[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-deepnote-notebooks":3,"mdc--ftnbf4-key":39,"related-org-openai-deepnote-notebooks":711,"related-repo-openai-deepnote-notebooks":918},{"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},"deepnote-notebooks","reason about Deepnote notebooks","Use when reading, reviewing, inspecting, or reasoning about hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook 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",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Python","python",{"name":20,"slug":21,"type":15},"SQL","sql",{"name":23,"slug":24,"type":15},"Notebooks","notebooks",{"name":26,"slug":27,"type":15},"Jupyter","jupyter",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-06-30T19:00:57.102",null,465,[],{"repoUrl":29,"stars":28,"forks":32,"topics":35,"description":36},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fdeepnote\u002Fskills\u002Fdeepnote-notebooks","---\nname: deepnote-notebooks\ndescription: Use when reading, reviewing, inspecting, or reasoning about hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook outputs through the Deepnote app tools.\n---\n\n# Deepnote Notebooks\n\n## Notebook Inspection Workflow\n\n1. Resolve the target notebook with `search` or project context before using `get_notebook`.\n2. Read the notebook with `get_notebook` before answering questions about structure, inputs, blocks, or latest run state.\n3. Preserve distinctions between block types, notebook inputs, code, SQL, markdown, and metadata in your reasoning.\n4. When reporting inputs, include the input `name`, `type`, current `value`, and `label` when useful.\n5. When SQL connection usage matters, use `list_integrations` and the integration usage tools to confirm project, notebook, or block references instead of inferring solely from names. When table, schema, or column context matters, use `get_integration` for cached structure.\n6. When asked to review or explain a notebook, ground the answer in specific notebook\u002Fblock names or IDs when useful.\n7. If the user asks to create a project, create a notebook, add blocks\u002Fcells, update existing blocks\u002Fcells, or scaffold notebook content, use the `deepnote-notebook-editing` skill.\n8. If the user asks for recent runs, failed runs, or run history, use `list_notebook_runs` before selecting a run for `get_run`.\n\n## Notebook Inspection Output\n\nGreat notebook-inspection output should help the user decide what the notebook does, whether it is safe to run, and what to do next. Prefer this structure:\n\nKeep notebook inspection brief and high signal by default. Lead with the answer, then include only the tables or cautions that materially help the user. Omit exhaustive block listings, raw code, and long outputs unless the user asks for more detail.\n\n1. Start with a one-sentence brief: `Notebook \"Name\" in project \"Project\" has 12 blocks, 2 inputs, 1 visible connection, and last ran successfully on YYYY-MM-DD HH:MM UTC.`\n1. Show a compact status table:\n\n| Field | Value |\n| --- | --- |\n| Project | `Project name` |\n| Notebook | `Notebook name` |\n| Notebook ID | `notebook-id` |\n| Scheduled | `Yes` or `No` |\n| Last Run | `status\u002Fdate\u002Frun id` or `No run visible` |\n| Visible Connections | `Integration name (type)` or `None visible via app tools` |\n\n1. If inputs exist, add an inputs table:\n\n| Input | Type | Current Value | Label |\n| --- | --- | --- | --- |\n| `input_name` | `text` | `safe summary or value` | `Human label` |\n\n1. Add a block map when useful, especially for reviews and debugging:\n\n| Order | Type | Purpose | Connection \u002F Output |\n| --- | --- | --- | --- |\n| `1` | `sql` | `SELECT demo.gapminder sample` | `Clickhouse (clickhouse)` |\n\n1. Add `Cautions` only when actionable: cells that print environment variables, hard-coded credentials, mutating external calls, long-running servers, large dataset dumps, missing inputs, failed\u002Fpending last runs, SQL blocks whose integration is not visible, or integration usage that was not checked when it matters.