[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-jetbrains-jupyter-notebook":3,"mdc-8usnlk-key":33,"related-repo-jetbrains-jupyter-notebook":827,"related-org-jetbrains-jupyter-notebook":953},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"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":9},"jetbrains","JetBrains","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fjetbrains.png",[12,16,19],{"name":13,"slug":14,"type":15},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Notebooks","notebooks",{"name":20,"slug":21,"type":15},"Jupyter","jupyter",252,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills","2026-07-13T06:42:43.406733",null,17,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Curated agent skills collection verified by JetBrains","https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills\u002Ftree\u002FHEAD\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.\"\nmetadata:\n  short-description: \"Create Jupyter notebooks for experiments and tutorials\"\n  author: OpenAI\n  source: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002F.curated\u002Fjupyter-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":34,"body":39},{"name":4,"description":6,"metadata":35},{"short-description":36,"author":37,"source":38},"Create Jupyter notebooks for experiments and tutorials","OpenAI","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002F.curated\u002Fjupyter-notebook",{"type":40,"children":41},"root",[42,51,57,72,77,84,116,122,155,161,273,294,300,328,441,539,592,598,626,631,652,658,699,705,717,722,756,761,767,772,778,821],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"jupyter-notebook-skill",[48],{"type":49,"value":50},"text","Jupyter Notebook Skill",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"Create clean, reproducible Jupyter notebooks for two primary modes:",{"type":43,"tag":58,"props":59,"children":60},"ul",{},[61,67],{"type":43,"tag":62,"props":63,"children":64},"li",{},[65],{"type":49,"value":66},"Experiments and exploratory analysis",{"type":43,"tag":62,"props":68,"children":69},{},[70],{"type":49,"value":71},"Tutorials and teaching-oriented walkthroughs",{"type":43,"tag":52,"props":73,"children":74},{},[75],{"type":49,"value":76},"Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.",{"type":43,"tag":78,"props":79,"children":81},"h2",{"id":80},"when-to-use",[82],{"type":49,"value":83},"When to use",{"type":43,"tag":58,"props":85,"children":86},{},[87,101,106,111],{"type":43,"tag":62,"props":88,"children":89},{},[90,92,99],{"type":49,"value":91},"Create a new ",{"type":43,"tag":93,"props":94,"children":96},"code",{"className":95},[],[97],{"type":49,"value":98},".ipynb",{"type":49,"value":100}," notebook from scratch.",{"type":43,"tag":62,"props":102,"children":103},{},[104],{"type":49,"value":105},"Convert rough notes or scripts into a structured notebook.",{"type":43,"tag":62,"props":107,"children":108},{},[109],{"type":49,"value":110},"Refactor an existing notebook to be more reproducible and skimmable.",{"type":43,"tag":62,"props":112,"children":113},{},[114],{"type":49,"value":115},"Build experiments or tutorials that will be read or re-run by other people.",{"type":43,"tag":78,"props":117,"children":119},{"id":118},"decision-tree",[120],{"type":49,"value":121},"Decision tree",{"type":43,"tag":58,"props":123,"children":124},{},[125,138,150],{"type":43,"tag":62,"props":126,"children":127},{},[128,130,136],{"type":49,"value":129},"If the request is exploratory, analytical, or hypothesis-driven, choose ",{"type":43,"tag":93,"props":131,"children":133},{"className":132},[],[134],{"type":49,"value":135},"experiment",{"type":49,"value":137},".",{"type":43,"tag":62,"props":139,"children":140},{},[141,143,149],{"type":49,"value":142},"If the request is instructional, step-by-step, or audience-specific, choose ",{"type":43,"tag":93,"props":144,"children":146},{"className":145},[],[147],{"type":49,"value":148},"tutorial",{"type":49,"value":137},{"type":43,"tag":62,"props":151,"children":152},{},[153],{"type":49,"value":154},"If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.",{"type":43,"tag":78,"props":156,"children":158},{"id":157},"skill-path-set-once",[159],{"type":49,"value":160},"Skill path (set