48,"value":369}," so the default download URL delivery is used; request ",{"type":42,"tag":72,"props":371,"children":373},{"className":372},[],[374],{"type":48,"value":230},{"type":48,"value":376}," when you need to inspect notebook outputs, snapshot errors, or result details.",{"type":42,"tag":58,"props":378,"children":379},{},[380],{"type":48,"value":381},"Before starting a run, inspect the notebook for cells that print environment variables, secrets, credentials, or entire configuration objects. If found, warn the user and get explicit confirmation before running. Also warn before running notebooks that start servers, send bulk requests, call external services, or mutate data.",{"type":42,"tag":51,"props":383,"children":385},{"id":384},"run-history",[386],{"type":48,"value":387},"Run History",{"type":42,"tag":58,"props":389,"children":390},{},[391,392,397,399,404,406,412,413,418,419,425,426,432,433,439,440,446],{"type":48,"value":256},{"type":42,"tag":72,"props":393,"children":395},{"className":394},[],[396],{"type":48,"value":171},{"type":48,"value":398}," when the user asks about recent runs, failed runs, run history, or anything older than the latest run metadata returned by ",{"type":42,"tag":72,"props":400,"children":402},{"className":401},[],[403],{"type":48,"value":77},{"type":48,"value":405},". The tool returns runs newest first with ",{"type":42,"tag":72,"props":407,"children":409},{"className":408},[],[410],{"type":48,"value":411},"runId",{"type":48,"value":109},{"type":42,"tag":72,"props":414,"children":416},{"className":415},[],[417],{"type":48,"value":330},{"type":48,"value":109},{"type":42,"tag":72,"props":420,"children":422},{"className":421},[],[423],{"type":48,"value":424},"status",{"type":48,"value":109},{"type":42,"tag":72,"props":427,"children":429},{"className":428},[],[430],{"type":48,"value":431},"createdAt",{"type":48,"value":109},{"type":42,"tag":72,"props":434,"children":436},{"className":435},[],[437],{"type":48,"value":438},"completedAt",{"type":48,"value":143},{"type":42,"tag":72,"props":441,"children":443},{"className":442},[],[444],{"type":48,"value":445},"pagination",{"type":48,"value":125},{"type":42,"tag":58,"props":448,"children":449},{},[450,452,457,459,464,466,472,474,480,482,488],{"type":48,"value":451},"For short history requests, call ",{"type":42,"tag":72,"props":453,"children":455},{"className":454},[],[456],{"type":48,"value":171},{"type":48,"value":458}," with the default ",{"type":42,"tag":72,"props":460,"children":462},{"className":461},[],[463],{"type":48,"value":179},{"type":48,"value":465}," of 20. For broader audits, use ",{"type":42,"tag":72,"props":467,"children":469},{"className":468},[],[470],{"type":48,"value":471},"pageSize: 100",{"type":48,"value":473}," and follow ",{"type":42,"tag":72,"props":475,"children":477},{"className":476},[],[478],{"type":48,"value":479},"pagination.nextPageToken",{"type":48,"value":481}," while ",{"type":42,"tag":72,"props":483,"children":485},{"className":484},[],[486],{"type":48,"value":487},"pagination.hasMore",{"type":48,"value":489}," is true, stopping once you have enough evidence for the user's question.",{"type":42,"tag":58,"props":491,"children":492},{},[493,494,499,501,506],{"type":48,"value":256},{"type":42,"tag":72,"props":495,"children":497},{"className":496},[],[498],{"type":48,"value":198},{"type":48,"value":500}," only after selecting a specific run that needs detail, snapshot availability, output inspection, or failure debugging. If the user asks \"why did the last run fail?