[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-jupyter-notebook":3,"mdc-8g3zem-key":36,"related-repo-openai-jupyter-notebook":826,"related-org-openai-jupyter-notebook":952},{"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},"jupyter-notebook","create and edit Jupyter notebooks","Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.",{"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},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Python","python",{"name":20,"slug":21,"type":15},"Notebooks","notebooks",{"name":23,"slug":24,"type":15},"Jupyter","jupyter",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:11.657079",null,1614,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"Skills Catalog for Codex","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002F.curated\u002Fjupyter-notebook","---\nname: \"jupyter-notebook\"\ndescription: \"Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.\"\n---\n\n\n# Jupyter Notebook Skill\n\nCreate clean, reproducible Jupyter notebooks for two primary modes:\n\n- Experiments and exploratory analysis\n- Tutorials and teaching-oriented walkthroughs\n\nPrefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.\n\n## When to use\n- Create a new `.ipynb` notebook from scratch.\n- Convert rough notes or scripts into a structured notebook.\n- Refactor an existing notebook to be more reproducible and skimmable.\n- Build experiments or tutorials that will be read or re-run by other people.\n\n## Decision tree\n- If the request is exploratory, analytical, or hypothesis-driven, choose `experiment`.\n- If the request is instructional, step-by-step, or audience-specific, choose `tutorial`.\n- If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.\n\n## Skill path (set once)\n\n```bash\nexport CODEX_HOME=\"${CODEX_HOME:-$HOME\u002F.codex}\"\nexport JUPYTER_NOTEBOOK_CLI=\"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py\"\n```\n\nUser-scoped skills install under `$CODEX_HOME\u002Fskills` (default: `~\u002F.codex\u002Fskills`).\n\n## Workflow\n1. Lock the intent.\nIdentify the notebook kind: `experiment` or `tutorial`.\nCapture the objective, audience, and what \"done\" looks like.\n\n2. Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind experiment \\\n  --title \"Compare prompt variants\" \\\n  --out output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n```\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n```\n\n3. Fill the notebook with small, runnable steps.\nKeep each code cell focused on one step.\nAdd short markdown cells that explain the purpose and expected result.\nAvoid large, noisy outputs when a short summary works.\n\n4. Apply the right pattern.\nFor experiments, follow `references\u002Fexperiment-patterns.md`.\nFor tutorials, follow `references\u002Ftutorial-patterns.md`.\n\n5. Edit safely when working with existing notebooks.\nPreserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story.\nPrefer targeted edits over full rewrites.\nIf you must edit raw JSON, review `references\u002Fnotebook-structure.md` first.\n\n6. Validate the result.\nRun the notebook top-to-bottom when the environment allows.\nIf execution is not possible, say so explicitly and call out how to validate locally.\nUse the final pass checklist in `references\u002Fquality-checklist.md`.\n\n## Templates and helper script\n- Templates live in `assets\u002Fexperiment-template.ipynb` and `assets\u002Ftutorial-template.ipynb`.\n- The helper script loads a template, updates the title cell, and writes a notebook.\n\nScript path:\n- `$JUPYTER_NOTEBOOK_CLI` (installed default: `$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py`)\n\n## Temp and output conventions\n- Use `tmp\u002Fjupyter-notebook\u002F` for intermediate files; delete when done.\n- Write final artifacts under `output\u002Fjupyter-notebook\u002F` when working in this repo.\n- Use stable, descriptive filenames (for example, `ablation-temperature.ipynb`).