\n1. End with `Useful Next Actions` only when it helps, such as run notebook, inspect latest run, list recent runs, map integrations, summarize outputs, or review risky cells.\n\nWhen the Deepnote app tools do not expose a detail, say `Not visible via app tools` rather than inferring from names. Keep raw code excerpts short; summarize large cells and mention block IDs when useful.\n\n## Code And Output Handling\n\n- Before suggesting code changes, inspect nearby blocks for imports, shared variables, SQL connections, inputs, and upstream assumptions.\n- Prefer deterministic notebook code. Avoid hidden global state, implicit external files, or hard-coded credentials.\n- Do not claim an edit was applied unless a write-capable tool is available and reports success. For project, notebook, block creation, and existing block updates, use `deepnote-notebook-editing`.\n- If you run a notebook, pass requested input values through `create_run.inputs` using the input `name` fields returned by `get_notebook`, then capture run status with `get_run`. Omit `snapshotDelivery` for status checks so the default download URL delivery is used; request `snapshotDelivery: \"inline\"` when you need to summarize snapshot content or errors.\n- Run input values do not change the notebook's saved default input values.\n- For SQL blocks, preserve the existing connection or data source in recommendations unless the user asks to move it. Use `get_integration` for cached table\u002Fcolumn context when needed.\n- Before running a notebook, flag cells that print `os.environ`, environment variables, credentials, tokens, or broad secret dumps. Do not run those notebooks unless the user explicitly confirms after the risk is named.\n- Treat cells that start servers, send network requests, write files, cancel\u002Fmodify external records, or call production-like systems as stateful. Call out the side effect before execution.\n\n## Review And Cleanup\n\nUse Deepnote app reads to verify notebook structure before making claims. If execution was not run, say so plainly and mention the remaining risk. For larger reviews, summarize relevant sections rather than listing every block.\n",{"data":40,"body":41},{"name":4,"description":6},{"type":42,"children":43},"root",[44,52,59,199,205,211,216,235,387,395,465,473,542,571,584,590,700,706],{"type":45,"tag":46,"props":47,"children":48},"element","h1",{"id":4},[49],{"type":50,"value":51},"text","Deepnote Notebooks",{"type":45,"tag":53,"props":54,"children":56},"h2",{"id":55},"notebook-inspection-workflow",[57],{"type":50,"value":58},"Notebook Inspection Workflow",{"type":45,"tag":60,"props":61,"children":62},"ol",{},[63,86,98,103,140,161,166,179],{"type":45,"tag":64,"props":65,"children":66},"li",{},[67,69,76,78,84],{"type":50,"value":68},"Resolve the target notebook with ",{"type":45,"tag":70,"props":71,"children":73},"code",{"className":72},[],[74],{"type":50,"value":75},"search",{"type":50,"value":77}," or project context before using ",{"type":45,"tag":70,"props":79,"children":81},{"className":80},[],[82],{"type":50,"value":83},"get_notebook",{"type":50,"value":85},".",{"type":45,"tag":64,"props":87,"children":88},{},[89,91,96],{"type":50,"value":90},"Read the notebook with ",{"type":45,"tag":70,"props":92,"children":94},{"className":93},[],[95],{"type":50,"value":83},{"type":50,"value":97}," before answering questions about structure, inputs, blocks, or latest run state.",{"type":45,"tag":64,"props":99,"children":100},{},[101],{"type":50,"value":102},"Preserve distinctions between block types, notebook inputs, code, SQL, markdown, and