[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-letta-jupyter-notebook":3,"mdc--vb8bjt-key":34,"related-repo-letta-jupyter-notebook":772,"related-org-letta-jupyter-notebook":892},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"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":11},"letta","Letta","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fletta.png","letta-ai",[13,17,20],{"name":14,"slug":15,"type":16},"Data Analysis","data-analysis","tag",{"name":18,"slug":19,"type":16},"Notebooks","notebooks",{"name":21,"slug":22,"type":16},"Jupyter","jupyter",127,"https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fskills","2026-07-13T06:25:16.23541",null,20,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"A shared repository for skills. Intended to be used with Letta Code, Claude Code, Codex CLI, and other agents that support skills.","https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fskills\u002Ftree\u002FHEAD\u002Ftools\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\n# Set to the directory containing this SKILL.md\nexport JUPYTER_NOTEBOOK_CLI=\"\u003Cpath-to-skill>\u002Fscripts\u002Fnew_notebook.py\"\n```\n\nReplace `\u003Cpath-to-skill>` with the actual skill installation directory (e.g. `.skills\u002Fjupyter-notebook` or `~\u002F.letta\u002Fskills\u002Fjupyter-notebook`).\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` (see \"Skill path\" section above)\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":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,48,54,69,74,81,113,119,152,158,219,248,254,281,394,492,545,551,579,584,597,603,644,650,662,667,701,706,712,717,723,766],{"type":40,"tag":41,"props":42,"children":44},"element","h1",{"id":43},"jupyter-notebook-skill",[45],{"type":46,"value":47},"text","Jupyter Notebook Skill",{"type":40,"tag":49,"props":50,"children":51},"p",{},[52],{"type":46,"value":53},"Create clean, reproducible Jupyter notebooks for two primary modes:",{"type":40,"tag":55,"props":56,"children":57},"ul",{},[58,64],{"type":40,"tag":59,"props":60,"children":61},"li",{},[62],{"type":46,"value":63},"Experiments and exploratory analysis",{"type":40,"tag":59,"props":65,"children":66},{},[67],{"type":46,"value":68},"Tutorials and teaching-oriented walkthroughs",{"type":40,"tag":49,"props":70,"children":71},{},[72],{"type":46,"value":73},"Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.",{"type":40,"tag":75,"props":76,"children":78},"h2",{"id":77},"when-to-use",[79],{"type":46,"value":80},"When to use",{"type":40,"tag":55,"props":82,"children":83},{},[84,98,103,108],{"type":40,"tag":59,"props":85,"children":86},{},[87,89,96],{"type":46,"value":88},"Create a new ",{"type":40,"tag":90,"props":91,"children":93},"code",{"className":92},[],[94],{"type":46,"value":95},".ipynb",{"type":46,"value":97}," notebook from scratch.",{"type":40,"tag":59,"props":99,"children":100},{},[101],{"type":46,"value":102},"Convert rough notes or scripts into a structured notebook.",{"type":40,"tag":59,"props":104,"children":105},{},[106],{"type":46,"value":107},"Refactor an existing notebook to be more reproducible and skimmable.",{"type":40,"tag":59,"props":109,"children":110},{},[111],{"type":46,"value":112},"Build experiments or tutorials that will be read or re-run by other people.",{"type":40,"tag":75,"props":114,"children":116},{"id":115},"decision-tree",[117],{"type":46,"value":118},"Decision tree",{"type":40,"tag":55,"props":120,"children":121},{},[122,135,147],{"type":40,"tag":59,"props":123,"children":124},{},[125,127,133],{"type":46,"value":126},"If the request is exploratory, analytical, or hypothesis-driven, choose ",{"type":40,"tag":90,"props":128,"children":130},{"className":129},[],[131],{"type":46,"value":132},"experiment",{"type":46,"value":134},".",{"type":40,"tag":59,"props":136,"children":137},{},[138,140,146],{"type":46,"value":139},"If