[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-code-migration":3,"mdc--9h1vny-key":34,"related-repo-anthropic-code-migration":316,"related-org-anthropic-code-migration":324},{"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},"code-migration","perform large-scale language code migrations","Run a large-scale language migration with the six-step process: create the map and the rules, stress-test the rules, translate everything, compile, run it, match behavior. Use when the user wants to migrate, port, or rewrite a codebase from one language to another (\"migrate this to Rust\", \"port our Python CLI to TypeScript\", \"should we rewrite this in Go?\"), or asks for a migration feasibility assessment. Not for incremental JS→TS adoption — that needs no machinery — or single-file conversions.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20],{"name":14,"slug":15,"type":16},"Claude Code","claude-code","tag",{"name":18,"slug":19,"type":16},"Migration","migration",{"name":21,"slug":22,"type":16},"Code Analysis","code-analysis",25,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcode-migration-kit-with-claude-code","2026-07-18T05:47:27.407608",null,1,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Prompts, templates, and scripts for running large-scale language migrations with Claude Code","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcode-migration-kit-with-claude-code\u002Ftree\u002FHEAD\u002Fskill","---\nname: code-migration\ndescription: >\n  Run a large-scale language migration with the six-step process: create the\n  map and the rules, stress-test the rules, translate everything, compile, run\n  it, match behavior. Use when the user wants to migrate, port, or rewrite a\n  codebase from one language to another (\"migrate this to Rust\", \"port our\n  Python CLI to TypeScript\", \"should we rewrite this in Go?\"), or asks for a\n  migration feasibility assessment. Not for incremental JS→TS adoption — that\n  needs no machinery — or single-file conversions.\n---\n\n# Code migration (six-step process)\n\nYou are orchestrating a language migration using the Claude Code Migration\nKit. [kit path]\u002FREADME.md defines the process; [kit path]\u002FCLAUDE.md defines\nyour standing rules — read both before acting (set [kit path] when installing\nthis skill). The standing rules override\nconvenience: queues live on disk, sign-off gates end workflows, the rulebook\nis read-only inside loops, reviewers are adversarial and separate.\n\n## Routing\n\n1. **No migration artifacts exist yet** (`migration\u002F` absent): run\n   `prompts\u002F00-feasibility.md`. Produce the report, deliver the verdict, STOP.\n   Do not begin Step 1 in the same session, even if the verdict is \"migrate\n   now\" — the human kicks off each phase.\n1b. **Feasibility signed off, no judge yet:** before Step 1, confirm a judge\n   exists that runs against both old and new code through the public surface.\n   If the existing suite is public-surface (or already in a third language),\n   it's the judge — carry it to Step 6. If it imports internals, run\n   `prompts\u002F00b-judge-setup.md` to build and validate a portable parity harness\n   (validated against the original AND deliberately broken code) and STOP at its\n   gate. Never start Step 1 without a judge — there's no exit condition without\n   one.\n2. **Feasibility and judge signed off, no map\u002Frules:** run Step 1 — adapt a\n   `scripts\u002Fdepmap_*` for the source ecosystem (`prompts\u002F01`), copy\n   `templates\u002FRULEBOOK.md` to `migration\u002FRULEBOOK.md` and draft it with the\n   human (the policy decisions are theirs; survey the codebase for the facts),\n   then `prompts\u002F02` for the gap inventory. Each ends at its own gate.\n3. **Step 1 signed off:** confirm the HUMAN has installed\n   `.claude\u002Fsettings.json` from `templates\u002Fsettings.json` — prompt 03\n   verifies it; never install it yourself — then run\n   `prompts\u002F03-stress-test.md`. But FIRST check the rulebook's §0 posture:\n   if this is a redesign migration, the bakeoff is invalid; substitute\n   adversarial design-doc review and tell the human why.\n4. **Stress test signed off:** confirm `migration\u002Fmanifest.tsv` exists\n   (prompt 01's closing action generates it), then run\n   `prompts\u002F04-translation-kickoff.md` with `scripts\u002Fqueue_runner.mjs` as the\n   queue — first check the referee price: if the target's typecheck is cheap,\n   the dissolve edit is the human's act at the gate — ask them to remove\n   those denies from settings.json; never edit it yourself (README Step 4\n   dissolves into Step 3).