once)",{"type":43,"tag":162,"props":163,"children":168},"pre",{"className":164,"code":165,"language":166,"meta":167,"style":167},"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=\"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py\"\n","bash","",[169],{"type":43,"tag":93,"props":170,"children":171},{"__ignoreMap":167},[172,236],{"type":43,"tag":173,"props":174,"children":177},"span",{"class":175,"line":176},"line",1,[178,184,190,196,201,206,211,216,221,226,231],{"type":43,"tag":173,"props":179,"children":181},{"style":180},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[182],{"type":49,"value":183},"export",{"type":43,"tag":173,"props":185,"children":187},{"style":186},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[188],{"type":49,"value":189}," CODEX_HOME",{"type":43,"tag":173,"props":191,"children":193},{"style":192},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[194],{"type":49,"value":195},"=",{"type":43,"tag":173,"props":197,"children":198},{"style":192},[199],{"type":49,"value":200},"\"${",{"type":43,"tag":173,"props":202,"children":203},{"style":186},[204],{"type":49,"value":205},"CODEX_HOME",{"type":43,"tag":173,"props":207,"children":208},{"style":192},[209],{"type":49,"value":210},":-",{"type":43,"tag":173,"props":212,"children":213},{"style":186},[214],{"type":49,"value":215},"$HOME",{"type":43,"tag":173,"props":217,"children":218},{"style":192},[219],{"type":49,"value":220},"\u002F",{"type":43,"tag":173,"props":222,"children":224},{"style":223},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[225],{"type":49,"value":137},{"type":43,"tag":173,"props":227,"children":228},{"style":186},[229],{"type":49,"value":230},"codex",{"type":43,"tag":173,"props":232,"children":233},{"style":192},[234],{"type":49,"value":235},"}\"\n",{"type":43,"tag":173,"props":237,"children":239},{"class":175,"line":238},2,[240,244,249,253,258,263,268],{"type":43,"tag":173,"props":241,"children":242},{"style":180},[243],{"type":49,"value":183},{"type":43,"tag":173,"props":245,"children":246},{"style":186},[247],{"type":49,"value":248}," JUPYTER_NOTEBOOK_CLI",{"type":43,"tag":173,"props":250,"children":251},{"style":192},[252],{"type":49,"value":195},{"type":43,"tag":173,"props":254,"children":255},{"style":192},[256],{"type":49,"value":257},"\"",{"type":43,"tag":173,"props":259,"children":260},{"style":186},[261],{"type":49,"value":262},"$CODEX_HOME",{"type":43,"tag":173,"props":264,"children":265},{"style":223},[266],{"type":49,"value":267},"\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py",{"type":43,"tag":173,"props":269,"children":270},{"style":192},[271],{"type":49,"value":272},"\"\n",{"type":43,"tag":52,"props":274,"children":275},{},[276,278,284,286,292],{"type":49,"value":277},"User-scoped skills install under ",{"type":43,"tag":93,"props":279,"children":281},{"className":280},[],[282],{"type":49,"value":283},"$CODEX_HOME\u002Fskills",{"type":49,"value":285}," (default: ",{"type":43,"tag":93,"props":287,"children":289},{"className":288},[],[290],{"type":49,"value":291},"~\u002F.codex\u002Fskills",{"type":49,"value":293},").",{"type":43,"tag":78,"props":295,"children":297},{"id":296},"workflow",[298],{"type":49,"value":299},"Workflow",{"type":43,"tag":301,"props":302,"children":303},"ol",{},[304,323],{"type":43,"tag":62,"props":305,"children":306},{},[307,309,314,316,321],{"type":49,"value":308},"Lock the intent.\nIdentify the notebook kind: ",{"type":43,"tag":93,"props":310,"children":312},{"className":311},[],[313],{"type":49,"value":135},{"type":49,"value":315}," or ",{"type":43,"tag":93,"props":317,"children":319},{"className":318},[],[320],{"type":49,"value":148},{"type":49,"value":322},".\nCapture the objective, audience, and what \"done\" looks like.",{"type":43,"tag":62,"props":324,"children":325},{},[326],{"type":49,"value":327},"Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.",{"type":43,"tag":162,"props":329,"children":331},{"className":164,"code":330,"language":166,"meta":167,"style":167},"uv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind experiment \\\n  --title \"Compare prompt variants\" \\\n  --out output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n",[332],{"type":43,"tag":93,"props":333,"children":334},{"__ignoreMap":167},[335,384,401,427],{"type":43,"tag":173,"props":336,"children":337},{"class":175,"line":176},[338,344,349,354,360,365,370,375,379],{"type":43,"tag":173,"props":339,"children":341},{"style":340},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[342],{"type":49,"value":343},"uv",{"type":43,"tag":173,"props":345,"children":346},{"style":223},[347],{"type":49,"value":348}," run",{"type":43,"tag":173,"props":350,"children":351},{"style":223},[352],{"type":49,"value":353}," --python",{"type":43,"tag":173,"props":355,"children":357},{"style":356},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[358],{"type":49,"value":359}," 