\n\n## Dependencies (install only when needed)\nPrefer `uv` for dependency management.\n\nOptional Python packages for local notebook execution:\n\n```bash\nuv pip install jupyterlab ipykernel\n```\n\nThe bundled scaffold script uses only the Python standard library and does not require extra dependencies.\n\n## Environment\nNo required environment variables.\n\n## Reference map\n- `references\u002Fexperiment-patterns.md`: experiment structure and heuristics.\n- `references\u002Ftutorial-patterns.md`: tutorial structure and teaching flow.\n- `references\u002Fnotebook-structure.md`: notebook JSON shape and safe editing rules.\n- `references\u002Fquality-checklist.md`: final validation checklist.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,71,76,83,115,121,154,160,272,293,299,327,440,538,591,597,625,630,651,657,698,704,716,721,755,760,766,771,777,820],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"jupyter-notebook-skill",[47],{"type":48,"value":49},"text","Jupyter Notebook Skill",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Create clean, reproducible Jupyter notebooks for two primary modes:",{"type":42,"tag":57,"props":58,"children":59},"ul",{},[60,66],{"type":42,"tag":61,"props":62,"children":63},"li",{},[64],{"type":48,"value":65},"Experiments and exploratory analysis",{"type":42,"tag":61,"props":67,"children":68},{},[69],{"type":48,"value":70},"Tutorials and teaching-oriented walkthroughs",{"type":42,"tag":51,"props":72,"children":73},{},[74],{"type":48,"value":75},"Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.",{"type":42,"tag":77,"props":78,"children":80},"h2",{"id":79},"when-to-use",[81],{"type":48,"value":82},"When to use",{"type":42,"tag":57,"props":84,"children":85},{},[86,100,105,110],{"type":42,"tag":61,"props":87,"children":88},{},[89,91,98],{"type":48,"value":90},"Create a new ",{"type":42,"tag":92,"props":93,"children":95},"code",{"className":94},[],[96],{"type":48,"value":97},".ipynb",{"type":48,"value":99}," notebook from scratch.",{"type":42,"tag":61,"props":101,"children":102},{},[103],{"type":48,"value":104},"Convert rough notes or scripts into a structured notebook.",{"type":42,"tag":61,"props":106,"children":107},{},[108],{"type":48,"value":109},"Refactor an existing notebook to be more reproducible and skimmable.",{"type":42,"tag":61,"props":111,"children":112},{},[113],{"type":48,"value":114},"Build experiments or tutorials that will be read or re-run by other people.",{"type":42,"tag":77,"props":116,"children":118},{"id":117},"decision-tree",[119],{"type":48,"value":120},"Decision tree",{"type":42,"tag":57,"props":122,"children":123},{},[124,137,149],{"type":42,"tag":61,"props":125,"children":126},{},[127,129,135],{"type":48,"value":128},"If the request is exploratory, analytical, or hypothesis-driven, choose ",{"type":42,"tag":92,"props":130,"children":132},{"className":131},[],[133],{"type":48,"value":134},"experiment",{"type":48,"value":136},".",{"type":42,"tag":61,"props":138,"children":139},{},[140,142,148],{"type":48,"value":141},"If the request is instructional, step-by-step, or audience-specific, choose ",{"type":42,"tag":92,"props":143,"children":145},{"className":144},[],[146],{"type":48,"value":147},"tutorial",{"type":48,"value":136},{"type":42,"tag":61,"props":150,"children":151},{},[152],{"type":48,"value":153},"If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.",{"type":42,"tag":77,"props":155,"children":157},{"id":156},"skill-path-set-once",[158],{"type":48,"value":159},"Skill path (set once)",{"type":42,"tag":161,"props":162,"children":167},"pre",{"className":163,"code":164,"language":165,"meta":166,"style":166},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","export CODEX_HOME=\"${CODEX_HOME:-$HOME\u002F.codex}\"\nexport