metadata in your reasoning.",{"type":45,"tag":64,"props":104,"children":105},{},[106,108,114,116,122,124,130,132,138],{"type":50,"value":107},"When reporting inputs, include the input ",{"type":45,"tag":70,"props":109,"children":111},{"className":110},[],[112],{"type":50,"value":113},"name",{"type":50,"value":115},", ",{"type":45,"tag":70,"props":117,"children":119},{"className":118},[],[120],{"type":50,"value":121},"type",{"type":50,"value":123},", current ",{"type":45,"tag":70,"props":125,"children":127},{"className":126},[],[128],{"type":50,"value":129},"value",{"type":50,"value":131},", and ",{"type":45,"tag":70,"props":133,"children":135},{"className":134},[],[136],{"type":50,"value":137},"label",{"type":50,"value":139}," when useful.",{"type":45,"tag":64,"props":141,"children":142},{},[143,145,151,153,159],{"type":50,"value":144},"When SQL connection usage matters, use ",{"type":45,"tag":70,"props":146,"children":148},{"className":147},[],[149],{"type":50,"value":150},"list_integrations",{"type":50,"value":152}," and the integration usage tools to confirm project, notebook, or block references instead of inferring solely from names. When table, schema, or column context matters, use ",{"type":45,"tag":70,"props":154,"children":156},{"className":155},[],[157],{"type":50,"value":158},"get_integration",{"type":50,"value":160}," for cached structure.",{"type":45,"tag":64,"props":162,"children":163},{},[164],{"type":50,"value":165},"When asked to review or explain a notebook, ground the answer in specific notebook\u002Fblock names or IDs when useful.",{"type":45,"tag":64,"props":167,"children":168},{},[169,171,177],{"type":50,"value":170},"If the user asks to create a project, create a notebook, add blocks\u002Fcells, update existing blocks\u002Fcells, or scaffold notebook content, use the ",{"type":45,"tag":70,"props":172,"children":174},{"className":173},[],[175],{"type":50,"value":176},"deepnote-notebook-editing",{"type":50,"value":178}," skill.",{"type":45,"tag":64,"props":180,"children":181},{},[182,184,190,192,198],{"type":50,"value":183},"If the user asks for recent runs, failed runs, or run history, use ",{"type":45,"tag":70,"props":185,"children":187},{"className":186},[],[188],{"type":50,"value":189},"list_notebook_runs",{"type":50,"value":191}," before selecting a run for ",{"type":45,"tag":70,"props":193,"children":195},{"className":194},[],[196],{"type":50,"value":197},"get_run",{"type":50,"value":85},{"type":45,"tag":53,"props":200,"children":202},{"id":201},"notebook-inspection-output",[203],{"type":50,"value":204},"Notebook Inspection Output",{"type":45,"tag":206,"props":207,"children":208},"p",{},[209],{"type":50,"value":210},"Great notebook-inspection output should help the user decide what the notebook does, whether it is safe to run, and what to do next. Prefer this structure:",{"type":45,"tag":206,"props":212,"children":213},{},[214],{"type":50,"value":215},"Keep notebook inspection brief and high signal by default. Lead with the answer, then include only the tables or cautions that materially help the user. Omit exhaustive block listings, raw code, and long outputs unless the user asks for more detail.",{"type":45,"tag":60,"props":217,"children":218},{},[219,230],{"type":45,"tag":64,"props":220,"children":221},{},[222,224],{"type":50,"value":223},"Start with a one-sentence brief: ",{"type":45,"tag":70,"props":225,"children":227},{"className":226},[],[228],{"type":50,"value":229},"Notebook \"Name\" in project \"Project\" has 12 blocks, 2 inputs, 1 visible connection, and last ran successfully on YYYY-MM-DD HH:MM UTC.",{"type":45,"tag":64,"props":231,"children":232},{},[233],{"type":50,"value":234},"Show a compact status