3.12",{"type":43,"tag":173,"props":361,"children":362},{"style":223},[363],{"type":49,"value":364}," python",{"type":43,"tag":173,"props":366,"children":367},{"style":192},[368],{"type":49,"value":369}," \"",{"type":43,"tag":173,"props":371,"children":372},{"style":186},[373],{"type":49,"value":374},"$JUPYTER_NOTEBOOK_CLI",{"type":43,"tag":173,"props":376,"children":377},{"style":192},[378],{"type":49,"value":257},{"type":43,"tag":173,"props":380,"children":381},{"style":186},[382],{"type":49,"value":383}," \\\n",{"type":43,"tag":173,"props":385,"children":386},{"class":175,"line":238},[387,392,397],{"type":43,"tag":173,"props":388,"children":389},{"style":223},[390],{"type":49,"value":391},"  --kind",{"type":43,"tag":173,"props":393,"children":394},{"style":223},[395],{"type":49,"value":396}," experiment",{"type":43,"tag":173,"props":398,"children":399},{"style":186},[400],{"type":49,"value":383},{"type":43,"tag":173,"props":402,"children":404},{"class":175,"line":403},3,[405,410,414,419,423],{"type":43,"tag":173,"props":406,"children":407},{"style":223},[408],{"type":49,"value":409},"  --title",{"type":43,"tag":173,"props":411,"children":412},{"style":192},[413],{"type":49,"value":369},{"type":43,"tag":173,"props":415,"children":416},{"style":223},[417],{"type":49,"value":418},"Compare prompt variants",{"type":43,"tag":173,"props":420,"children":421},{"style":192},[422],{"type":49,"value":257},{"type":43,"tag":173,"props":424,"children":425},{"style":186},[426],{"type":49,"value":383},{"type":43,"tag":173,"props":428,"children":430},{"class":175,"line":429},4,[431,436],{"type":43,"tag":173,"props":432,"children":433},{"style":223},[434],{"type":49,"value":435},"  --out",{"type":43,"tag":173,"props":437,"children":438},{"style":223},[439],{"type":49,"value":440}," output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n",{"type":43,"tag":162,"props":442,"children":444},{"className":164,"code":443,"language":166,"meta":167,"style":167},"uv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",[445],{"type":43,"tag":93,"props":446,"children":447},{"__ignoreMap":167},[448,487,503,527],{"type":43,"tag":173,"props":449,"children":450},{"class":175,"line":176},[451,455,459,463,467,471,475,479,483],{"type":43,"tag":173,"props":452,"children":453},{"style":340},[454],{"type":49,"value":343},{"type":43,"tag":173,"props":456,"children":457},{"style":223},[458],{"type":49,"value":348},{"type":43,"tag":173,"props":460,"children":461},{"style":223},[462],{"type":49,"value":353},{"type":43,"tag":173,"props":464,"children":465},{"style":356},[466],{"type":49,"value":359},{"type":43,"tag":173,"props":468,"children":469},{"style":223},[470],{"type":49,"value":364},{"type":43,"tag":173,"props":472,"children":473},{"style":192},[474],{"type":49,"value":369},{"type":43,"tag":173,"props":476,"children":477},{"style":186},[478],{"type":49,"value":374},{"type":43,"tag":173,"props":480,"children":481},{"style":192},[482],{"type":49,"value":257},{"type":43,"tag":173,"props":484,"children":485},{"style":186},[486],{"type":49,"value":383},{"type":43,"tag":173,"props":488,"children":489},{"class":175,"line":238},[490,494,499],{"type":43,"tag":173,"props":491,"children":492},{"style":223},[493],{"type":49,"value":391},{"type":43,"tag":173,"props":495,"children":496},{"style":223},[497],{"type":49,"value":498}," tutorial",{"type":43,"tag":173,"props":500,"children":501},{"style":186},[502],{"type":49,"value":383},{"type":43,"tag":173,"props":504,"children":505},{"class":175,"line":403},[506,510,514,519,523],{"type":43,"tag":173,"props":507,"children":508},{"style":223},[509],{"type":49,"value":409},{"type":43,"tag":173,"props":511,"children":512},{"style":192},[513],{"type":49,"value":369},{"type":43,"tag":173,"props":515,"children":516},{"style":223},[517],{"type":49,"value":518},"Intro to embeddings",{"type":43,"tag":173,"props":520,"children":521},{"style":192},[522],{"type":49,"value":257},{"type":43,"tag":173,"props":524,"children":525},{"style":186},[526],{"type":49,"value":383},{"type":43,"tag":173,"props":528,"children":529},{"class":175,"line":429},[530,534],{"type":43,"tag":173,"props":531,"children":532},{"style":223},[533],{"type":49,"value":435},{"type":43,"tag":173,"props":535,"children":536},{"style":223},[537],{"type":49,"value":538}," output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",{"type":43,"tag":301,"props":540,"children":541},{"start":403},[542,547,567,580],{"type":43,"tag":62,"props":543,"children":544},{},[545],{"type":49,"value":546},"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":43,"tag":62,"props":548,"children":549},{},[550,552,558,560,566],{"type":49,"value":551},"Apply the right pattern.