JUPYTER_NOTEBOOK_CLI=\"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py\"\n","bash","",[168],{"type":42,"tag":92,"props":169,"children":170},{"__ignoreMap":166},[171,235],{"type":42,"tag":172,"props":173,"children":176},"span",{"class":174,"line":175},"line",1,[177,183,189,195,200,205,210,215,220,225,230],{"type":42,"tag":172,"props":178,"children":180},{"style":179},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[181],{"type":48,"value":182},"export",{"type":42,"tag":172,"props":184,"children":186},{"style":185},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[187],{"type":48,"value":188}," CODEX_HOME",{"type":42,"tag":172,"props":190,"children":192},{"style":191},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[193],{"type":48,"value":194},"=",{"type":42,"tag":172,"props":196,"children":197},{"style":191},[198],{"type":48,"value":199},"\"${",{"type":42,"tag":172,"props":201,"children":202},{"style":185},[203],{"type":48,"value":204},"CODEX_HOME",{"type":42,"tag":172,"props":206,"children":207},{"style":191},[208],{"type":48,"value":209},":-",{"type":42,"tag":172,"props":211,"children":212},{"style":185},[213],{"type":48,"value":214},"$HOME",{"type":42,"tag":172,"props":216,"children":217},{"style":191},[218],{"type":48,"value":219},"\u002F",{"type":42,"tag":172,"props":221,"children":223},{"style":222},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[224],{"type":48,"value":136},{"type":42,"tag":172,"props":226,"children":227},{"style":185},[228],{"type":48,"value":229},"codex",{"type":42,"tag":172,"props":231,"children":232},{"style":191},[233],{"type":48,"value":234},"}\"\n",{"type":42,"tag":172,"props":236,"children":238},{"class":174,"line":237},2,[239,243,248,252,257,262,267],{"type":42,"tag":172,"props":240,"children":241},{"style":179},[242],{"type":48,"value":182},{"type":42,"tag":172,"props":244,"children":245},{"style":185},[246],{"type":48,"value":247}," JUPYTER_NOTEBOOK_CLI",{"type":42,"tag":172,"props":249,"children":250},{"style":191},[251],{"type":48,"value":194},{"type":42,"tag":172,"props":253,"children":254},{"style":191},[255],{"type":48,"value":256},"\"",{"type":42,"tag":172,"props":258,"children":259},{"style":185},[260],{"type":48,"value":261},"$CODEX_HOME",{"type":42,"tag":172,"props":263,"children":264},{"style":222},[265],{"type":48,"value":266},"\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py",{"type":42,"tag":172,"props":268,"children":269},{"style":191},[270],{"type":48,"value":271},"\"\n",{"type":42,"tag":51,"props":273,"children":274},{},[275,277,283,285,291],{"type":48,"value":276},"User-scoped skills install under ",{"type":42,"tag":92,"props":278,"children":280},{"className":279},[],[281],{"type":48,"value":282},"$CODEX_HOME\u002Fskills",{"type":48,"value":284}," (default: ",{"type":42,"tag":92,"props":286,"children":288},{"className":287},[],[289],{"type":48,"value":290},"~\u002F.codex\u002Fskills",{"type":48,"value":292},").",{"type":42,"tag":77,"props":294,"children":296},{"id":295},"workflow",[297],{"type":48,"value":298},"Workflow",{"type":42,"tag":300,"props":301,"children":302},"ol",{},[303,322],{"type":42,"tag":61,"props":304,"children":305},{},[306,308,313,315,320],{"type":48,"value":307},"Lock the intent.\nIdentify the notebook kind: ",{"type":42,"tag":92,"props":309,"children":311},{"className":310},[],[312],{"type":48,"value":134},{"type":48,"value":314}," or ",{"type":42,"tag":92,"props":316,"children":318},{"className":317},[],[319],{"type":48,"value":147},{"type":48,"value":321},".\nCapture the objective, audience, and what \"done\" looks like.",{"type":42,"tag":61,"props":323,"children":324},{},[325],{"type":48,"value":326},"Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.",{"type":42,"tag":161,"props":328,"children":330},{"className":163,"code":329,"language":165,"meta":166,"style":166},"uv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind experiment \\\n  --title \"Compare prompt variants\" \\\n  --out