table:",{"type":45,"tag":236,"props":237,"children":238},"table",{},[239,258],{"type":45,"tag":240,"props":241,"children":242},"thead",{},[243],{"type":45,"tag":244,"props":245,"children":246},"tr",{},[247,253],{"type":45,"tag":248,"props":249,"children":250},"th",{},[251],{"type":50,"value":252},"Field",{"type":45,"tag":248,"props":254,"children":255},{},[256],{"type":50,"value":257},"Value",{"type":45,"tag":259,"props":260,"children":261},"tbody",{},[262,280,297,314,339,363],{"type":45,"tag":244,"props":263,"children":264},{},[265,271],{"type":45,"tag":266,"props":267,"children":268},"td",{},[269],{"type":50,"value":270},"Project",{"type":45,"tag":266,"props":272,"children":273},{},[274],{"type":45,"tag":70,"props":275,"children":277},{"className":276},[],[278],{"type":50,"value":279},"Project name",{"type":45,"tag":244,"props":281,"children":282},{},[283,288],{"type":45,"tag":266,"props":284,"children":285},{},[286],{"type":50,"value":287},"Notebook",{"type":45,"tag":266,"props":289,"children":290},{},[291],{"type":45,"tag":70,"props":292,"children":294},{"className":293},[],[295],{"type":50,"value":296},"Notebook name",{"type":45,"tag":244,"props":298,"children":299},{},[300,305],{"type":45,"tag":266,"props":301,"children":302},{},[303],{"type":50,"value":304},"Notebook ID",{"type":45,"tag":266,"props":306,"children":307},{},[308],{"type":45,"tag":70,"props":309,"children":311},{"className":310},[],[312],{"type":50,"value":313},"notebook-id",{"type":45,"tag":244,"props":315,"children":316},{},[317,322],{"type":45,"tag":266,"props":318,"children":319},{},[320],{"type":50,"value":321},"Scheduled",{"type":45,"tag":266,"props":323,"children":324},{},[325,331,333],{"type":45,"tag":70,"props":326,"children":328},{"className":327},[],[329],{"type":50,"value":330},"Yes",{"type":50,"value":332}," or ",{"type":45,"tag":70,"props":334,"children":336},{"className":335},[],[337],{"type":50,"value":338},"No",{"type":45,"tag":244,"props":340,"children":341},{},[342,347],{"type":45,"tag":266,"props":343,"children":344},{},[345],{"type":50,"value":346},"Last Run",{"type":45,"tag":266,"props":348,"children":349},{},[350,356,357],{"type":45,"tag":70,"props":351,"children":353},{"className":352},[],[354],{"type":50,"value":355},"status\u002Fdate\u002Frun id",{"type":50,"value":332},{"type":45,"tag":70,"props":358,"children":360},{"className":359},[],[361],{"type":50,"value":362},"No run visible",{"type":45,"tag":244,"props":364,"children":365},{},[366,371],{"type":45,"tag":266,"props":367,"children":368},{},[369],{"type":50,"value":370},"Visible Connections",{"type":45,"tag":266,"props":372,"children":373},{},[374,380,381],{"type":45,"tag":70,"props":375,"children":377},{"className":376},[],[378],{"type":50,"value":379},"Integration name (type)",{"type":50,"value":332},{"type":45,"tag":70,"props":382,"children":384},{"className":383},[],[385],{"type":50,"value":386},"None visible via app tools",{"type":45,"tag":60,"props":388,"children":389},{},[390],{"type":45,"tag":64,"props":391,"children":392},{},[393],{"type":50,"value":394},"If inputs exist, add an inputs table:",{"type":45,"tag":236,"props":396,"children":397},{},[398,424],{"type":45,"tag":240,"props":399,"children":400},{},[401],{"type":45,"tag":244,"props":402,"children":403},{},[404,409,414,419],{"type":45,"tag":248,"props":405,"children":406},{},[407],{"type":50,"value":408},"Input",{"type":45,"tag":248,"props":410,"children":411},{},[412],{"type":50,"value":413},"Type",{"type":45,"tag":248,"props":415,"children":416},{},[417],{"type":50,"value":418},"Current Value",{"type":45,"tag":248,"props":420,"children":421},{},[422],{"type":50,"value":423},"Label",{"type":45,"tag":259,"props":425,"children":426},{},[427],{"type":45,"tag":244,"props":428,"children":429},{},[430,439,447,456],{"type":45,"tag":266,"props":431,"children":432},{},[433],{"type":45,"tag":70,"props":434,"children":436},{"className":435},[],[437],{"type":50,"value":438},"input_name",{"type":45,"tag":266,"props":440,"children":441},{},[442],{"type":45,"tag":70,"props":443,"children":445},{"className":444},[],[446],{"type":50,"value":50},{"type":45,"tag":266,"props":448,"children":449},{},[450],{"type":45,"tag":70,"props":451,"children":453},{"className":452},[],[454],{"type":50,"value":455},"safe