\nFor experiments, follow ",{"type":43,"tag":93,"props":553,"children":555},{"className":554},[],[556],{"type":49,"value":557},"references\u002Fexperiment-patterns.md",{"type":49,"value":559},".\nFor tutorials, follow ",{"type":43,"tag":93,"props":561,"children":563},{"className":562},[],[564],{"type":49,"value":565},"references\u002Ftutorial-patterns.md",{"type":49,"value":137},{"type":43,"tag":62,"props":568,"children":569},{},[570,572,578],{"type":49,"value":571},"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":43,"tag":93,"props":573,"children":575},{"className":574},[],[576],{"type":49,"value":577},"references\u002Fnotebook-structure.md",{"type":49,"value":579}," first.",{"type":43,"tag":62,"props":581,"children":582},{},[583,585,591],{"type":49,"value":584},"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":43,"tag":93,"props":586,"children":588},{"className":587},[],[589],{"type":49,"value":590},"references\u002Fquality-checklist.md",{"type":49,"value":137},{"type":43,"tag":78,"props":593,"children":595},{"id":594},"templates-and-helper-script",[596],{"type":49,"value":597},"Templates and helper script",{"type":43,"tag":58,"props":599,"children":600},{},[601,621],{"type":43,"tag":62,"props":602,"children":603},{},[604,606,612,614,620],{"type":49,"value":605},"Templates live in ",{"type":43,"tag":93,"props":607,"children":609},{"className":608},[],[610],{"type":49,"value":611},"assets\u002Fexperiment-template.ipynb",{"type":49,"value":613}," and ",{"type":43,"tag":93,"props":615,"children":617},{"className":616},[],[618],{"type":49,"value":619},"assets\u002Ftutorial-template.ipynb",{"type":49,"value":137},{"type":43,"tag":62,"props":622,"children":623},{},[624],{"type":49,"value":625},"The helper script loads a template, updates the title cell, and writes a notebook.",{"type":43,"tag":52,"props":627,"children":628},{},[629],{"type":49,"value":630},"Script path:",{"type":43,"tag":58,"props":632,"children":633},{},[634],{"type":43,"tag":62,"props":635,"children":636},{},[637,642,644,650],{"type":43,"tag":93,"props":638,"children":640},{"className":639},[],[641],{"type":49,"value":374},{"type":49,"value":643}," (installed default: ",{"type":43,"tag":93,"props":645,"children":647},{"className":646},[],[648],{"type":49,"value":649},"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py",{"type":49,"value":651},")",{"type":43,"tag":78,"props":653,"children":655},{"id":654},"temp-and-output-conventions",[656],{"type":49,"value":657},"Temp and output conventions",{"type":43,"tag":58,"props":659,"children":660},{},[661,674,687],{"type":43,"tag":62,"props":662,"children":663},{},[664,666,672],{"type":49,"value":665},"Use ",{"type":43,"tag":93,"props":667,"children":669},{"className":668},[],[670],{"type":49,"value":671},"tmp\u002Fjupyter-notebook\u002F",{"type":49,"value":673}," for intermediate files; delete when done.",{"type":43,"tag":62,"props":675,"children":676},{},[677,679,685],{"type":49,"value":678},"Write final artifacts under ",{"type":43,"tag":93,"props":680,"children":682},{"className":681},[],[683],{"type":49,"value":684},"output\u002Fjupyter-notebook\u002F",{"type":49,"value":686}," when working in this repo.",{"type":43,"tag":62,"props":688,"children":689},{},[690,692,698],{"type":49,"value":691},"Use stable, descriptive filenames (for example, ",{"type":43,"tag":93,"props":693,"children":695},{"className":694},[],[696],{"type":49,"value":697},"ablation-temperature.ipynb",{"type":49,"value":293},{"type":43,"tag":78,"props":700,"children":702},{"id":701},"dependencies-install-only-when-needed",[703],{"type":49,"value":704},"Dependencies (install only when needed)",{"type":43,"tag":52,"props":706,"children":707},{},[708,710,715],{"type":49,"value":709},"Prefer ",{"type":43,"tag":93,"props":711,"children":713},{"className":712},[],[714],{"type":49,"value":343},{"type":49,"value":716}," for dependency management.",{"type":43,"tag":52,"props":718,"children":719},{},[720],{"type":49,"value":721},"Optional