output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n",[331],{"type":42,"tag":92,"props":332,"children":333},{"__ignoreMap":166},[334,383,400,426],{"type":42,"tag":172,"props":335,"children":336},{"class":174,"line":175},[337,343,348,353,359,364,369,374,378],{"type":42,"tag":172,"props":338,"children":340},{"style":339},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[341],{"type":48,"value":342},"uv",{"type":42,"tag":172,"props":344,"children":345},{"style":222},[346],{"type":48,"value":347}," run",{"type":42,"tag":172,"props":349,"children":350},{"style":222},[351],{"type":48,"value":352}," --python",{"type":42,"tag":172,"props":354,"children":356},{"style":355},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[357],{"type":48,"value":358}," 3.12",{"type":42,"tag":172,"props":360,"children":361},{"style":222},[362],{"type":48,"value":363}," python",{"type":42,"tag":172,"props":365,"children":366},{"style":191},[367],{"type":48,"value":368}," \"",{"type":42,"tag":172,"props":370,"children":371},{"style":185},[372],{"type":48,"value":373},"$JUPYTER_NOTEBOOK_CLI",{"type":42,"tag":172,"props":375,"children":376},{"style":191},[377],{"type":48,"value":256},{"type":42,"tag":172,"props":379,"children":380},{"style":185},[381],{"type":48,"value":382}," \\\n",{"type":42,"tag":172,"props":384,"children":385},{"class":174,"line":237},[386,391,396],{"type":42,"tag":172,"props":387,"children":388},{"style":222},[389],{"type":48,"value":390},"  --kind",{"type":42,"tag":172,"props":392,"children":393},{"style":222},[394],{"type":48,"value":395}," experiment",{"type":42,"tag":172,"props":397,"children":398},{"style":185},[399],{"type":48,"value":382},{"type":42,"tag":172,"props":401,"children":403},{"class":174,"line":402},3,[404,409,413,418,422],{"type":42,"tag":172,"props":405,"children":406},{"style":222},[407],{"type":48,"value":408},"  --title",{"type":42,"tag":172,"props":410,"children":411},{"style":191},[412],{"type":48,"value":368},{"type":42,"tag":172,"props":414,"children":415},{"style":222},[416],{"type":48,"value":417},"Compare prompt variants",{"type":42,"tag":172,"props":419,"children":420},{"style":191},[421],{"type":48,"value":256},{"type":42,"tag":172,"props":423,"children":424},{"style":185},[425],{"type":48,"value":382},{"type":42,"tag":172,"props":427,"children":429},{"class":174,"line":428},4,[430,435],{"type":42,"tag":172,"props":431,"children":432},{"style":222},[433],{"type":48,"value":434},"  --out",{"type":42,"tag":172,"props":436,"children":437},{"style":222},[438],{"type":48,"value":439}," output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n",{"type":42,"tag":161,"props":441,"children":443},{"className":163,"code":442,"language":165,"meta":166,"style":166},"uv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",[444],{"type":42,"tag":92,"props":445,"children":446},{"__ignoreMap":166},[447,486,502,526],{"type":42,"tag":172,"props":448,"children":449},{"class":174,"line":175},[450,454,458,462,466,470,474,478,482],{"type":42,"tag":172,"props":451,"children":452},{"style":339},[453],{"type":48,"value":342},{"type":42,"tag":172,"props":455,"children":456},{"style":222},[457],{"type":48,"value":347},{"type":42,"tag":172,"props":459,"children":460},{"style":222},[461],{"type":48,"value":352},{"type":42,"tag":172,"props":463,"children":464},{"style":355},[465],{"type":48,"value":358},{"type":42,"tag":172,"props":467,"children":468},{"style":222},[469],{"type":48,"value":363},{"type":42,"tag":172,"props":471,"children":472},{"style":191},[473],{"type":48,"value":368},{"type":42,"tag":172,"props":475,"children":476},{"style":185},[477],{"type":48,"value":373},{"type":42,"tag":172,"props":479,"children":480},{"style":191},[481],{"type":48,"value":256},{"type":42,"tag":172,"props":483,"children":484},{"style":185},[485],{"type":48,"value":382},{"type":42,"tag":172,"props":487,"children":488},{"class":174,"line":237},[489,493,498],{"type":42,"tag":172,"props":490,"children":491},{"style":222},[492],{"type":48,"value":390},{"type":42,"tag":172,"props":494,"children":495},{"style":222},[496],{"type":48,"value":497}," tutorial",{"type":42,"tag":172,"props":499,"children":500},{"style":185},[501],{"type":48,"value":382},{"type":42,"tag":172,"props":503,"children":504},{"class":174,"line":402},[505,509,513,518,522],{"type":42,"tag":172,"props":506,"children":507},{"style":222},[508],{"type":48,"value":408},{"type":42,"tag":172,"props":510,"children":511},{"style":191},[512],{"type":48,"value":368},{"type":42,"tag":172,"props":514,"children":515},{"style":222},[516],{"type":48,"value":517},"Intro