\" and no run ID is provided, list recent runs first, pick the newest failed run, then call ",{"type":42,"tag":72,"props":502,"children":504},{"className":503},[],[505],{"type":48,"value":198},{"type":48,"value":507}," for that run.",{"type":42,"tag":51,"props":509,"children":511},{"id":510},"cached-integration-structure",[512],{"type":48,"value":513},"Cached Integration Structure",{"type":42,"tag":58,"props":515,"children":516},{},[517,518,523,525,530,532,538,540,545,546,552,554,560,562,568],{"type":48,"value":256},{"type":42,"tag":72,"props":519,"children":521},{"className":520},[],[522],{"type":48,"value":88},{"type":48,"value":524}," to resolve an integration name or type to an ID, then call ",{"type":42,"tag":72,"props":526,"children":528},{"className":527},[],[529],{"type":48,"value":99},{"type":48,"value":531}," for cached table structure. The response includes integration details plus ",{"type":42,"tag":72,"props":533,"children":535},{"className":534},[],[536],{"type":48,"value":537},"tables",{"type":48,"value":539},", where each table has ",{"type":42,"tag":72,"props":541,"children":543},{"className":542},[],[544],{"type":48,"value":300},{"type":48,"value":109},{"type":42,"tag":72,"props":547,"children":549},{"className":548},[],[550],{"type":48,"value":551},"schema",{"type":48,"value":553},", optional ",{"type":42,"tag":72,"props":555,"children":557},{"className":556},[],[558],{"type":48,"value":559},"database",{"type":48,"value":561},", and cached ",{"type":42,"tag":72,"props":563,"children":565},{"className":564},[],[566],{"type":48,"value":567},"columns",{"type":48,"value":569}," with names and database-native types.",{"type":42,"tag":58,"props":571,"children":572},{},[573,574,579,580,585,586,591],{"type":48,"value":256},{"type":42,"tag":72,"props":575,"children":577},{"className":576},[],[578],{"type":48,"value":107},{"type":48,"value":109},{"type":42,"tag":72,"props":581,"children":583},{"className":582},[],[584],{"type":48,"value":115},{"type":48,"value":143},{"type":42,"tag":72,"props":587,"children":589},{"className":588},[],[590],{"type":48,"value":123},{"type":48,"value":592}," filters when the user asks about a specific database, schema, or exact table. These filters apply to cached structure rows; an empty table list means no matching cached structure is visible through the app tools, not proof that the live database has no such table.",{"type":42,"tag":58,"props":594,"children":595},{},[596],{"type":48,"value":597},"When reporting cached structure, say it is cached. Do not present it as a fresh live database scan, and do not claim access to row previews or query results unless you obtained them from a notebook run snapshot or another exposed app tool.",{"type":42,"tag":51,"props":599,"children":601},{"id":600},"notebook-run-inputs",[602],{"type":48,"value":603},"Notebook Run Inputs",{"type":42,"tag":58,"props":605,"children":606},{},[607,612,614,620,622,627],{"type":42,"tag":72,"props":608,"children":610},{"className":609},[],[611],{"type":48,"value":160},{"type":48,"value":613}," accepts an optional ",{"type":42,"tag":72,"props":615,"children":617},{"className":616},[],[618],{"type":48,"value":619},"inputs",{"type":48,"value":621}," object. Keys must be notebook input names from ",{"type":42,"tag":72,"props":623,"children":625},{"className":624},[],[626],{"type":48,"value":77},{"type":48,"value":628},", not labels or block IDs. Values must match the input block type:",{"type":42,"tag":64,"props":630,"children":631},{},[632,637,642,647,652],{"type":42,"tag":68,"props":633,"children":634},{},[635],{"type":48,"value":636},"Text, textarea, file, date, slider, and single-select inputs use strings.",{"type":42,"tag":68,"props":638,"children":639},{},[640],{"type":48,"value":641},"Checkbox inputs use booleans.",{"type":42,"tag":68,"props":643,"children":644},{},[645],{"type":48,"value":646},"Multi-select inputs use arrays of strings.",{"type":42,"tag":68,"props":648,"children":649},{},[650],{"type":48,"value":651},"Date-range inputs use a string or an array of exactly two strings.",{"type":42,"tag":68,"props":653,"children":654},{},[655],{"type":48,"value":656},"Slider values must be numeric strings.",{"type":42,"tag":58,"props":658,"children":659},{},[660,662,667,669,674],{"type":48,"value":661},"If the user provides a label instead of a name, inspect ",{"type":42,"tag":72,"props":663,"children":665},{"className":664},[],[666],{"type":48,"value":77},{"type":48,"value":668}," inputs and map it to the closest input ",{"type":42,"tag":72,"props":670,"children":672},{"className":671},[],[673],{"type":48,"value":300},{"type":48,"value":675}," only when the match is unambiguous. Otherwise ask for