summary or value",{"type":45,"tag":266,"props":457,"children":458},{},[459],{"type":45,"tag":70,"props":460,"children":462},{"className":461},[],[463],{"type":50,"value":464},"Human label",{"type":45,"tag":60,"props":466,"children":467},{},[468],{"type":45,"tag":64,"props":469,"children":470},{},[471],{"type":50,"value":472},"Add a block map when useful, especially for reviews and debugging:",{"type":45,"tag":236,"props":474,"children":475},{},[476,501],{"type":45,"tag":240,"props":477,"children":478},{},[479],{"type":45,"tag":244,"props":480,"children":481},{},[482,487,491,496],{"type":45,"tag":248,"props":483,"children":484},{},[485],{"type":50,"value":486},"Order",{"type":45,"tag":248,"props":488,"children":489},{},[490],{"type":50,"value":413},{"type":45,"tag":248,"props":492,"children":493},{},[494],{"type":50,"value":495},"Purpose",{"type":45,"tag":248,"props":497,"children":498},{},[499],{"type":50,"value":500},"Connection \u002F Output",{"type":45,"tag":259,"props":502,"children":503},{},[504],{"type":45,"tag":244,"props":505,"children":506},{},[507,516,524,533],{"type":45,"tag":266,"props":508,"children":509},{},[510],{"type":45,"tag":70,"props":511,"children":513},{"className":512},[],[514],{"type":50,"value":515},"1",{"type":45,"tag":266,"props":517,"children":518},{},[519],{"type":45,"tag":70,"props":520,"children":522},{"className":521},[],[523],{"type":50,"value":21},{"type":45,"tag":266,"props":525,"children":526},{},[527],{"type":45,"tag":70,"props":528,"children":530},{"className":529},[],[531],{"type":50,"value":532},"SELECT demo.gapminder sample",{"type":45,"tag":266,"props":534,"children":535},{},[536],{"type":45,"tag":70,"props":537,"children":539},{"className":538},[],[540],{"type":50,"value":541},"Clickhouse (clickhouse)",{"type":45,"tag":60,"props":543,"children":544},{},[545,558],{"type":45,"tag":64,"props":546,"children":547},{},[548,550,556],{"type":50,"value":549},"Add ",{"type":45,"tag":70,"props":551,"children":553},{"className":552},[],[554],{"type":50,"value":555},"Cautions",{"type":50,"value":557}," only when actionable: cells that print environment variables, hard-coded credentials, mutating external calls, long-running servers, large dataset dumps, missing inputs, failed\u002Fpending last runs, SQL blocks whose integration is not visible, or integration usage that was not checked when it matters.",{"type":45,"tag":64,"props":559,"children":560},{},[561,563,569],{"type":50,"value":562},"End with ",{"type":45,"tag":70,"props":564,"children":566},{"className":565},[],[567],{"type":50,"value":568},"Useful Next Actions",{"type":50,"value":570}," only when it helps, such as run notebook, inspect latest run, list recent runs, map integrations, summarize outputs, or review risky cells.",{"type":45,"tag":206,"props":572,"children":573},{},[574,576,582],{"type":50,"value":575},"When the Deepnote app tools do not expose a detail, say ",{"type":45,"tag":70,"props":577,"children":579},{"className":578},[],[580],{"type":50,"value":581},"Not visible via app tools",{"type":50,"value":583}," rather than inferring from names. Keep raw code excerpts short; summarize large cells and mention block IDs when useful.",{"type":45,"tag":53,"props":585,"children":587},{"id":586},"code-and-output-handling",[588],{"type":50,"value":589},"Code And Output Handling",{"type":45,"tag":591,"props":592,"children":593},"ul",{},[594,599,604,615,665,670,682,695],{"type":45,"tag":64,"props":595,"children":596},{},[597],{"type":50,"value":598},"Before suggesting code changes, inspect