to embeddings",{"type":42,"tag":172,"props":519,"children":520},{"style":191},[521],{"type":48,"value":256},{"type":42,"tag":172,"props":523,"children":524},{"style":185},[525],{"type":48,"value":382},{"type":42,"tag":172,"props":527,"children":528},{"class":174,"line":428},[529,533],{"type":42,"tag":172,"props":530,"children":531},{"style":222},[532],{"type":48,"value":434},{"type":42,"tag":172,"props":534,"children":535},{"style":222},[536],{"type":48,"value":537}," output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",{"type":42,"tag":300,"props":539,"children":540},{"start":402},[541,546,566,579],{"type":42,"tag":61,"props":542,"children":543},{},[544],{"type":48,"value":545},"Fill the notebook with small, runnable steps.\nKeep each code cell focused on one step.\nAdd short markdown cells that explain the purpose and expected result.\nAvoid large, noisy outputs when a short summary works.",{"type":42,"tag":61,"props":547,"children":548},{},[549,551,557,559,565],{"type":48,"value":550},"Apply the right pattern.\nFor experiments, follow ",{"type":42,"tag":92,"props":552,"children":554},{"className":553},[],[555],{"type":48,"value":556},"references\u002Fexperiment-patterns.md",{"type":48,"value":558},".\nFor tutorials, follow ",{"type":42,"tag":92,"props":560,"children":562},{"className":561},[],[563],{"type":48,"value":564},"references\u002Ftutorial-patterns.md",{"type":48,"value":136},{"type":42,"tag":61,"props":567,"children":568},{},[569,571,577],{"type":48,"value":570},"Edit safely when working with existing notebooks.\nPreserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story.\nPrefer targeted edits over full rewrites.\nIf you must edit raw JSON, review ",{"type":42,"tag":92,"props":572,"children":574},{"className":573},[],[575],{"type":48,"value":576},"references\u002Fnotebook-structure.md",{"type":48,"value":578}," first.",{"type":42,"tag":61,"props":580,"children":581},{},[582,584,590],{"type":48,"value":583},"Validate the result.\nRun the notebook top-to-bottom when the environment allows.\nIf execution is not possible, say so explicitly and call out how to validate locally.\nUse the final pass checklist in ",{"type":42,"tag":92,"props":585,"children":587},{"className":586},[],[588],{"type":48,"value":589},"references\u002Fquality-checklist.md",{"type":48,"value":136},{"type":42,"tag":77,"props":592,"children":594},{"id":593},"templates-and-helper-script",[595],{"type":48,"value":596},"Templates and helper script",{"type":42,"tag":57,"props":598,"children":599},{},[600,620],{"type":42,"tag":61,"props":601,"children":602},{},[603,605,611,613,619],{"type":48,"value":604},"Templates live in ",{"type":42,"tag":92,"props":606,"children":608},{"className":607},[],[609],{"type":48,"value":610},"assets\u002Fexperiment-template.ipynb",{"type":48,"value":612}," and ",{"type":42,"tag":92,"props":614,"children":616},{"className":615},[],[617],{"type":48,"value":618},"assets\u002Ftutorial-template.ipynb",{"type":48,"value":136},{"type":42,"tag":61,"props":621,"children":622},{},[623],{"type":48,"value":624},"The helper script loads a template, updates the title cell, and writes a notebook.",{"type":42,"tag":51,"props":626,"children":627},{},[628],{"type":48,"value":629},"Script path:",{"type":42,"tag":57,"props":631,"children":632},{},[633],{"type":42,"tag":61,"props":634,"children":635},{},[636,641,643,649],{"type":42,"tag":92,"props":637,"children":639},{"className":638},[],[640],{"type":48,"value":373},{"type":48,"value":642}," (installed