clarification. Run input values apply only to the new run and do not update the notebook's saved defaults.",{"type":42,"tag":51,"props":677,"children":679},{"id":678},"run-snapshots",[680],{"type":48,"value":681},"Run Snapshots",{"type":42,"tag":58,"props":683,"children":684},{},[685,687,692,694,699,701,706,708,714,716,722,724,729],{"type":48,"value":686},"When ",{"type":42,"tag":72,"props":688,"children":690},{"className":689},[],[691],{"type":48,"value":206},{"type":48,"value":693}," is omitted, ",{"type":42,"tag":72,"props":695,"children":697},{"className":696},[],[698],{"type":48,"value":198},{"type":48,"value":700}," returns ",{"type":42,"tag":72,"props":702,"children":704},{"className":703},[],[705],{"type":48,"value":214},{"type":48,"value":707}," for available ",{"type":42,"tag":72,"props":709,"children":711},{"className":710},[],[712],{"type":48,"value":713},".snapshot.deepnote",{"type":48,"value":715}," files and ",{"type":42,"tag":72,"props":717,"children":719},{"className":718},[],[720],{"type":48,"value":721},"snapshotContent: null",{"type":48,"value":723},"; this is equivalent to ",{"type":42,"tag":72,"props":725,"children":727},{"className":726},[],[728],{"type":48,"value":222},{"type":48,"value":730},". The URL is short-lived and grants access to the run snapshot, so do not paste it into the final answer unless the user asks for a download link or file handoff.",{"type":42,"tag":58,"props":732,"children":733},{},[734,735,740],{"type":48,"value":256},{"type":42,"tag":72,"props":736,"children":738},{"className":737},[],[739],{"type":48,"value":230},{"type":48,"value":741}," when the user asks you to inspect outputs, summarize results, diagnose a failed run from snapshot details, map visible references from the snapshot, or otherwise reason over the snapshot content. Inline snapshots can be large and sensitive, so summarize the relevant blocks, outputs, failures, or data shape instead of dumping raw content.",{"type":42,"tag":58,"props":743,"children":744},{},[745,747,752,754,759,761,766,768,773],{"type":48,"value":746},"If the current Deepnote app tool schema does not expose ",{"type":42,"tag":72,"props":748,"children":750},{"className":749},[],[751],{"type":48,"value":206},{"type":48,"value":753},", use the fields returned by ",{"type":42,"tag":72,"props":755,"children":757},{"className":756},[],[758],{"type":48,"value":198},{"type":48,"value":760}," as-is and do not invent ",{"type":42,"tag":72,"props":762,"children":764},{"className":763},[],[765],{"type":48,"value":238},{"type":48,"value":767}," or ",{"type":42,"tag":72,"props":769,"children":771},{"className":770},[],[772],{"type":48,"value":214},{"type":48,"value":125},{"type":42,"tag":51,"props":775,"children":777},{"id":776},"sensitive-outputs",[778],{"type":48,"value":779},"Sensitive Outputs",{"type":42,"tag":58,"props":781,"children":782},{},[783],{"type":48,"value":784},"When snapshot content, snapshot download URLs, or errors include sensitive, proprietary, personal, or production-like data, minimize exposure in the response. Summarize the result, shape, quality issues, aggregates, or failure mode instead of dumping raw records, presigned URLs, or long logs.",{"type":42,"tag":51,"props":786,"children":788},{"id":787},"environment-changes",[789],{"type":48,"value":790},"Environment Changes",{"type":42,"tag":58,"props":792,"children":793},{},[794],{"type":48,"value":795},"The Deepnote app tools currently do not expose environment mutation tools. Do not claim to change package versions, environment images, hardware, integrations, credentials, secrets, scheduled runs, or shared app settings unless a current tool explicitly supports that action.",{"type":42,"tag":51,"props":797,"children":799},{"id":798},"reporting-results",[800],{"type":48,"value":801},"Reporting Results",{"type":42,"tag":58,"props":803,"children":804},{},[805,807,812],{"type":48,"value":806},"For successful runs, include the executed notebook name or ID, run ID, status, any input overrides that are safe to mention, and the important result from inline snapshot content when you requested it. If you only