\n5. **Translation queue empty:** Step 4 via `prompts\u002F05-survey-build.md`\n   (survey build → machine queue → fixers without compiler access; skip it\n   entirely if Step 4 dissolved into Step 3), then Step 5 (hello world,\n   smoke), then Step 6 (inherited suite burndown, or parity referee against\n   the old code).\n6. **Step 6 done-gate passed** (both counts documented — README Step 6): run\n   `prompts\u002F06-post-parity.md` — collect the port markers, classify fix-now\n   vs document-and-close, ship each fix as its own flagged change proved by a\n   parity re-run. Ends at its own gate.\n\n## Constant behaviors\n\n- Report progress as burndown numbers (`queue_runner.mjs status`), not prose.\n- A failure seen three times is a rule bug: stop fixing instances, queue the\n  amendment, propose regenerating the slice.\n- \"Don't migrate\" and \"stop here\" are valid recommendations at every gate.\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,48,74,81,283,289],{"type":40,"tag":41,"props":42,"children":44},"element","h1",{"id":43},"code-migration-six-step-process",[45],{"type":46,"value":47},"text","Code migration (six-step process)",{"type":40,"tag":49,"props":50,"children":51},"p",{},[52,54,60,62,66,68,72],{"type":46,"value":53},"You are orchestrating a language migration using the Claude Code Migration\nKit. ",{"type":40,"tag":55,"props":56,"children":57},"span",{},[58],{"type":46,"value":59},"kit path",{"type":46,"value":61},"\u002FREADME.md defines the process; ",{"type":40,"tag":55,"props":63,"children":64},{},[65],{"type":46,"value":59},{"type":46,"value":67},"\u002FCLAUDE.md defines\nyour standing rules — read both before acting (set ",{"type":40,"tag":55,"props":69,"children":70},{},[71],{"type":46,"value":59},{"type":46,"value":73}," when installing\nthis skill). The standing rules override\nconvenience: queues live on disk, sign-off gates end workflows, the rulebook\nis read-only inside loops, reviewers are adversarial and separate.",{"type":40,"tag":75,"props":76,"children":78},"h2",{"id":77},"routing",[79],{"type":46,"value":80},"Routing",{"type":40,"tag":82,"props":83,"children":84},"ol",{},[85,129,179,213,247,265],{"type":40,"tag":86,"props":87,"children":88},"li",{},[89,95,97,104,106,112,114,119,121,127],{"type":40,"tag":90,"props":91,"children":92},"strong",{},[93],{"type":46,"value":94},"No migration artifacts exist yet",{"type":46,"value":96}," (",{"type":40,"tag":98,"props":99,"children":101},"code",{"className":100},[],[102],{"type":46,"value":103},"migration\u002F",{"type":46,"value":105}," absent): run\n",{"type":40,"tag":98,"props":107,"children":109},{"className":108},[],[110],{"type":46,"value":111},"prompts\u002F00-feasibility.md",{"type":46,"value":113},". Produce the report, deliver the verdict, STOP.\nDo not begin Step 1 in the same session, even if the verdict is \"migrate\nnow\" — the human kicks off each phase.\n1b. ",{"type":40,"tag":90,"props":115,"children":116},{},[117],{"type":46,"value":118},"Feasibility signed off, no judge yet:",{"type":46,"value":120}," before Step 1, confirm a judge\nexists that runs against both old and new code through the public surface.\nIf the existing suite is public-surface (or already in a third language),\nit's the judge — carry it to Step 6. If it imports internals, run\n",{"type":40,"tag":98,"props":122,"children":124},{"className":123},[],[125],{"type":46,"value":126},"prompts\u002F00b-judge-setup.md",{"type":46,"value":128}," to build and validate a portable parity harness\n(validated against the original AND deliberately broken code) and STOP at its\ngate. Never start Step 1 without a judge — there's no exit condition without\none.",{"type":40,"tag":86,"props":130,"children":131},{},[132,137,139,145,147,153,155,161,163,169,171,177],{"type":40,"tag":90,"props":133,"children":134},{},[135],{"type":46,"value":136},"Feasibility and judge signed off, no map\u002Frules:",{"type":46,"value":138}," run Step 1 — adapt a\n",{"type":40,"tag":98,"props":140,"children":142},{"className":141},[],[143],{"type":46,"value":144},"scripts\u002Fdepmap_*",{"type":46,"value":146}," for the source ecosystem (",{"type":40,"tag":98,"props":148,"children":150},{"className":149},[],[151],{"type":46,"value":152},"prompts\u002F01",{"type":46,"value":154},"), copy\n",{"type":40,"tag":98,"props":156,"children":158},{"className":157},[],[159],{"type":46,"value":160},"templates\u002FRULEBOOK.md",{"type":46,"value":162}," to ",{"type":40,"tag":98,"props":164,"children":166},{"className":165},[],[167],{"type":46,"value":168},"migration\u002FRULEBOOK.md",{"type":46,"value":170}," and draft it with the\nhuman (the policy decisions are theirs; survey the codebase for the