the request is instructional, step-by-step, or audience-specific, choose ",{"type":40,"tag":90,"props":141,"children":143},{"className":142},[],[144],{"type":46,"value":145},"tutorial",{"type":46,"value":134},{"type":40,"tag":59,"props":148,"children":149},{},[150],{"type":46,"value":151},"If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.",{"type":40,"tag":75,"props":153,"children":155},{"id":154},"skill-path-set-once",[156],{"type":46,"value":157},"Skill path (set once)",{"type":40,"tag":159,"props":160,"children":165},"pre",{"className":161,"code":162,"language":163,"meta":164,"style":164},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Set to the directory containing this SKILL.md\nexport JUPYTER_NOTEBOOK_CLI=\"\u003Cpath-to-skill>\u002Fscripts\u002Fnew_notebook.py\"\n","bash","",[166],{"type":40,"tag":90,"props":167,"children":168},{"__ignoreMap":164},[169,181],{"type":40,"tag":170,"props":171,"children":174},"span",{"class":172,"line":173},"line",1,[175],{"type":40,"tag":170,"props":176,"children":178},{"style":177},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[179],{"type":46,"value":180},"# Set to the directory containing this SKILL.md\n",{"type":40,"tag":170,"props":182,"children":184},{"class":172,"line":183},2,[185,191,197,203,208,214],{"type":40,"tag":170,"props":186,"children":188},{"style":187},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[189],{"type":46,"value":190},"export",{"type":40,"tag":170,"props":192,"children":194},{"style":193},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[195],{"type":46,"value":196}," JUPYTER_NOTEBOOK_CLI",{"type":40,"tag":170,"props":198,"children":200},{"style":199},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[201],{"type":46,"value":202},"=",{"type":40,"tag":170,"props":204,"children":205},{"style":199},[206],{"type":46,"value":207},"\"",{"type":40,"tag":170,"props":209,"children":211},{"style":210},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[212],{"type":46,"value":213},"\u003Cpath-to-skill>\u002Fscripts\u002Fnew_notebook.py",{"type":40,"tag":170,"props":215,"children":216},{"style":199},[217],{"type":46,"value":218},"\"\n",{"type":40,"tag":49,"props":220,"children":221},{},[222,224,230,232,238,240,246],{"type":46,"value":223},"Replace ",{"type":40,"tag":90,"props":225,"children":227},{"className":226},[],[228],{"type":46,"value":229},"\u003Cpath-to-skill>",{"type":46,"value":231}," with the actual skill installation directory (e.g. ",{"type":40,"tag":90,"props":233,"children":235},{"className":234},[],[236],{"type":46,"value":237},".skills\u002Fjupyter-notebook",{"type":46,"value":239}," or ",{"type":40,"tag":90,"props":241,"children":243},{"className":242},[],[244],{"type":46,"value":245},"~\u002F.letta\u002Fskills\u002Fjupyter-notebook",{"type":46,"value":247},").",{"type":40,"tag":75,"props":249,"children":251},{"id":250},"workflow",[252],{"type":46,"value":253},"Workflow",{"type":40,"tag":255,"props":256,"children":257},"ol",{},[258,276],{"type":40,"tag":59,"props":259,"children":260},{},[261,263,268,269,274],{"type":46,"value":262},"Lock the intent.\nIdentify the notebook kind: ",{"type":40,"tag":90,"props":264,"children":266},{"className":265},[],[267],{"type":46,"value":132},{"type":46,"value":239},{"type":40,"tag":90,"props":270,"children":272},{"className":271},[],[273],{"type":46,"value":145},{"type":46,"value":275},".