nearby blocks for imports, shared variables, SQL connections, inputs, and upstream assumptions.",{"type":45,"tag":64,"props":600,"children":601},{},[602],{"type":50,"value":603},"Prefer deterministic notebook code. Avoid hidden global state, implicit external files, or hard-coded credentials.",{"type":45,"tag":64,"props":605,"children":606},{},[607,609,614],{"type":50,"value":608},"Do not claim an edit was applied unless a write-capable tool is available and reports success. For project, notebook, block creation, and existing block updates, use ",{"type":45,"tag":70,"props":610,"children":612},{"className":611},[],[613],{"type":50,"value":176},{"type":50,"value":85},{"type":45,"tag":64,"props":616,"children":617},{},[618,620,626,628,633,635,640,642,647,649,655,657,663],{"type":50,"value":619},"If you run a notebook, pass requested input values through ",{"type":45,"tag":70,"props":621,"children":623},{"className":622},[],[624],{"type":50,"value":625},"create_run.inputs",{"type":50,"value":627}," using the input ",{"type":45,"tag":70,"props":629,"children":631},{"className":630},[],[632],{"type":50,"value":113},{"type":50,"value":634}," fields returned by ",{"type":45,"tag":70,"props":636,"children":638},{"className":637},[],[639],{"type":50,"value":83},{"type":50,"value":641},", then capture run status with ",{"type":45,"tag":70,"props":643,"children":645},{"className":644},[],[646],{"type":50,"value":197},{"type":50,"value":648},". Omit ",{"type":45,"tag":70,"props":650,"children":652},{"className":651},[],[653],{"type":50,"value":654},"snapshotDelivery",{"type":50,"value":656}," for status checks so the default download URL delivery is used; request ",{"type":45,"tag":70,"props":658,"children":660},{"className":659},[],[661],{"type":50,"value":662},"snapshotDelivery: \"inline\"",{"type":50,"value":664}," when you need to summarize snapshot content or errors.",{"type":45,"tag":64,"props":666,"children":667},{},[668],{"type":50,"value":669},"Run input values do not change the notebook's saved default input values.",{"type":45,"tag":64,"props":671,"children":672},{},[673,675,680],{"type":50,"value":674},"For SQL blocks, preserve the existing connection or data source in recommendations unless the user asks to move it. Use ",{"type":45,"tag":70,"props":676,"children":678},{"className":677},[],[679],{"type":50,"value":158},{"type":50,"value":681}," for cached table\u002Fcolumn context when needed.",{"type":45,"tag":64,"props":683,"children":684},{},[685,687,693],{"type":50,"value":686},"Before running a notebook, flag cells that print ",{"type":45,"tag":70,"props":688,"children":690},{"className":689},[],[691],{"type":50,"value":692},"os.environ",{"type":50,"value":694},", environment variables, credentials, tokens, or broad secret dumps. Do not run those notebooks unless the user explicitly confirms after the risk is named.",{"type":45,"tag":64,"props":696,"children":697},{},[698],{"type":50,"value":699},"Treat cells that start servers, send network requests, write files, cancel\u002Fmodify external records, or call production-like systems as stateful. Call out the side effect before execution.",{"type":45,"tag":53,"props":701,"children":703},{"id":702},"review-and-cleanup",[704],{"type":50,"value":705},"Review And Cleanup",{"type":45,"tag":206,"props":707,"children":708},{},[709],{"type":50,"value":710},"Use Deepnote app reads to verify notebook structure before making claims. If execution was not run, say so plainly and mention the remaining risk. For larger reviews, summarize relevant sections rather than listing every