have ",{"type":42,"tag":72,"props":808,"children":810},{"className":809},[],[811],{"type":48,"value":214},{"type":48,"value":813},", mention that a snapshot is available without exposing the URL by default. For failures, include concise error detail and the next fix to try. If a run fails before it starts, such as a workspace or parallel run limit, report the user-facing API error directly. Avoid pasting long logs unless the user asks for them.",{"type":42,"tag":58,"props":815,"children":816},{},[817],{"type":48,"value":818},"Keep run reports brief and information-dense unless the user asks for detail. Prefer one compact run table plus the most important result or first actionable error. Do not paste long logs, raw snapshots, or full notebook outputs by default.",{"type":42,"tag":58,"props":820,"children":821},{},[822],{"type":48,"value":823},"Prefer this run summary shape:",{"type":42,"tag":825,"props":826,"children":827},"table",{},[828,847],{"type":42,"tag":829,"props":830,"children":831},"thead",{},[832],{"type":42,"tag":833,"props":834,"children":835},"tr",{},[836,842],{"type":42,"tag":837,"props":838,"children":839},"th",{},[840],{"type":48,"value":841},"Field",{"type":42,"tag":837,"props":843,"children":844},{},[845],{"type":48,"value":846},"Value",{"type":42,"tag":848,"props":849,"children":850},"tbody",{},[851,869,886,925,942,965,989],{"type":42,"tag":833,"props":852,"children":853},{},[854,860],{"type":42,"tag":855,"props":856,"children":857},"td",{},[858],{"type":48,"value":859},"Notebook",{"type":42,"tag":855,"props":861,"children":862},{},[863],{"type":42,"tag":72,"props":864,"children":866},{"className":865},[],[867],{"type":48,"value":868},"Notebook name",{"type":42,"tag":833,"props":870,"children":871},{},[872,877],{"type":42,"tag":855,"props":873,"children":874},{},[875],{"type":48,"value":876},"Run ID",{"type":42,"tag":855,"props":878,"children":879},{},[880],{"type":42,"tag":72,"props":881,"children":883},{"className":882},[],[884],{"type":48,"value":885},"run-id",{"type":42,"tag":833,"props":887,"children":888},{},[889,894],{"type":42,"tag":855,"props":890,"children":891},{},[892],{"type":48,"value":893},"Status",{"type":42,"tag":855,"props":895,"children":896},{},[897,903,904,910,911,917,919],{"type":42,"tag":72,"props":898,"children":900},{"className":899},[],[901],{"type":48,"value":902},"success",{"type":48,"value":109},{"type":42,"tag":72,"props":905,"children":907},{"className":906},[],[908],{"type":48,"value":909},"failed",{"type":48,"value":109},{"type":42,"tag":72,"props":912,"children":914},{"className":913},[],[915],{"type":48,"value":916},"pending",{"type":48,"value":918},", or ",{"type":42,"tag":72,"props":920,"children":922},{"className":921},[],[923],{"type":48,"value":924},"running",{"type":42,"tag":833,"props":926,"children":927},{},[928,933],{"type":42,"tag":855,"props":929,"children":930},{},[931],{"type":48,"value":932},"Started",{"type":42,"tag":855,"props":934,"children":935},{},[936],{"type":42,"tag":72,"props":937,"children":939},{"className":938},[],[940],{"type":48,"value":941},"YYYY-MM-DD HH:MM UTC",{"type":42,"tag":833,"props":943,"children":944},{},[945,950],{"type":42,"tag":855,"props":946,"children":947},{},[948],{"type":48,"value":949},"Completed",{"type":42,"tag":855,"props":951,"children":952},{},[953,958,959],{"type":42,"tag":72,"props":954,"children":956},{"className":955},[],[957],{"type":48,"value":941},{"type":48,"value":767},{"type":42,"tag":72,"props":960,"children":962},{"className":961},[],[963],{"type":48,"value":964},"Still running",{"type":42,"tag":833,"props":966,"children":967},{},[968,973],{"type":42,"tag":855,"props":969,"children":970},{},[971],{"type":48,"value":972},"Inputs",{"type":42,"tag":855,"props":974,"children":975},{},[976,982,983],{"type":42,"tag":72,"props":977,"children":979},{"className":978},[],[980],{"type":48,"value":981},"safe input