Python packages for local notebook execution:",{"type":43,"tag":162,"props":723,"children":725},{"className":164,"code":724,"language":166,"meta":167,"style":167},"uv pip install jupyterlab ipykernel\n",[726],{"type":43,"tag":93,"props":727,"children":728},{"__ignoreMap":167},[729],{"type":43,"tag":173,"props":730,"children":731},{"class":175,"line":176},[732,736,741,746,751],{"type":43,"tag":173,"props":733,"children":734},{"style":340},[735],{"type":49,"value":343},{"type":43,"tag":173,"props":737,"children":738},{"style":223},[739],{"type":49,"value":740}," pip",{"type":43,"tag":173,"props":742,"children":743},{"style":223},[744],{"type":49,"value":745}," install",{"type":43,"tag":173,"props":747,"children":748},{"style":223},[749],{"type":49,"value":750}," jupyterlab",{"type":43,"tag":173,"props":752,"children":753},{"style":223},[754],{"type":49,"value":755}," ipykernel\n",{"type":43,"tag":52,"props":757,"children":758},{},[759],{"type":49,"value":760},"The bundled scaffold script uses only the Python standard library and does not require extra dependencies.",{"type":43,"tag":78,"props":762,"children":764},{"id":763},"environment",[765],{"type":49,"value":766},"Environment",{"type":43,"tag":52,"props":768,"children":769},{},[770],{"type":49,"value":771},"No required environment variables.",{"type":43,"tag":78,"props":773,"children":775},{"id":774},"reference-map",[776],{"type":49,"value":777},"Reference map",{"type":43,"tag":58,"props":779,"children":780},{},[781,791,801,811],{"type":43,"tag":62,"props":782,"children":783},{},[784,789],{"type":43,"tag":93,"props":785,"children":787},{"className":786},[],[788],{"type":49,"value":557},{"type":49,"value":790},": experiment structure and heuristics.",{"type":43,"tag":62,"props":792,"children":793},{},[794,799],{"type":43,"tag":93,"props":795,"children":797},{"className":796},[],[798],{"type":49,"value":565},{"type":49,"value":800},": tutorial structure and teaching flow.",{"type":43,"tag":62,"props":802,"children":803},{},[804,809],{"type":43,"tag":93,"props":805,"children":807},{"className":806},[],[808],{"type":49,"value":577},{"type":49,"value":810},": notebook JSON shape and safe editing rules.",{"type":43,"tag":62,"props":812,"children":813},{},[814,819],{"type":43,"tag":93,"props":815,"children":817},{"className":816},[],[818],{"type":49,"value":590},{"type":49,"value":820},": final validation checklist.",{"type":43,"tag":822,"props":823,"children":824},"style",{},[825],{"type":49,"value":826},"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":828,"total":952},[829,848,865,881,896,919,936],{"slug":830,"name":830,"fn":831,"description":832,"org":833,"tags":834,"stars":22,"repoUrl":23,"updatedAt":847},"algorithmic-art","create generative art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[835,838,841,844],{"name":836,"slug":837,"type":15},"Creative","creative",{"name":839,"slug":840,"type":15},"Generative Art","generative-art",{"name":842,"slug":843,"type":15},"Graphics","graphics",{"name":845,"slug":846,"type":15},"JavaScript","javascript","2026-07-13T06:41:35.540127",{"slug":849,"name":849,"fn":850,"description":851,"org":852,"tags":853,"stars":22,"repoUrl":23,"updatedAt":864},"antfu","configure JavaScript projects with Anthony Fu's tools","Anthony Fu's opinionated tooling and conventions for JavaScript\u002FTypeScript projects. Use when setting up new projects, configuring ESLint\u002FPrettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[854,857,860,861],{"name":855,"slug":856,"type":15},"Best Practices","best-practices",{"name":858,"slug":859,"type":15},"Engineering","engineering",{"name":845,"slug":846,"type":15},{"name":862,"slug":863,"type":15},"TypeScript","typescript","2026-07-13T06:43:13.153309",{"slug":866,"name":866,"fn":867,"description":868,"org":869,"tags":870,"stars":22,"repoUrl":23,"updatedAt":880},"brand-guidelines","apply Anthropic brand guidelines","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[871,874,877],{"name":872,"slug":873,"type":15},"Branding","branding",{"name":875,"slug":876,"type":15},"Design","design",{"name":878,"slug":879,"type":15},"Typography","typography","2026-07-13T06:43:06.077629",{"slug":882,"name":882,"fn":883,"description":884,"org":885,"tags":886,"stars":22,"repoUrl":23,"updatedAt":895},"canvas-design","create visual art and design