default: ",{"type":42,"tag":92,"props":644,"children":646},{"className":645},[],[647],{"type":48,"value":648},"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py",{"type":48,"value":650},")",{"type":42,"tag":77,"props":652,"children":654},{"id":653},"temp-and-output-conventions",[655],{"type":48,"value":656},"Temp and output conventions",{"type":42,"tag":57,"props":658,"children":659},{},[660,673,686],{"type":42,"tag":61,"props":661,"children":662},{},[663,665,671],{"type":48,"value":664},"Use ",{"type":42,"tag":92,"props":666,"children":668},{"className":667},[],[669],{"type":48,"value":670},"tmp\u002Fjupyter-notebook\u002F",{"type":48,"value":672}," for intermediate files; delete when done.",{"type":42,"tag":61,"props":674,"children":675},{},[676,678,684],{"type":48,"value":677},"Write final artifacts under ",{"type":42,"tag":92,"props":679,"children":681},{"className":680},[],[682],{"type":48,"value":683},"output\u002Fjupyter-notebook\u002F",{"type":48,"value":685}," when working in this repo.",{"type":42,"tag":61,"props":687,"children":688},{},[689,691,697],{"type":48,"value":690},"Use stable, descriptive filenames (for example, ",{"type":42,"tag":92,"props":692,"children":694},{"className":693},[],[695],{"type":48,"value":696},"ablation-temperature.ipynb",{"type":48,"value":292},{"type":42,"tag":77,"props":699,"children":701},{"id":700},"dependencies-install-only-when-needed",[702],{"type":48,"value":703},"Dependencies (install only when needed)",{"type":42,"tag":51,"props":705,"children":706},{},[707,709,714],{"type":48,"value":708},"Prefer ",{"type":42,"tag":92,"props":710,"children":712},{"className":711},[],[713],{"type":48,"value":342},{"type":48,"value":715}," for dependency management.",{"type":42,"tag":51,"props":717,"children":718},{},[719],{"type":48,"value":720},"Optional Python packages for local notebook execution:",{"type":42,"tag":161,"props":722,"children":724},{"className":163,"code":723,"language":165,"meta":166,"style":166},"uv pip install jupyterlab ipykernel\n",[725],{"type":42,"tag":92,"props":726,"children":727},{"__ignoreMap":166},[728],{"type":42,"tag":172,"props":729,"children":730},{"class":174,"line":175},[731,735,740,745,750],{"type":42,"tag":172,"props":732,"children":733},{"style":339},[734],{"type":48,"value":342},{"type":42,"tag":172,"props":736,"children":737},{"style":222},[738],{"type":48,"value":739}," pip",{"type":42,"tag":172,"props":741,"children":742},{"style":222},[743],{"type":48,"value":744}," install",{"type":42,"tag":172,"props":746,"children":747},{"style":222},[748],{"type":48,"value":749}," jupyterlab",{"type":42,"tag":172,"props":751,"children":752},{"style":222},[753],{"type":48,"value":754}," ipykernel\n",{"type":42,"tag":51,"props":756,"children":757},{},[758],{"type":48,"value":759},"The bundled scaffold script uses only the Python standard library and does not require extra dependencies.",{"type":42,"tag":77,"props":761,"children":763},{"id":762},"environment",[764],{"type":48,"value":765},"Environment",{"type":42,"tag":51,"props":767,"children":768},{},[769],{"type":48,"value":770},"No required environment variables.",{"type":42,"tag":77,"props":772,"children":774},{"id":773},"reference-map",[775],{"type":48,"value":776},"Reference map",{"type":42,"tag":57,"props":778,"children":779},{},[780,790,800,810],{"type":42,"tag":61,"props":781,"children":782},{},[783,788],{"type":42,"tag":92,"props":784,"children":786},{"className":785},[],[787],{"type":48,"value":556},{"type":48,"value":789},": experiment structure and heuristics.",{"type":42,"tag":61,"props":791,"children":792},{},[793,798],{"type":42,"tag":92,"props":794,"children":796},{"className":795},[],[797],{"type":48,"value":564},{"type":48,"value":799},": tutorial structure and teaching flow.",{"type":42,"tag":61,"props":801,"children":802},{},[803,808],{"type":42,"tag":92,"props":804,"children":806},{"className":805},[],[807],{"type":48,"value":576},{"type":48,"value":809},": notebook