\nCapture the objective, audience, and what \"done\" looks like.",{"type":40,"tag":59,"props":277,"children":278},{},[279],{"type":46,"value":280},"Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.",{"type":40,"tag":159,"props":282,"children":284},{"className":161,"code":283,"language":163,"meta":164,"style":164},"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",[285],{"type":40,"tag":90,"props":286,"children":287},{"__ignoreMap":164},[288,337,354,380],{"type":40,"tag":170,"props":289,"children":290},{"class":172,"line":173},[291,297,302,307,313,318,323,328,332],{"type":40,"tag":170,"props":292,"children":294},{"style":293},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[295],{"type":46,"value":296},"uv",{"type":40,"tag":170,"props":298,"children":299},{"style":210},[300],{"type":46,"value":301}," run",{"type":40,"tag":170,"props":303,"children":304},{"style":210},[305],{"type":46,"value":306}," --python",{"type":40,"tag":170,"props":308,"children":310},{"style":309},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[311],{"type":46,"value":312}," 3.12",{"type":40,"tag":170,"props":314,"children":315},{"style":210},[316],{"type":46,"value":317}," python",{"type":40,"tag":170,"props":319,"children":320},{"style":199},[321],{"type":46,"value":322}," \"",{"type":40,"tag":170,"props":324,"children":325},{"style":193},[326],{"type":46,"value":327},"$JUPYTER_NOTEBOOK_CLI",{"type":40,"tag":170,"props":329,"children":330},{"style":199},[331],{"type":46,"value":207},{"type":40,"tag":170,"props":333,"children":334},{"style":193},[335],{"type":46,"value":336}," \\\n",{"type":40,"tag":170,"props":338,"children":339},{"class":172,"line":183},[340,345,350],{"type":40,"tag":170,"props":341,"children":342},{"style":210},[343],{"type":46,"value":344},"  --kind",{"type":40,"tag":170,"props":346,"children":347},{"style":210},[348],{"type":46,"value":349}," experiment",{"type":40,"tag":170,"props":351,"children":352},{"style":193},[353],{"type":46,"value":336},{"type":40,"tag":170,"props":355,"children":357},{"class":172,"line":356},3,[358,363,367,372,376],{"type":40,"tag":170,"props":359,"children":360},{"style":210},[361],{"type":46,"value":362},"  --title",{"type":40,"tag":170,"props":364,"children":365},{"style":199},[366],{"type":46,"value":322},{"type":40,"tag":170,"props":368,"children":369},{"style":210},[370],{"type":46,"value":371},"Compare prompt variants",{"type":40,"tag":170,"props":373,"children":374},{"style":199},[375],{"type":46,"value":207},{"type":40,"tag":170,"props":377,"children":378},{"style":193},[379],{"type":46,"value":336},{"type":40,"tag":170,"props":381,"children":383},{"class":172,"line":382},4,[384,389],{"type":40,"tag":170,"props":385,"children":386},{"style":210},[387],{"type":46,"value":388},"  --out",{"type":40,"tag":170,"props":390,"children":391},{"style":210},[392],{"type":46,"value":393}," output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n",{"type":40,"tag":159,"props":395,"children":397},{"className":161,"code":396,"language":163,"meta":164,"style":164},"uv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",[398],{"type":40,"tag":90,"props":399,"children":400},{"__ignoreMap":164},[401,440,456,480],{"type":40,"tag":170,"props":402,"children":403},{"class":172,"line":173},[404,408,412,416,420,424,428,432,436],{"type":40,"tag":170,"props":405,"children":406},{"style":293},[407],{"type":46,"value":296},{"type":40,"tag":170,"props":409,"children":410},{"style":210},[411],{"type":46,"value":301},{"type":40,"tag":170,"props":413,"children":414},{"style":210},[415],{"type":46,"value":306},{"type":40,"tag":170,"props":417,"children":418},{"style":309},[419],{"type":46,"value":312},{"type":40,"tag":170,"props":421,"children":422},{"style":210},[423],{"type":46,"value":317},{"type":40,"tag":170,"props":425,"children":426},{"style":199},[427],{"type":46,"value":322},{"type":40,"tag":170,"props":429,"children":430},{"style":193},[431],{"type":46,"value":327},{"type":40,"tag":170,"props":433,"children":434},{"style":199},[435],{"type":46,"value":207},{"type":40,"tag":170,"props":437,"children":438},{"style":193},[439],{"type":46,"value":336},{"type":40,"tag":170,"props":441,"children":442},{"class":172,"line":183},[443,447,452],{"type":40,"tag":170,"props