assets","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[887,888,889,892],{"name":836,"slug":837,"type":15},{"name":875,"slug":876,"type":15},{"name":890,"slug":891,"type":15},"Images","images",{"name":893,"slug":894,"type":15},"PDF","pdf","2026-07-13T06:39:58.803113",{"slug":897,"name":897,"fn":898,"description":899,"org":900,"tags":901,"stars":22,"repoUrl":23,"updatedAt":918},"ci-cd-containerization-advisor","design CI\u002FCD pipelines for Kotlin applications","Design reproducible build, image, and deployment pipelines for Kotlin plus Spring applications, including CI verification, layered containers, rollout safety, and deployment-time migration coordination. Use when creating or improving Dockerfiles, CI workflows, image hardening, Kubernetes manifests, release gates, or deployment strategies for Spring Boot services, especially where build reproducibility and operational safety matter.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[902,905,908,911,912,915],{"name":903,"slug":904,"type":15},"CI\u002FCD","ci-cd",{"name":906,"slug":907,"type":15},"Containers","containers",{"name":909,"slug":910,"type":15},"Deployment","deployment",{"name":858,"slug":859,"type":15},{"name":913,"slug":914,"type":15},"Kotlin","kotlin",{"name":916,"slug":917,"type":15},"Spring","spring","2026-07-13T06:41:47.83899",{"slug":920,"name":920,"fn":921,"description":922,"org":923,"tags":924,"stars":22,"repoUrl":23,"updatedAt":935},"cloudflare-deploy","deploy applications 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":9},[925,928,931,934],{"name":926,"slug":927,"type":15},"Cloudflare","cloudflare",{"name":929,"slug":930,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":932,"slug":933,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":909,"slug":910,"type":15},"2026-07-17T06:04:42.853896",{"slug":937,"name":937,"fn":938,"description":939,"org":940,"tags":941,"stars":22,"repoUrl":23,"updatedAt":951},"compose-ui-control","interact with Compose Desktop applications","Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[942,945,948],{"name":943,"slug":944,"type":15},"Automation","automation",{"name":946,"slug":947,"type":15},"Desktop","desktop",{"name":949,"slug":950,"type":15},"UI Components","ui-components","2026-07-13T06:40:38.798626",128,{"items":954,"total":1077},[955,971,980,989,1000,1008,1017,1026,1035,1045,1054,1067],{"slug":956,"name":956,"fn":957,"description":958,"org":959,"tags":960,"stars":968,"repoUrl":969,"updatedAt":970},"mps-aspect-accessories","configure JetBrains MPS module dependencies","Wire MPS module and model dependencies, used languages, used devkits, extended languages, runtime solutions, accessory models, and language\u002Fdependency versions. Use when adding\u002Fremoving module dependencies, importing languages or devkits into a model, declaring runtime solutions, or shipping accessory content visible to consumers without explicit import.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[961,964,967],{"name":962,"slug":963,"type":15},"Architecture","architecture",{"name":965,"slug":966,"type":15},"Configuration","configuration",{"name":858,"slug":859,"type":15},1650,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002FMPS","2026-07-17T06:06:57.311661",{"slug":972,"name":972,"fn":973,"description":974,"org":975,"tags":976,"stars":968,"repoUrl":969,"updatedAt":979},"mps-aspect-actions","define and edit MPS node factories","Use when defining or editing MPS node factories (the \"actions\" aspect) — `NodeFactories` roots, per-concept `NodeFactory` setup functions that initialize a freshly created node and optionally copy data from a replaced `sampleNode`, plus the actions aspect's `CopyPasteHandlers` and `PasteWrappers` roots. Reach for this skill when a substitution, side transform, completion replacement, or `add new initialized(...)` should preserve fields from the node it is replacing, or when defaults set in a constructor are not enough.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[977,978],{"name":962,"slug":963,"type":15},{"name":858,"slug":859,"type":15},"2026-07-17T06:04:48.066901",{"slug":981,"name":981,"fn":982,"description":983,"org":984,"tags":985,"stars":968,"repoUrl":969,"updatedAt":988},"mps-aspect-behavior","define and edit MPS concept behavior","Use when defining or editing MPS `ConceptBehavior` — per-concept methods (non-virtual \u002F virtual \u002F abstract \u002F static \u002F virtual static), constructors, virtual dispatch (MRO), super and interface-default calls (`super\u003CInterface>.method`), overriding methods from `lang.core.behavior` interfaces such as `ScopeProvider.getScope` \u002F `INamedConcept.getName` \u002F `BaseConcept.getPresentation`, calling sibling methods (`LocalBehaviorMethodCall`) and behavior methods from other aspects via `node.method(...)`. Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fbehavior.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[986,987],{"name":962,"slug":963,"type":15},{"name":858,"slug":859,"type":15},"2026-07-13T06:45:21.757084",{"slug":990,"name":990,"fn":991,"description":992,"org":993,"tags":994,"stars":968,"repoUrl":969,"updatedAt":999},"mps-aspect-constraints","define JetBrains MPS language constraints","Use when defining or editing MPS language constraints — property validators \u002F setters \u002F getters, referent search scopes (imperative or inherited via `ScopeProvider.getScope`), `referentSetHandler` side effects, default-scope blocks, `canBeChild` \u002F `canBeParent` \u002F `canBeAncestor` \u002F `canBeRoot` placement rules, `defaultConcreteConcept` for abstract concepts, `set \u003Cread-only>` and `{name}` aliasing, and scope helpers (`SimpleRoleScope`, `ListScope`, `CompositeScope`, `HidingByNameScope`). Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fconstraints.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[995,996],{"name":962,"slug":963,"type":15},{"name":997,"slug":998,"type":15},"Code Analysis","code-analysis","2026-07-23T05:41:33.639365",{"slug":1001,"name":1001,"fn":1002,"description":1003,"org":1004,"tags":1005,"stars":968,"repoUrl":969,"updatedAt":1007},"mps-aspect-dataflow","define and debug MPS dataflow builders","Use when defining or debugging MPS dataflow builders for a concept — control\u002Fdata flow declarations that drive reachability analysis and variable-use checking. Covers DataFlowBuilderDeclaration, BuilderBlock, emit instructions (code for, jump, ifjump, label, read, write, ret, mayBeUnreachable), positions (AfterPosition, BeforePosition, LabelPosition), the jetbrains.mps.lang.dataFlow language, the NodeParameter implicit, BL+smodel usage inside builder bodies, and IBuilderMode for advanced analyses such as nullable\u002Fnon-null tracking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1006],{"name":13,"slug":14,"type":15},"2026-07-13T06:45:19.114674",{"slug":1009,"name":1009,"fn":1010,"description":1011,"org":1012,"tags":1013,"stars":968,"repoUrl":969,"updatedAt":1016},"mps-aspect-editor","define MPS editor layouts","Use when creating or changing MPS editor definitions — the overall workflow from scaffolding a `ConceptEditorDeclaration` through componentizing reusable `EditorComponentDeclaration`s, refining cell models and cell layouts, applying style sheets and indent-layout style items, wiring smart references, leveraging inheritance via super-concepts and interfaces, inspecting (`print_node_json`, `show_node_representation`) and validating (`check_root_node_problems`). Covers `jetbrains.mps.lang.editor` cell models (`CellModel_RefNode`\u002F`CellModel_RefNodeList`\u002F`CellModel_RefCell`\u002F`CellModel_Property`\u002F`CellModel_Constant`), layout choices, and JSON blueprints for common editor shapes. For the non-layout side (action maps, keymaps, transformation\u002Fsubstitute menus) use `mps-aspect-editor-menus-and-keymaps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1014,1015],{"name":875,"slug":876,"type":15},{"name":949,"slug":950,"type":15},"2026-07-23T05:41:56.638151",{"slug":1018,"name":1018,"fn":1019,"description":1020,"org":1021,"tags":1022,"stars":968,"repoUrl":969,"updatedAt":1025},"mps-aspect-editor-menus-and-keymaps","author MPS editor menus and keymaps","Use when authoring the **non-layout** parts of the MPS editor aspect — what happens when the user types, presses a key, triggers completion, pastes, or invokes a context action. Covers action maps (`CellActionMapDeclaration`), cell keymaps (`CellKeyMapDeclaration`), transformation menus (`TransformationMenu_Default` \u002F `_Named` \u002F `_Contribution`), substitute menus (`SubstituteMenu_Default` \u002F `SubstituteMenu` \u002F contributions), side transforms (LEFT\u002FRIGHT), legacy cell menus, paste wrappers and copy-paste handlers (in the actions language), completion styling, reference presentation, two-step deletion, and the editor selection API. Trigger terms: `actionMap`, `keyMap`, `delete_action_id`, `transformationMenu`, `substituteMenu`, `Ctrl+Space`, `Ctrl+Alt+B`, side transform, paste wrapper, completion