summary",{"type":48,"value":767},{"type":42,"tag":72,"props":984,"children":986},{"className":985},[],[987],{"type":48,"value":988},"None",{"type":42,"tag":833,"props":990,"children":991},{},[992,997],{"type":42,"tag":855,"props":993,"children":994},{},[995],{"type":48,"value":996},"Result",{"type":42,"tag":855,"props":998,"children":999},{},[1000],{"type":42,"tag":72,"props":1001,"children":1003},{"className":1002},[],[1004],{"type":48,"value":1005},"short result summary",{"type":42,"tag":58,"props":1007,"children":1008},{},[1009],{"type":48,"value":1010},"For failed or stuck runs, use a debugging report:",{"type":42,"tag":825,"props":1012,"children":1013},{},[1014,1030],{"type":42,"tag":829,"props":1015,"children":1016},{},[1017],{"type":42,"tag":833,"props":1018,"children":1019},{},[1020,1025],{"type":42,"tag":837,"props":1021,"children":1022},{},[1023],{"type":48,"value":1024},"Check",{"type":42,"tag":837,"props":1026,"children":1027},{},[1028],{"type":48,"value":1029},"Finding",{"type":42,"tag":848,"props":1031,"children":1032},{},[1033,1062,1079,1124],{"type":42,"tag":833,"props":1034,"children":1035},{},[1036,1041],{"type":42,"tag":855,"props":1037,"children":1038},{},[1039],{"type":48,"value":1040},"Run state",{"type":42,"tag":855,"props":1042,"children":1043},{},[1044,1049,1050,1055,1056],{"type":42,"tag":72,"props":1045,"children":1047},{"className":1046},[],[1048],{"type":48,"value":909},{"type":48,"value":109},{"type":42,"tag":72,"props":1051,"children":1053},{"className":1052},[],[1054],{"type":48,"value":916},{"type":48,"value":918},{"type":42,"tag":72,"props":1057,"children":1059},{"className":1058},[],[1060],{"type":48,"value":1061},"running for N minutes",{"type":42,"tag":833,"props":1063,"children":1064},{},[1065,1070],{"type":42,"tag":855,"props":1066,"children":1067},{},[1068],{"type":48,"value":1069},"First actionable error",{"type":42,"tag":855,"props":1071,"children":1072},{},[1073],{"type":42,"tag":72,"props":1074,"children":1076},{"className":1075},[],[1077],{"type":48,"value":1078},"short error text",{"type":42,"tag":833,"props":1080,"children":1081},{},[1082,1087],{"type":42,"tag":855,"props":1083,"children":1084},{},[1085],{"type":48,"value":1086},"Likely cause",{"type":42,"tag":855,"props":1088,"children":1089},{},[1090,1096,1097,1103,1104,1110,1111,1117,1118],{"type":42,"tag":72,"props":1091,"children":1093},{"className":1092},[],[1094],{"type":48,"value":1095},"missing input",{"type":48,"value":109},{"type":42,"tag":72,"props":1098,"children":1100},{"className":1099},[],[1101],{"type":48,"value":1102},"missing file",{"type":48,"value":109},{"type":42,"tag":72,"props":1105,"children":1107},{"className":1106},[],[1108],{"type":48,"value":1109},"server not listening",{"type":48,"value":109},{"type":42,"tag":72,"props":1112,"children":1114},{"className":1113},[],[1115],{"type":48,"value":1116},"dependency failure",{"type":48,"value":918},{"type":42,"tag":72,"props":1119,"children":1121},{"className":1120},[],[1122],{"type":48,"value":1123},"unknown from app tools",{"type":42,"tag":833,"props":1125,"children":1126},{},[1127,1132],{"type":42,"tag":855,"props":1128,"children":1129},{},[1130],{"type":48,"value":1131},"Safe next step",{"type":42,"tag":855,"props":1133,"children":1134},{},[1135,1141,1142,1148,1149,1155,1156],{"type":42,"tag":72,"props":1136,"children":1138},{"className":1137},[],[1139],{"type":48,"value":1140},"inspect notebook",{"type":48,"value":109},{"type":42,"tag":72,"props":1143,"children":1145},{"className":1144},[],[1146],{"type":48,"value":1147},"rerun with inputs",{"type":48,"value":109},{"type":42,"tag":72,"props":1150,"children":1152},{"className":1151},[],[1153],{"type":48,"value":1154},"start serving notebook",{"type":48,"value":918},{"type":42,"tag":72,"props":1157,"children":1159},{"className":1158},[],[1160],{"type":48,"value":1161},"manual Deepnote action needed",{"type":42,"tag":58,"props":1163,"children":1164},{},[1165],{"type":48,"value":1166},"When inspecting a large run snapshot, request inline delivery only when necessary, then summarize block counts, failed blocks, final outputs, and the first actionable error instead of pasting the