":444,"children":445},{"style":210},[446],{"type":46,"value":344},{"type":40,"tag":170,"props":448,"children":449},{"style":210},[450],{"type":46,"value":451}," tutorial",{"type":40,"tag":170,"props":453,"children":454},{"style":193},[455],{"type":46,"value":336},{"type":40,"tag":170,"props":457,"children":458},{"class":172,"line":356},[459,463,467,472,476],{"type":40,"tag":170,"props":460,"children":461},{"style":210},[462],{"type":46,"value":362},{"type":40,"tag":170,"props":464,"children":465},{"style":199},[466],{"type":46,"value":322},{"type":40,"tag":170,"props":468,"children":469},{"style":210},[470],{"type":46,"value":471},"Intro to embeddings",{"type":40,"tag":170,"props":473,"children":474},{"style":199},[475],{"type":46,"value":207},{"type":40,"tag":170,"props":477,"children":478},{"style":193},[479],{"type":46,"value":336},{"type":40,"tag":170,"props":481,"children":482},{"class":172,"line":382},[483,487],{"type":40,"tag":170,"props":484,"children":485},{"style":210},[486],{"type":46,"value":388},{"type":40,"tag":170,"props":488,"children":489},{"style":210},[490],{"type":46,"value":491}," output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n",{"type":40,"tag":255,"props":493,"children":494},{"start":356},[495,500,520,533],{"type":40,"tag":59,"props":496,"children":497},{},[498],{"type":46,"value":499},"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":40,"tag":59,"props":501,"children":502},{},[503,505,511,513,519],{"type":46,"value":504},"Apply the right pattern.\nFor experiments, follow ",{"type":40,"tag":90,"props":506,"children":508},{"className":507},[],[509],{"type":46,"value":510},"references\u002Fexperiment-patterns.md",{"type":46,"value":512},".\nFor tutorials, follow ",{"type":40,"tag":90,"props":514,"children":516},{"className":515},[],[517],{"type":46,"value":518},"references\u002Ftutorial-patterns.md",{"type":46,"value":134},{"type":40,"tag":59,"props":521,"children":522},{},[523,525,531],{"type":46,"value":524},"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":40,"tag":90,"props":526,"children":528},{"className":527},[],[529],{"type":46,"value":530},"references\u002Fnotebook-structure.md",{"type":46,"value":532}," first.",{"type":40,"tag":59,"props":534,"children":535},{},[536,538,544],{"type":46,"value":537},"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":40,"tag":90,"props":539,"children":541},{"className":540},[],[542],{"type":46,"value":543},"references\u002Fquality-checklist.md",{"type":46,"value":134},{"type":40,"tag":75,"props":546,"children":548},{"id":547},"templates-and-helper-script",[549],{"type":46,"value":550},"Templates and helper script",{"type":40,"tag":55,"props":552,"children":553},{},[554,574],{"type":40,"tag":59,"props":555,"children":556},{},[557,559,565,567,573],{"type":46,"value":558},"Templates live in ",{"type":40,"tag":90,"props":560,"children":562},{"className":561},[],[563],{"type":46,"value":564},"assets\u002Fexperiment-template.ipynb",{"type":46,"value":566}," and ",{"type":40,"tag":90,"props":568,"children":570},{"className":569},[],[571],{"type":46,"value":572},"assets\u002Ftutorial-template.ipynb",{"type":46,"value":134},{"type":40,"tag":59,"props":575,"children":576},{},[577],{"type":46,"value":578},"The helper script loads a template, updates the title cell, and writes a notebook.",{"type":40,"tag":49,"props":580,"children":581},{},[582],{"type":46,"value":583},"Script path:",{"type":40,"tag":55,"props":585,"children":586},{},[587],{"type":40,"tag":59,"props":588,"children":589},{},[590,595],{"type":40,"tag":90,"props":591,"children":593},{"className":592},[],[594],{"type":46,"value":327},{"type":46,"value":596}," (see \"Skill path\" section above)",{"type":40,"tag":75,"props":598,"children":600},{"id":599},"temp-and-output-conventions",[601],{"type":46,"value":602},"Temp and output