facts),\nthen ",{"type":40,"tag":98,"props":172,"children":174},{"className":173},[],[175],{"type":46,"value":176},"prompts\u002F02",{"type":46,"value":178}," for the gap inventory. Each ends at its own gate.",{"type":40,"tag":86,"props":180,"children":181},{},[182,187,189,195,197,203,205,211],{"type":40,"tag":90,"props":183,"children":184},{},[185],{"type":46,"value":186},"Step 1 signed off:",{"type":46,"value":188}," confirm the HUMAN has installed\n",{"type":40,"tag":98,"props":190,"children":192},{"className":191},[],[193],{"type":46,"value":194},".claude\u002Fsettings.json",{"type":46,"value":196}," from ",{"type":40,"tag":98,"props":198,"children":200},{"className":199},[],[201],{"type":46,"value":202},"templates\u002Fsettings.json",{"type":46,"value":204}," — prompt 03\nverifies it; never install it yourself — then run\n",{"type":40,"tag":98,"props":206,"children":208},{"className":207},[],[209],{"type":46,"value":210},"prompts\u002F03-stress-test.md",{"type":46,"value":212},". But FIRST check the rulebook's §0 posture:\nif this is a redesign migration, the bakeoff is invalid; substitute\nadversarial design-doc review and tell the human why.",{"type":40,"tag":86,"props":214,"children":215},{},[216,221,223,229,231,237,239,245],{"type":40,"tag":90,"props":217,"children":218},{},[219],{"type":46,"value":220},"Stress test signed off:",{"type":46,"value":222}," confirm ",{"type":40,"tag":98,"props":224,"children":226},{"className":225},[],[227],{"type":46,"value":228},"migration\u002Fmanifest.tsv",{"type":46,"value":230}," exists\n(prompt 01's closing action generates it), then run\n",{"type":40,"tag":98,"props":232,"children":234},{"className":233},[],[235],{"type":46,"value":236},"prompts\u002F04-translation-kickoff.md",{"type":46,"value":238}," with ",{"type":40,"tag":98,"props":240,"children":242},{"className":241},[],[243],{"type":46,"value":244},"scripts\u002Fqueue_runner.mjs",{"type":46,"value":246}," as the\nqueue — first check the referee price: if the target's typecheck is cheap,\nthe dissolve edit is the human's act at the gate — ask them to remove\nthose denies from settings.json; never edit it yourself (README Step 4\ndissolves into Step 3).",{"type":40,"tag":86,"props":248,"children":249},{},[250,255,257,263],{"type":40,"tag":90,"props":251,"children":252},{},[253],{"type":46,"value":254},"Translation queue empty:",{"type":46,"value":256}," Step 4 via ",{"type":40,"tag":98,"props":258,"children":260},{"className":259},[],[261],{"type":46,"value":262},"prompts\u002F05-survey-build.md",{"type":46,"value":264},"\n(survey build → machine queue → fixers without compiler access; skip it\nentirely if Step 4 dissolved into Step 3), then Step 5 (hello world,\nsmoke), then Step 6 (inherited suite burndown, or parity referee against\nthe old code).",{"type":40,"tag":86,"props":266,"children":267},{},[268,273,275,281],{"type":40,"tag":90,"props":269,"children":270},{},[271],{"type":46,"value":272},"Step 6 done-gate passed",{"type":46,"value":274}," (both counts documented — README Step 6): run\n",{"type":40,"tag":98,"props":276,"children":278},{"className":277},[],[279],{"type":46,"value":280},"prompts\u002F06-post-parity.md",{"type":46,"value":282}," — collect the port markers, classify fix-now\nvs document-and-close, ship each fix as its own flagged change proved by a\nparity re-run. Ends at its own gate.",{"type":40,"tag":75,"props":284,"children":286},{"id":285},"constant-behaviors",[287],{"type":46,"value":288},"Constant behaviors",{"type":40,"tag":290,"props":291,"children":292},"ul",{},[293,306,311],{"type":40,"tag":86,"props":294,"children":295},{},[296,298,304],{"type":46,"value":297},"Report progress as burndown numbers (",{"type":40,"tag":98,"props":299,"children":301},{"className":300},[],[302],{"type":46,"value":303},"queue_runner.mjs status",{"type":46,"value":305},"), not prose.",{"type":40,"tag":86,"props":307,"children":308},{},[309],{"type":46,"value":310},"A failure seen three times is a rule bug: stop fixing instances, queue the\namendment, propose regenerating the slice.",{"type":40,"tag":86,"props":312,"children":313},{},[314],{"type":46,"value":315},"\"Don't migrate\" and \"stop here\" are valid recommendations at every gate.",{"items":317,"total":27},[318],{"slug":4,"name":4,"fn":5,"description":6,"org":319,"tags":320,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[321,322,323],{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"items":325,"total":512},[326,347,361,373,392,405,426,446,460,475,483,496],{"slug":327,"name":327,"fn":328,"description":329,"org":330,"tags":331,"stars":344,"repoUrl":345,"updatedAt":346},"algorithmic-art","create algorithmic 