block.",{"items":712,"total":917},[713,734,757,774,790,809,828,844,860,874,886,901],{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":731,"repoUrl":732,"updatedAt":733},"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},[719,722,725,728],{"name":720,"slug":721,"type":15},"Documents","documents",{"name":723,"slug":724,"type":15},"Healthcare","healthcare",{"name":726,"slug":727,"type":15},"Insurance","insurance",{"name":729,"slug":730,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":735,"name":735,"fn":736,"description":737,"org":738,"tags":739,"stars":754,"repoUrl":755,"updatedAt":756},"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},[740,743,745,748,751],{"name":741,"slug":742,"type":15},".NET","dotnet",{"name":744,"slug":735,"type":15},"ASP.NET Core",{"name":746,"slug":747,"type":15},"Blazor","blazor",{"name":749,"slug":750,"type":15},"C#","csharp",{"name":752,"slug":753,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":758,"name":758,"fn":759,"description":760,"org":761,"tags":762,"stars":754,"repoUrl":755,"updatedAt":773},"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},[763,766,769,772],{"name":764,"slug":765,"type":15},"Apps SDK","apps-sdk",{"name":767,"slug":768,"type":15},"ChatGPT","chatgpt",{"name":770,"slug":771,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":775,"name":775,"fn":776,"description":777,"org":778,"tags":779,"stars":754,"repoUrl":755,"updatedAt":789},"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},[780,783,786],{"name":781,"slug":782,"type":15},"API Development","api-development",{"name":784,"slug":785,"type":15},"CLI","cli",{"name":787,"slug":788,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":754,"repoUrl":755,"updatedAt":808},"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},[796,799,802,805],{"name":797,"slug":798,"type":15},"Cloudflare","cloudflare",{"name":800,"slug":801,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":803,"slug":804,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":806,"slug":807,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":810,"name":810,"fn":811,"description":812,"org":813,"tags":814,"stars":754,"repoUrl":755,"updatedAt":827},"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},[815,818,821,824],{"name":816,"slug":817,"type":15},"Productivity","productivity",{"name":819,"slug":820,"type":15},"Project Management","project-management",{"name":822,"slug":823,"type":15},"Strategy","strategy",{"name":825,"slug":826,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":829,"name":829,"fn":830,"description":831,"org":832,"tags":833,"stars":754,"repoUrl":755,"updatedAt":843},"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},[834,837,839,842],{"name":835,"slug":836,"type":15},"Design","design",{"name":838,"slug":829,"type":15},"Figma",{"name":840,"slug":841,"type":15},"Frontend","frontend",{"name":770,"slug":771,"type":15},"2026-04-12T05:06:47.939943",{"slug":845,"name":845,"fn":846,"description":847,"org":848,"tags":849,"stars":754,"repoUrl":755,"updatedAt":859},"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},[850,851,854,855,856],{"name":835,"slug":836,"type":15},{"name":852,"slug":853,"type":15},"Design System","design-system",{"name":838,"slug":829,"type":15},{"name":840,"slug":841,"type":15},{"name":857,"slug":858,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":861,"name":861,"fn":862,"description":863,"org":864,"tags":865,"stars":754,"repoUrl":755,"updatedAt":873},"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},[866,867,868,871,872],{"name":835,"slug":836,"type":15},{"name":852,"slug":853,"type":15},{"name":869,"slug":870,"type":15},"Documentation","documentation",{"name":838,"slug":829,"type":15},{"name":840,"slug":841,"type":15},"2026-05-16T06:07:47.821474",{"slug":875,"name":875,"fn":876,"description":877,"org":878,"tags":879,"stars":754,"repoUrl":755,"updatedAt":885},"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},[880,881,882,883,884],{"name":835,"slug":836,"type":15},{"name":838,"slug":829,"type":15},{"name":840,"slug":841,"type":15},{"name":857,"slug":858,"type":15},{"name":752,"slug":753,"type":15},"2026-05-16T06:07:40.583615",{"slug":887,"name":887,"fn":888,"description":889,"org":890,"tags":891,"stars":754,"repoUrl":755,"updatedAt":900},"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},[892,895,896,899],{"name":893,"slug":894,"type":15},"Animation","animation",{"name":787,"slug":788,"type":15},{"name":897,"slug":898,"type":15},"Creative","creative",{"name":835,"slug":836,"type":15},"2026-05-02T05:31:48.48485",{"slug":902,"name":902,"fn":903,"description":904,"org":905,"tags":906,"stars":754,"repoUrl":755,"updatedAt":916},"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},[907,908,909,912,915],{"name":897,"slug":898,"type":15},{"name":835,"slug":836,"type":15},{"name":910,"slug":911,"type":15},"Image Generation","image-generation",{"name":913,"slug":914,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":919,"total":1032},[920,936,952,964,982,1000,1020],{"slug":921,"name":921,"fn":922,"description":923,"org":924,"tags":925,"stars":28,"repoUrl":29,"updatedAt":30},"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},[926,929,932,935],{"name":927,"slug":928,"type":15},"Accessibility","accessibility",{"name":930,"slug":931,"type":15},"Charts","charts",{"name":933,"slug":934,"type":15},"Data Visualization","data-visualization",{"name":835,"slug":836,"type":15},{"slug":937,"name":937,"fn":938,"description":939,"org":940,"tags":941,"stars":28,"repoUrl":29,"updatedAt":951},"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},[942,945,948],{"name":943,"slug":944,"type":15},"Agents","agents",{"name":946,"slug":947,"type":15},"Browser Automation","browser-automation",{"name":949,"slug":950,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":953,"name":953,"fn":954,"description":955,"org":956,"tags":957,"stars":28,"repoUrl":29,"updatedAt":963},"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},[958,959,962],{"name":946,"slug":947,"type":15},{"name":960,"slug":961,"type":15},"Local Development","local-development",{"name":949,"slug":950,"type":15},"2026-04-06T18:41:17.526867",{"slug":965,"name":965,"fn":966,"description":967,"org":968,"tags":969,"stars":28,"repoUrl":29,"updatedAt":981},"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},[970,971,972,975,978],{"name":943,"slug":944,"type":15},{"name":803,"slug":804,"type":15},{"name":973,"slug":974,"type":15},"SDK","sdk",{"name":976,"slug":977,"type":15},"Serverless","serverless",{"name":979,"slug":980,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":983,"name":983,"fn":984,"description":985,"org":986,"tags":987,"stars":28,"repoUrl":29,"updatedAt":999},"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},[988,989,992,995,996],{"name":840,"slug":841,"type":15},{"name":990,"slug":991,"type":15},"React","react",{"name":993,"slug":994,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":857,"slug":858,"type":15},{"name":997,"slug":998,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1001,"name":1001,"fn":1002,"description":1003,"org":1004,"tags":1005,"stars":28,"repoUrl":29,"updatedAt":1019},"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},[1006,1009,1012,1015,1018],{"name":1007,"slug":1008,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1010,"slug":1011,"type":15},"Cost Optimization","cost-optimization",{"name":1013,"slug":1014,"type":15},"LLM","llm",{"name":1016,"slug":1017,"type":15},"Performance","performance",{"name":997,"slug":998,"type":15},"2026-04-06T18:40:44.377464",{"slug":1021,"name":1021,"fn":1022,"description":1023,"org":1024,"tags":1025,"stars":28,"repoUrl":29,"updatedAt":1031},"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},[1026,1027,1030],{"name":1010,"slug":1011,"type":15},{"name":1028,"slug":1029,"type":15},"Database","database",{"name":1013,"slug":1014,"type":15},"2026-04-06T18:41:08.513425",600]