snapshot.",{"items":1168,"total":1288},[1169,1187,1203,1215,1235,1257,1277],{"slug":1170,"name":1170,"fn":1171,"description":1172,"org":1173,"tags":1174,"stars":25,"repoUrl":26,"updatedAt":27},"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},[1175,1178,1181,1184],{"name":1176,"slug":1177,"type":15},"Accessibility","accessibility",{"name":1179,"slug":1180,"type":15},"Charts","charts",{"name":1182,"slug":1183,"type":15},"Data Visualization","data-visualization",{"name":1185,"slug":1186,"type":15},"Design","design",{"slug":1188,"name":1188,"fn":1189,"description":1190,"org":1191,"tags":1192,"stars":25,"repoUrl":26,"updatedAt":1202},"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},[1193,1196,1199],{"name":1194,"slug":1195,"type":15},"Agents","agents",{"name":1197,"slug":1198,"type":15},"Browser Automation","browser-automation",{"name":1200,"slug":1201,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1204,"name":1204,"fn":1205,"description":1206,"org":1207,"tags":1208,"stars":25,"repoUrl":26,"updatedAt":1214},"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},[1209,1210,1213],{"name":1197,"slug":1198,"type":15},{"name":1211,"slug":1212,"type":15},"Local Development","local-development",{"name":1200,"slug":1201,"type":15},"2026-04-06T18:41:17.526867",{"slug":1216,"name":1216,"fn":1217,"description":1218,"org":1219,"tags":1220,"stars":25,"repoUrl":26,"updatedAt":1234},"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},[1221,1222,1225,1228,1231],{"name":1194,"slug":1195,"type":15},{"name":1223,"slug":1224,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1226,"slug":1227,"type":15},"SDK","sdk",{"name":1229,"slug":1230,"type":15},"Serverless","serverless",{"name":1232,"slug":1233,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1236,"name":1236,"fn":1237,"description":1238,"org":1239,"tags":1240,"stars":25,"repoUrl":26,"updatedAt":1256},"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},[1241,1244,1247,1250,1253],{"name":1242,"slug":1243,"type":15},"Frontend","frontend",{"name":1245,"slug":1246,"type":15},"React","react",{"name":1248,"slug":1249,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1251,"slug":1252,"type":15},"UI Components","ui-components",{"name":1254,"slug":1255,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1258,"name":1258,"fn":1259,"description":1260,"org":1261,"tags":1262,"stars":25,"repoUrl":26,"updatedAt":1276},"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},[1263,1266,1269,1272,1275],{"name":1264,"slug":1265,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1267,"slug":1268,"type":15},"Cost Optimization","cost-optimization",{"name":1270,"slug":1271,"type":15},"LLM","llm",{"name":1273,"slug":1274,"type":15},"Performance","performance",{"name":1254,"slug":1255,"type":15},"2026-04-06T18:40:44.377464",{"slug":1278,"name":1278,"fn":1279,"description":1280,"org":1281,"tags":1282,"stars":25,"repoUrl":26,"updatedAt":1287},"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},[1283,1284,1286],{"name":1267,"slug":1268,"type":15},{"name":1285,"slug":559,"type":15},"Database",{"name":1270,"slug":1271,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1290,"total":1487},[1291,1312,1335,1352,1368,1385,1404,1416,1430,1444,1456,1471],{"slug":1292,"name":1292,"fn":1293,"description":1294,"org":1295,"tags":1296,"stars":1309,"repoUrl":1310,"updatedAt":1311},"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},[1297,1300,1303,1306],{"name":1298,"slug":1299,"type":15},"Documents","documents",{"name":1301,"slug":1302,"type":15},"Healthcare","healthcare",{"name":1304,"slug":1305,"type":15},"Insurance","insurance",{"name":1307,"slug":1308,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1313,"name":1313,"fn":1314,"description":1315,"org":1316,"tags":1317,"stars":1332,"repoUrl":1333,"updatedAt":1334},"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},[1318,1321,1323,1326,1329],{"name":1319,"slug":1320,"type":15},".NET","dotnet",{"name":1322,"slug":1313,"type":15},"ASP.NET Core",{"name":1324,"slug":1325,"type":15},"Blazor","blazor",{"name":1327,"slug":1328,"type":15},"C#","csharp",{"name":1330,"slug":1331,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1336,"name":1336,"fn":1337,"description":1338,"org":1339,"tags":1340,"stars":1332,"repoUrl":1333,"updatedAt":1351},"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},[1341,1344,1347,1350],{"name":1342,"slug":1343,"type":15},"Apps