conventions",{"type":40,"tag":55,"props":604,"children":605},{},[606,619,632],{"type":40,"tag":59,"props":607,"children":608},{},[609,611,617],{"type":46,"value":610},"Use ",{"type":40,"tag":90,"props":612,"children":614},{"className":613},[],[615],{"type":46,"value":616},"tmp\u002Fjupyter-notebook\u002F",{"type":46,"value":618}," for intermediate files; delete when done.",{"type":40,"tag":59,"props":620,"children":621},{},[622,624,630],{"type":46,"value":623},"Write final artifacts under ",{"type":40,"tag":90,"props":625,"children":627},{"className":626},[],[628],{"type":46,"value":629},"output\u002Fjupyter-notebook\u002F",{"type":46,"value":631}," when working in this repo.",{"type":40,"tag":59,"props":633,"children":634},{},[635,637,643],{"type":46,"value":636},"Use stable, descriptive filenames (for example, ",{"type":40,"tag":90,"props":638,"children":640},{"className":639},[],[641],{"type":46,"value":642},"ablation-temperature.ipynb",{"type":46,"value":247},{"type":40,"tag":75,"props":645,"children":647},{"id":646},"dependencies-install-only-when-needed",[648],{"type":46,"value":649},"Dependencies (install only when needed)",{"type":40,"tag":49,"props":651,"children":652},{},[653,655,660],{"type":46,"value":654},"Prefer ",{"type":40,"tag":90,"props":656,"children":658},{"className":657},[],[659],{"type":46,"value":296},{"type":46,"value":661}," for dependency management.",{"type":40,"tag":49,"props":663,"children":664},{},[665],{"type":46,"value":666},"Optional Python packages for local notebook execution:",{"type":40,"tag":159,"props":668,"children":670},{"className":161,"code":669,"language":163,"meta":164,"style":164},"uv pip install jupyterlab ipykernel\n",[671],{"type":40,"tag":90,"props":672,"children":673},{"__ignoreMap":164},[674],{"type":40,"tag":170,"props":675,"children":676},{"class":172,"line":173},[677,681,686,691,696],{"type":40,"tag":170,"props":678,"children":679},{"style":293},[680],{"type":46,"value":296},{"type":40,"tag":170,"props":682,"children":683},{"style":210},[684],{"type":46,"value":685}," pip",{"type":40,"tag":170,"props":687,"children":688},{"style":210},[689],{"type":46,"value":690}," install",{"type":40,"tag":170,"props":692,"children":693},{"style":210},[694],{"type":46,"value":695}," jupyterlab",{"type":40,"tag":170,"props":697,"children":698},{"style":210},[699],{"type":46,"value":700}," ipykernel\n",{"type":40,"tag":49,"props":702,"children":703},{},[704],{"type":46,"value":705},"The bundled scaffold script uses only the Python standard library and does not require extra dependencies.",{"type":40,"tag":75,"props":707,"children":709},{"id":708},"environment",[710],{"type":46,"value":711},"Environment",{"type":40,"tag":49,"props":713,"children":714},{},[715],{"type":46,"value":716},"No required environment variables.",{"type":40,"tag":75,"props":718,"children":720},{"id":719},"reference-map",[721],{"type":46,"value":722},"Reference map",{"type":40,"tag":55,"props":724,"children":725},{},[726,736,746,756],{"type":40,"tag":59,"props":727,"children":728},{},[729,734],{"type":40,"tag":90,"props":730,"children":732},{"className":731},[],[733],{"type":46,"value":510},{"type":46,"value":735},": experiment structure and heuristics.",{"type":40,"tag":59,"props":737,"children":738},{},[739,744],{"type":40,"tag":90,"props":740,"children":742},{"className":741},[],[743],{"type":46,"value":518},{"type":46,"value":745},": tutorial structure and teaching flow.",{"type":40,"tag":59,"props":747,"children":748},{},[749,754],{"type":40,"tag":90,"props":750,"children":752},{"className":751},[],[753],{"type":46,"value":530},{"type":46,"value":755},": notebook JSON shape and safe editing rules.",{"type":40,"tag":59,"props":757,"children":758},{},[759,764],{"type":40,"tag":90,"props":760,"children":762},{"className":761},[],[763],{"type":46,"value":543},{"type":46,"value":765},": final validation checklist.",{"type":40,"tag":767,"props":768,"children":769},"style",{},[770],{"type":46,"value":771},"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":773,"total":891},[774,790,807,826,841,862,872],{"slug":775,"name":775,"fn":776,"description":777,"org":778,"tags":779,"stars":23,"repoUrl":24,"updatedAt":789},"1password","manage secrets with 1Password CLI","Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading\u002Finjecting\u002Frunning secrets via op.