JSON shape and safe editing rules.",{"type":42,"tag":61,"props":811,"children":812},{},[813,818],{"type":42,"tag":92,"props":814,"children":816},{"className":815},[],[817],{"type":48,"value":589},{"type":48,"value":819},": final validation checklist.",{"type":42,"tag":821,"props":822,"children":823},"style",{},[824],{"type":48,"value":825},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":827,"total":951},[828,849,866,881,900,919,935],{"slug":829,"name":829,"fn":830,"description":831,"org":832,"tags":833,"stars":25,"repoUrl":26,"updatedAt":848},"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},[834,837,839,842,845],{"name":835,"slug":836,"type":15},".NET","dotnet",{"name":838,"slug":829,"type":15},"ASP.NET Core",{"name":840,"slug":841,"type":15},"Blazor","blazor",{"name":843,"slug":844,"type":15},"C#","csharp",{"name":846,"slug":847,"type":15},"Web Development","web-development","2026-04-12T05:07:02.819491",{"slug":850,"name":850,"fn":851,"description":852,"org":853,"tags":854,"stars":25,"repoUrl":26,"updatedAt":865},"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},[855,858,861,864],{"name":856,"slug":857,"type":15},"Apps SDK","apps-sdk",{"name":859,"slug":860,"type":15},"ChatGPT","chatgpt",{"name":862,"slug":863,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":867,"name":867,"fn":868,"description":869,"org":870,"tags":871,"stars":25,"repoUrl":26,"updatedAt":880},"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},[872,875,878],{"name":873,"slug":874,"type":15},"API Development","api-development",{"name":876,"slug":877,"type":15},"CLI","cli",{"name":879,"slug":229,"type":15},"Codex","2026-04-12T05:07:04.132762",{"slug":882,"name":882,"fn":883,"description":884,"org":885,"tags":886,"stars":25,"repoUrl":26,"updatedAt":899},"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},[887,890,893,896],{"name":888,"slug":889,"type":15},"Cloudflare","cloudflare",{"name":891,"slug":892,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":894,"slug":895,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":897,"slug":898,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":901,"name":901,"fn":902,"description":903,"org":904,"tags":905,"stars":25,"repoUrl":26,"updatedAt":918},"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},[906,909,912,915],{"name":907,"slug":908,"type":15},"Productivity","productivity",{"name":910,"slug":911,"type":15},"Project Management","project-management",{"name":913,"slug":914,"type":15},"Strategy","strategy",{"name":916,"slug":917,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":920,"name":920,"fn":921,"description":922,"org":923,"tags":924,"stars":25,"repoUrl":26,"updatedAt":934},"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},[925,928,930,933],{"name":926,"slug":927,"type":15},"Design","design",{"name":929,"slug":920,"type":15},"Figma",{"name":931,"slug":932,"type":15},"Frontend","frontend",{"name":862,"slug":863,"type":15},"2026-04-12T05:06:47.939943",{"slug":936,"name":936,"fn":937,"description":938,"org":939,"tags":940,"stars":25,"repoUrl":26,"updatedAt":950},"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},[941,942,945,946,947],{"name":926,"slug":927,"type":15},{"name":943,"slug":944,"type":15},"Design System","design-system",{"name":929,"slug":920,"type":15},{"name":931,"slug":932,"type":15},{"name":948,"slug":949,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",29,{"items":953,"total":1082},[954,975,983,990,996,1003,1010,1017,1025,1039,1051,1066],{"slug":955,"name":955,"fn":956,"description":957,"org":958,"tags":959,"stars":972,"repoUrl":973,"updatedAt":974},"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},[960,963,966,969],{"name":961,"slug":962,"type":15},"Documents","documents",{"name":964,"slug":965,"type":15},"Healthcare","healthcare",{"name":967,"slug":968,"type":15},"Insurance","insurance",{"name":970,"slug":971,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