styling, `PasteWrappers`, `CopyPasteHandlers`. For the **layout** side (cells, layouts, style sheets) use `mps-aspect-editor` instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1023,1024],{"name":858,"slug":859,"type":15},{"name":949,"slug":950,"type":15},"2026-07-23T05:41:49.666535",{"slug":1027,"name":1027,"fn":1028,"description":1029,"org":1030,"tags":1031,"stars":968,"repoUrl":969,"updatedAt":1034},"mps-aspect-generation-plan","modify MPS generation plans","Use when defining or modifying an MPS generation plan — explicit ordering of generators, checkpoints for cross-model reference resolution, forks for parallel branches, IncludePlan composition, conditional PlanContribution activation, ParameterEquals\u002FConceptListSelector fork selectors, and InitModelAttributes for targetFacet routing. Apply when working with @genplan models, the jetbrains.mps.lang.generator.plan language, attaching plans via DevKits or the Custom generation facet, or debugging cross-model mapping label resolution.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1032,1033],{"name":962,"slug":963,"type":15},{"name":858,"slug":859,"type":15},"2026-07-13T06:44:59.507855",{"slug":1036,"name":1036,"fn":1037,"description":1038,"org":1039,"tags":1040,"stars":968,"repoUrl":969,"updatedAt":1044},"mps-aspect-generator","define JetBrains MPS generator rules","Use when defining or modifying MPS generators — author a generator module, add or edit root\u002Freduction\u002Fweaving\u002Fpattern mapping rules, attach template macros ($COPY_SRC, $LOOP, $IF, $PROPERTY, $REF, $SWITCH, $MAP_SRC, $WEAVE, $INSERT, $LABEL, $TRACE, $VAR), wire mapping labels, build template switches, write pre\u002Fpost mapping scripts, navigate `genContext`, or debug \"rule didn't fire\", missing references, empty output, infinite reduction loops, and generated-Java compile failures.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1041,1042,1043],{"name":962,"slug":963,"type":15},{"name":997,"slug":998,"type":15},{"name":858,"slug":859,"type":15},"2026-07-17T06:06:58.042999",{"slug":1046,"name":1046,"fn":1047,"description":1048,"org":1049,"tags":1050,"stars":968,"repoUrl":969,"updatedAt":1053},"mps-aspect-intentions","define and edit MPS intentions","Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding `IntentionDeclaration` roots, parameterized or surround-with variants, description\u002FisApplicable\u002Fexecute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the language's `intentions` model and uses `jetbrains.mps.lang.intentions`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1051,1052],{"name":962,"slug":963,"type":15},{"name":858,"slug":859,"type":15},"2026-07-23T05:41:48.692899",{"slug":1055,"name":1055,"fn":1056,"description":1057,"org":1058,"tags":1059,"stars":968,"repoUrl":969,"updatedAt":1066},"mps-aspect-migrations","author and debug MPS migration scripts","Use when authoring or debugging MPS migration scripts that upgrade user models after a language definition changes — covers jetbrains.mps.lang.migration (MigrationScript class-based, PureMigrationScript declarative, MoveConcept\u002FMoveContainmentLink\u002FMoveReferenceLink\u002FMoveProperty, ordering via OrderDependency, data exchange via putData\u002FgetData, RefactoringLog, ConceptMigrationReference) and jetbrains.mps.lang.script Enhancement Scripts (MigrationScript with MigrationScriptPart_Instance, ExtractInterfaceMigration, FactoryMigrationScriptPart, CommentMigrationScriptPart) — when a model needs version-gated upgrade, concept rename or removal, link or property rename, instance-level transformation, or composition of migration steps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1060,1063],{"name":1061,"slug":1062,"type":15},"Debugging","debugging",{"name":1064,"slug":1065,"type":15},"Migration","migration","2026-07-13T06:45:20.372122",{"slug":1068,"name":1068,"fn":1069,"description":1070,"org":1071,"tags":1072,"stars":968,"repoUrl":969,"updatedAt":1076},"mps-aspect-structure-concepts","define concepts in MPS structure aspect","Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's `structure` aspect. Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation, and the full `mps_mcp_alter_structure` \u002F `mps_mcp_query_structure` reference. Use when authoring or modifying a language's structure model.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1073],{"name":1074,"slug":1075,"type":15},"Data Modeling","data-modeling","2026-07-23T05:41:30.705975",188]