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[780,783,786],{"name":781,"slug":782,"type":16},"Authentication","authentication",{"name":784,"slug":785,"type":16},"CLI","cli",{"name":787,"slug":788,"type":16},"Security","security","2026-07-13T06:24:39.504387",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":23,"repoUrl":24,"updatedAt":806},"agent-slack","automate Slack messaging and workflows","Slack automation CLI — read\u002Fsend\u002Fsearch messages, browse threads and channels, manage channels, download attachments, look up users, and run workflows.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[796,799,800,803],{"name":797,"slug":798,"type":16},"Automation","automation",{"name":784,"slug":785,"type":16},{"name":801,"slug":802,"type":16},"Messaging","messaging",{"name":804,"slug":805,"type":16},"Slack","slack","2026-07-13T06:23:51.908511",{"slug":808,"name":808,"fn":809,"description":810,"org":811,"tags":812,"stars":23,"repoUrl":24,"updatedAt":825},"ai-news","fetch and summarize AI news","Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[813,816,819,822],{"name":814,"slug":815,"type":16},"Communications","communications",{"name":817,"slug":818,"type":16},"LLM","llm",{"name":820,"slug":821,"type":16},"Research","research",{"name":823,"slug":824,"type":16},"Summarization","summarization","2026-07-13T06:24:20.520223",{"slug":827,"name":827,"fn":828,"description":829,"org":830,"tags":831,"stars":23,"repoUrl":24,"updatedAt":840},"creating-letta-code-channels","build and debug Letta Code channels","Builds and debugs Letta Code channels, including first-party channel adapters and dynamic user channel plugins under ~\u002F.letta\u002Fchannels. Use when adding Telegram, WhatsApp, Bluesky, Slack, Discord, or custom channel support; testing channel routing, pairing, MessageChannel, runtime dependencies, or channel plugin manifests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[832,835,838,839],{"name":833,"slug":834,"type":16},"Agents","agents",{"name":836,"slug":837,"type":16},"API Development","api-development",{"name":801,"slug":802,"type":16},{"name":804,"slug":805,"type":16},"2026-07-13T06:25:55.843495",{"slug":842,"name":842,"fn":843,"description":844,"org":845,"tags":846,"stars":23,"repoUrl":24,"updatedAt":861},"datadog","query Datadog observability data","Query Datadog observability data (logs, metrics, monitors, dashboards, hosts) via direct API. Use when investigating production issues, checking monitors, searching logs, or accessing Datadog data.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[847,849,852,855,858],{"name":848,"slug":842,"type":16},"Datadog",{"name":850,"slug":851,"type":16},"Logs","logs",{"name":853,"slug":854,"type":16},"Metrics","metrics",{"name":856,"slug":857,"type":16},"Monitoring","monitoring",{"name":859,"slug":860,"type":16},"Observability","observability","2026-07-13T06:24:27.990605",{"slug":863,"name":863,"fn":864,"description":865,"org":866,"tags":867,"stars":23,"repoUrl":24,"updatedAt":871},"discord","automate Discord server and channel tasks","Discord automation CLI — send\u002Fread\u002Fsearch messages, manage channels and servers, react, create threads, pin messages, and look up users.