":829,"name":829,"fn":830,"description":831,"org":976,"tags":977,"stars":25,"repoUrl":26,"updatedAt":848},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[978,979,980,981,982],{"name":835,"slug":836,"type":15},{"name":838,"slug":829,"type":15},{"name":840,"slug":841,"type":15},{"name":843,"slug":844,"type":15},{"name":846,"slug":847,"type":15},{"slug":850,"name":850,"fn":851,"description":852,"org":984,"tags":985,"stars":25,"repoUrl":26,"updatedAt":865},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[986,987,988,989],{"name":856,"slug":857,"type":15},{"name":859,"slug":860,"type":15},{"name":862,"slug":863,"type":15},{"name":9,"slug":8,"type":15},{"slug":867,"name":867,"fn":868,"description":869,"org":991,"tags":992,"stars":25,"repoUrl":26,"updatedAt":880},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[993,994,995],{"name":873,"slug":874,"type":15},{"name":876,"slug":877,"type":15},{"name":879,"slug":229,"type":15},{"slug":882,"name":882,"fn":883,"description":884,"org":997,"tags":998,"stars":25,"repoUrl":26,"updatedAt":899},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[999,1000,1001,1002],{"name":888,"slug":889,"type":15},{"name":891,"slug":892,"type":15},{"name":894,"slug":895,"type":15},{"name":897,"slug":898,"type":15},{"slug":901,"name":901,"fn":902,"description":903,"org":1004,"tags":1005,"stars":25,"repoUrl":26,"updatedAt":918},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1006,1007,1008,1009],{"name":907,"slug":908,"type":15},{"name":910,"slug":911,"type":15},{"name":913,"slug":914,"type":15},{"name":916,"slug":917,"type":15},{"slug":920,"name":920,"fn":921,"description":922,"org":1011,"tags":1012,"stars":25,"repoUrl":26,"updatedAt":934},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1013,1014,1015,1016],{"name":926,"slug":927,"type":15},{"name":929,"slug":920,"type":15},{"name":931,"slug":932,"type":15},{"name":862,"slug":863,"type":15},{"slug":936,"name":936,"fn":937,"description":938,"org":1018,"tags":1019,"stars":25,"repoUrl":26,"updatedAt":950},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1020,1021,1022,1023,1024],{"name":926,"slug":927,"type":15},{"name":943,"slug":944,"type":15},{"name":929,"slug":920,"type":15},{"name":931,"slug":932,"type":15},{"name":948,"slug":949,"type":15},{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1029,"tags":1030,"stars":25,"repoUrl":26,"updatedAt":1038},"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},[1031,1032,1033,1036,1037],{"name":926,"slug":927,"type":15},{"name":943,"slug":944,"type":15},{"name":1034,"slug":1035,"type":15},"Documentation","documentation",{"name":929,"slug":920,"type":15},{"name":931,"slug":932,"type":15},"2026-05-16T06:07:47.821474",{"slug":1040,"name":1040,"fn":1041,"description":1042,"org":1043,"tags":1044,"stars":25,"repoUrl":26,"updatedAt":1050},"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},[1045,1046,1047,1048,1049],{"name":926,"slug":927,"type":15},{"name":929,"slug":920,"type":15},{"name":931,"slug":932,"type":15},{"name":948,"slug":949,"type":15},{"name":846,"slug":847,"type":15},"2026-05-16T06:07:40.583615",{"slug":1052,"name":1052,"fn":1053,"description":1054,"org":1055,"tags":1056,"stars":25,"repoUrl":26,"updatedAt":1065},"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},[1057,1060,1061,1064],{"name":1058,"slug":1059,"type":15},"Animation","animation",{"name":879,"slug":229,"type":15},{"name":1062,"slug":1063,"type":15},"Creative","creative",{"name":926,"slug":927,"type":15},"2026-05-02T05:31:48.48485",{"slug":1067,"name":1067,"fn":1068,"description":1069,"org":1070,"tags":1071,"stars":25,"repoUrl":26,"updatedAt":1081},"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},[1072,1073,1074,1077,1080],{"name":1062,"slug":1063,"type":15},{"name":926,"slug":927,"type":15},{"name":1075,"slug":1076,"type":15},"Image Generation","image-generation",{"name":1078,"slug":1079,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]