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":11},[332,335,338,341],{"name":333,"slug":334,"type":16},"Creative","creative",{"name":336,"slug":337,"type":16},"Design","design",{"name":339,"slug":340,"type":16},"Generative Art","generative-art",{"name":342,"slug":343,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":348,"name":348,"fn":349,"description":350,"org":351,"tags":352,"stars":344,"repoUrl":345,"updatedAt":360},"brand-guidelines","apply Anthropic brand colors and typography","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":11},[353,356,357],{"name":354,"slug":355,"type":16},"Branding","branding",{"name":336,"slug":337,"type":16},{"name":358,"slug":359,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":362,"name":362,"fn":363,"description":364,"org":365,"tags":366,"stars":344,"repoUrl":345,"updatedAt":372},"canvas-design","create posters and visual art as PNG or PDF","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":11},[367,368,369],{"name":333,"slug":334,"type":16},{"name":336,"slug":337,"type":16},{"name":370,"slug":371,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":374,"name":374,"fn":375,"description":376,"org":377,"tags":378,"stars":344,"repoUrl":345,"updatedAt":391},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[379,382,383,386,388],{"name":380,"slug":381,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":384,"slug":385,"type":16},"Anthropic SDK","anthropic-sdk",{"name":387,"slug":374,"type":16},"Claude API",{"name":389,"slug":390,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":393,"name":393,"fn":394,"description":395,"org":396,"tags":397,"stars":344,"repoUrl":345,"updatedAt":404},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[398,401],{"name":399,"slug":400,"type":16},"Documentation","documentation",{"name":402,"slug":403,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":406,"name":406,"fn":407,"description":408,"org":409,"tags":410,"stars":344,"repoUrl":345,"updatedAt":425},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[411,414,416,419,422],{"name":412,"slug":413,"type":16},"Documents","documents",{"name":415,"slug":406,"type":16},"DOCX",{"name":417,"slug":418,"type":16},"Office","office",{"name":420,"slug":421,"type":16},"Templates","templates",{"name":423,"slug":424,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":427,"name":427,"fn":428,"description":429,"org":430,"tags":431,"stars":344,"repoUrl":345,"updatedAt":445},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[432,433,436,439,442],{"name":336,"slug":337,"type":16},{"name":434,"slug":435,"type":16},"Frontend","frontend",{"name":437,"slug":438,"type":16},"React","react",{"name":440,"slug":441,"type":16},"Tailwind CSS","tailwind-css",{"name":443,"slug":444,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":447,"name":447,"fn":448,"description":449,"org":450,"tags":451,"stars":344,"repoUrl":345,"updatedAt":459},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[452,455,456],{"name":453,"slug":454,"type":16},"Communications","communications",{"name":420,"slug":421,"type":16},{"name":457,"slug":458,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":461,"name":461,"fn":462,"description":463,"org":464,"tags":465,"stars":344,"repoUrl":345,"updatedAt":474},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[466,467,470,471],{"name":380,"slug":381,"type":16},{"name":468,"slug":469,"type":16},"API Development","api-development",{"name":389,"slug":390,"type":16},{"name":472,"slug":473,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":371,"name":371,"fn":476,"description":477,"org":478,"tags":479,"stars":344,"repoUrl":345,"updatedAt":482},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[480,481],{"name":412,"slug":413,"type":16},{"name":370,"slug":371,"type":16},"2026-04-06T17:56:02.483316",{"slug":484,"name":484,"fn":485,"description":486,"org":487,"tags":488,"stars":344,"repoUrl":345,"updatedAt":495},"pptx","create and edit PowerPoint presentations","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[489,492],{"name":490,"slug":491,"type":16},"PowerPoint","powerpoint",{"name":493,"slug":494,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":497,"name":497,"fn":498,"description":499,"org":500,"tags":501,"stars":344,"repoUrl":345,"updatedAt":511},"skill-creator","create and optimize agent skills","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[502,503,504,507,510],{"name":380,"slug":381,"type":16},{"name":399,"slug":400,"type":16},{"name":505,"slug":506,"type":16},"Evals","evals",{"name":508,"slug":509,"type":16},"Performance","performance",{"name":402,"slug":403,"type":16},"2026-04-19T06:45:40.804",490]