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[868,869,870],{"name":797,"slug":798,"type":16},{"name":784,"slug":785,"type":16},{"name":801,"slug":802,"type":16},"2026-07-13T06:24:26.62387",{"slug":873,"name":873,"fn":874,"description":875,"org":876,"tags":877,"stars":23,"repoUrl":24,"updatedAt":890},"doc","create and edit Word documents","Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts\u002Frender_docx.py` for visual checks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[878,881,884,887],{"name":879,"slug":880,"type":16},"Documents","documents",{"name":882,"slug":883,"type":16},"DOCX","docx",{"name":885,"slug":886,"type":16},"Office","office",{"name":888,"slug":889,"type":16},"Word","word","2026-07-13T06:23:44.299568",45,{"items":893,"total":1048},[894,908,923,935,947,961,971,982,994,1010,1021,1033],{"slug":895,"name":895,"fn":896,"description":897,"org":898,"tags":899,"stars":905,"repoUrl":906,"updatedAt":907},"acquiring-skills","discover and install agent skills","Discover and install skills from Hermes, ClawHub, GitHub, and other registries. Load this skill whenever a user asks for a capability you don't already have — image generation, social media, email, calendar, finance, DevOps, search, browser automation, etc.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[900,901,902],{"name":833,"slug":834,"type":16},{"name":797,"slug":798,"type":16},{"name":903,"slug":904,"type":16},"GitHub","github",2831,"https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fletta-code","2026-07-13T06:22:58.45767",{"slug":909,"name":910,"fn":911,"description":912,"org":913,"tags":914,"stars":905,"repoUrl":906,"updatedAt":922},"context-doctor","Context Doctor","repair system prompt and memory degradation","Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[915,916,919],{"name":833,"slug":834,"type":16},{"name":917,"slug":918,"type":16},"AI Context","ai-context",{"name":920,"slug":921,"type":16},"Debugging","debugging","2026-07-13T06:22:50.151002",{"slug":924,"name":924,"fn":925,"description":926,"org":927,"tags":928,"stars":905,"repoUrl":906,"updatedAt":934},"converting-mcps-to-skills","connect MCP servers to create skills","Connect to MCP (Model Context Protocol) servers and create skills for repeated use. Load when a user wants to use an MCP server, connect to external tools via MCP, or when they mention MCP, model context protocol, or specific MCP servers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[929,930,931],{"name":833,"slug":834,"type":16},{"name":797,"slug":798,"type":16},{"name":932,"slug":933,"type":16},"MCP","mcp","2026-07-13T06:23:37.646079",{"slug":936,"name":936,"fn":937,"description":938,"org":939,"tags":940,"stars":905,"repoUrl":906,"updatedAt":946},"creating-mods","create and edit Letta Code mods","Creates and edits trusted local Letta Code mods, including tools, slash commands, local-only model providers, lifecycle\u002Fturn events, scoped conversation helpers, panels, and capability-gated behavior. Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider\u002Fmodel adapter, transform turns, react to app events, or add lightweight mod UI outside the dedicated \u002Fstatusline flow.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[941,942,943],{"name":833,"slug":834,"type":16},{"name":797,"slug":798,"type":16},{"name":944,"slug":945,"type":16},"Coding","coding","2026-07-23T05:42:38.133565",{"slug":948,"name":948,"fn":949,"description":950,"org":951,"tags":952,"stars":905,"repoUrl":906,"updatedAt":960},"creating-skills","create and update agent skills","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[953,954,957],{"name":833,"slug":834,"type":16},{"name":955,"slug":956,"type":16},"Documentation","documentation",{"name":958,"slug":959,"type":16},"Plugin Development","plugin-development","2026-07-13T06:22:56.998659",{"slug":962,"name":962,"fn":963,"description":964,"org":965,"tags":966,"stars":905,"repoUrl":906,"updatedAt":970},"customizing-commands","create and manage Letta slash commands","Creates, edits, and enables Letta Code mod-provided slash commands. Use when the user asks to add a custom \u002Fcommand, slash command, command shortcut, scoped conversation-backed command, or command-driven panel behavior.