SDK","apps-sdk",{"name":1345,"slug":1346,"type":15},"ChatGPT","chatgpt",{"name":1348,"slug":1349,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1353,"name":1353,"fn":1354,"description":1355,"org":1356,"tags":1357,"stars":1332,"repoUrl":1333,"updatedAt":1367},"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},[1358,1361,1364],{"name":1359,"slug":1360,"type":15},"API Development","api-development",{"name":1362,"slug":1363,"type":15},"CLI","cli",{"name":1365,"slug":1366,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1369,"name":1369,"fn":1370,"description":1371,"org":1372,"tags":1373,"stars":1332,"repoUrl":1333,"updatedAt":1384},"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},[1374,1377,1380,1381],{"name":1375,"slug":1376,"type":15},"Cloudflare","cloudflare",{"name":1378,"slug":1379,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1223,"slug":1224,"type":15},{"name":1382,"slug":1383,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1386,"name":1386,"fn":1387,"description":1388,"org":1389,"tags":1390,"stars":1332,"repoUrl":1333,"updatedAt":1403},"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},[1391,1394,1397,1400],{"name":1392,"slug":1393,"type":15},"Productivity","productivity",{"name":1395,"slug":1396,"type":15},"Project Management","project-management",{"name":1398,"slug":1399,"type":15},"Strategy","strategy",{"name":1401,"slug":1402,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1405,"name":1405,"fn":1406,"description":1407,"org":1408,"tags":1409,"stars":1332,"repoUrl":1333,"updatedAt":1415},"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},[1410,1411,1413,1414],{"name":1185,"slug":1186,"type":15},{"name":1412,"slug":1405,"type":15},"Figma",{"name":1242,"slug":1243,"type":15},{"name":1348,"slug":1349,"type":15},"2026-04-12T05:06:47.939943",{"slug":1417,"name":1417,"fn":1418,"description":1419,"org":1420,"tags":1421,"stars":1332,"repoUrl":1333,"updatedAt":1429},"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},[1422,1423,1426,1427,1428],{"name":1185,"slug":1186,"type":15},{"name":1424,"slug":1425,"type":15},"Design System","design-system",{"name":1412,"slug":1405,"type":15},{"name":1242,"slug":1243,"type":15},{"name":1251,"slug":1252,"type":15},"2026-05-10T05:59:52.971881",{"slug":1431,"name":1431,"fn":1432,"description":1433,"org":1434,"tags":1435,"stars":1332,"repoUrl":1333,"updatedAt":1443},"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},[1436,1437,1438,1441,1442],{"name":1185,"slug":1186,"type":15},{"name":1424,"slug":1425,"type":15},{"name":1439,"slug":1440,"type":15},"Documentation","documentation",{"name":1412,"slug":1405,"type":15},{"name":1242,"slug":1243,"type":15},"2026-05-16T06:07:47.821474",{"slug":1445,"name":1445,"fn":1446,"description":1447,"org":1448,"tags":1449,"stars":1332,"repoUrl":1333,"updatedAt":1455},"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},[1450,1451,1452,1453,1454],{"name":1185,"slug":1186,"type":15},{"name":1412,"slug":1405,"type":15},{"name":1242,"slug":1243,"type":15},{"name":1251,"slug":1252,"type":15},{"name":1330,"slug":1331,"type":15},"2026-05-16T06:07:40.583615",{"slug":1457,"name":1457,"fn":1458,"description":1459,"org":1460,"tags":1461,"stars":1332,"repoUrl":1333,"updatedAt":1470},"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},[1462,1465,1466,1469],{"name":1463,"slug":1464,"type":15},"Animation","animation",{"name":1365,"slug":1366,"type":15},{"name":1467,"slug":1468,"type":15},"Creative","creative",{"name":1185,"slug":1186,"type":15},"2026-05-02T05:31:48.48485",{"slug":1472,"name":1472,"fn":1473,"description":1474,"org":1475,"tags":1476,"stars":1332,"repoUrl":1333,"updatedAt":1486},"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},[1477,1478,1479,1482,1485],{"name":1467,"slug":1468,"type":15},{"name":1185,"slug":1186,"type":15},{"name":1480,"slug":1481,"type":15},"Image Generation","image-generation",{"name":1483,"slug":1484,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]