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[967,968,969],{"name":833,"slug":834,"type":16},{"name":797,"slug":798,"type":16},{"name":784,"slug":785,"type":16},"2026-07-13T06:23:18.266798",{"slug":972,"name":972,"fn":973,"description":974,"org":975,"tags":976,"stars":905,"repoUrl":906,"updatedAt":981},"customizing-statusline","customize Letta Code statusline mods","Creates, edits, and migrates Letta Code statusline mods. Use when handling the \u002Fstatusline command or continuing work started by \u002Fstatusline.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[977,978],{"name":784,"slug":785,"type":16},{"name":979,"slug":980,"type":16},"Engineering","engineering","2026-07-13T06:23:27.465985",{"slug":983,"name":983,"fn":984,"description":985,"org":986,"tags":987,"stars":905,"repoUrl":906,"updatedAt":993},"dispatching-coding-agents","dispatch stateless coding agents","Dispatch stateless coding agents (Claude Code or Codex) via Bash. Use when you're stuck, need a second opinion, or need parallel research on a hard problem. They have no memory — you must provide all context.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[988,989,990],{"name":833,"slug":834,"type":16},{"name":944,"slug":945,"type":16},{"name":991,"slug":992,"type":16},"Multi-Agent","multi-agent","2026-07-26T05:46:56.388845",{"slug":995,"name":995,"fn":996,"description":997,"org":998,"tags":999,"stars":905,"repoUrl":906,"updatedAt":1009},"editing-letta-code-desktop-preferences","edit Letta Code Desktop preferences","Edits Letta Code Desktop (LCD) preferences by safely reading and updating ~\u002F.letta\u002Fdesktop_preferences.json. Use only when the user asks to change current Desktop\u002FLCD settings such as theme, default working directory, remote access preference, or remote environment name via the preferences JSON.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1000,1003,1006],{"name":1001,"slug":1002,"type":16},"Configuration","configuration",{"name":1004,"slug":1005,"type":16},"Desktop","desktop",{"name":1007,"slug":1008,"type":16},"Themes","themes","2026-07-13T06:23:41.407811",{"slug":1011,"name":1011,"fn":1012,"description":1013,"org":1014,"tags":1015,"stars":905,"repoUrl":906,"updatedAt":1020},"finding-agents","locate and manage agents on server","Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1016,1017],{"name":833,"slug":834,"type":16},{"name":1018,"slug":1019,"type":16},"Management","management","2026-07-16T06:02:17.297841",{"slug":1022,"name":1022,"fn":1023,"description":1024,"org":1025,"tags":1026,"stars":905,"repoUrl":906,"updatedAt":1032},"generating-mod-envs","generate Letta mod learning environments","Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for `\u002Fmods learn --env`; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative controls, and candidate diversity hints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1027,1028,1031],{"name":833,"slug":834,"type":16},{"name":1029,"slug":1030,"type":16},"AI Infrastructure","ai-infrastructure",{"name":1001,"slug":1002,"type":16},"2026-07-13T06:23:08.838181",{"slug":1034,"name":1034,"fn":1035,"description":1036,"org":1037,"tags":1038,"stars":905,"repoUrl":906,"updatedAt":1047},"image-generation","generate images from text prompts","Generate images from text prompts (and optionally edit\u002Fremix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1039,1042,1045],{"name":1040,"slug":1041,"type":16},"Creative","creative",{"name":1043,"slug":1044,"type":16},"Graphics","graphics",{"name":1046,"slug":1034,"type":16},"Image Generation","2026-07-13T06:23:06.189403",69]