[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEVEZE2DMJC4K18JCPQ4JS":3,"skill-same:01M6DEVEZE2DMJC4K18JCPQ4JS":116},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6DEVEZE2DMJC4K18JCPQ4JS","social-corpus-extraction",null,"Use when building a personal writing\u002Fstyle corpus from a user's OWN messages and posts across Discord, Facebook posts + comments, Facebook Messenger, and WhatsApp — isolating only the owner's authored text, then folding every source into one deduplicated jsonl corpus. Handles the traps that silently break these extractions: the Meta DYI double-encoded-UTF-8 mojibake, the 4-way Facebook post-path drift, WhatsApp-DYI-has-no-message-bodies, and locale-dependent title strings. NOT for scraping other people's content, NOT a live-API social client (see social-media-toolchain), NOT for one specific person's hardcoded identity — every script takes the owner identity by argv\u002Fenv.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"social corpus extraction","extraction","social","scraping","env","across","message","drift","facebook","only","use","writing","text","Media","api","social-media","Meta","messages","whatsapp","discord","2026-11-10 10:12:30",false,"---\nname: social-corpus-extraction\ndescription: \"Use when building a personal writing\u002Fstyle corpus from a user's OWN messages and posts across Discord, Facebook posts + comments, Facebook Messenger, and WhatsApp — isolating only the owner's authored text, then folding every source into one deduplicated jsonl corpus. Handles the traps that silently break these extractions: the Meta DYI double-encoded-UTF-8 mojibake, the 4-way Facebook post-path drift, WhatsApp-DYI-has-no-message-bodies, and locale-dependent title strings. NOT for scraping other people's content, NOT a live-API social client (see social-media-toolchain), NOT for one specific person's hardcoded identity — every script takes the owner identity by argv\u002Fenv.\"\n---\n\n# social-corpus-extraction\n\nTurn a user's own social-media history into a clean, deduplicated **writing corpus** (for style\nanalysis, fine-tuning, or personal archive). Five stdlib-only Python scripts under `scripts\u002F`, each\nmirroring the same three-output shape (`\u003Cowner>_all.txt`, `\u003Cowner>_substantial.txt`, `\u003Cowner>.jsonl`)\nplus a unifier. **Classify structurally, never by language** — the owner's archive may be in any\nlocale, and every locale-dependent heuristic is a bug (see gotcha 4).\n\n## The rails, and which actually carry the owner's WRITING\n\n| Source | Rail | What you get |\n|---|---|---|\n| Discord | DiscordChatExporter JSON | full history — `isolate_discord.py` (reference impl) |\n| Facebook posts + comments | Meta \"Download Your Information\" (JSON, All-time) | full history — `isolate_facebook.py` |\n| Facebook Messenger | same DYI zip, `messages\u002Finbox\u002F` | full history — `isolate_messenger.py` |\n| WhatsApp | **phone-side only** — per-chat \"Export chat\" `_chat.txt`, or the on-device DB | `isolate_whatsapp.py` |\n| WhatsApp via Meta DYI | ❌ **NO message bodies** — account metadata only (gotcha 3) | — |\n| a live MCP rail (`social-hub`) | partial recent window only (Baileys ~4-5 days) | supplements, never replaces the export |\n\nThen `build_corpus.py` folds every per-source `.jsonl` into one deduplicated corpus with a MANIFEST\nthat accounts for every dropped record under a named reason.\n\n## The four traps (each cost real debugging — do not rediscover)\n\n1. **Meta DYI mojibake is double-encoded UTF-8, and the naive fix silently corrupts.**\n   Meta emits `Ä`+U+0083 where `ă` belongs. `s.encode('latin-1').decode('utf-8')` is the correct\n   *inverse* but NOT safe: on an already-clean string with Latin-1-range chars it raises (so a\n   try\u002Fexcept returns it UNREPAIRED and silent); on a mixed string with any char > U+00FF it raises\n   too. **Gate the repair on a detector** (a UTF-8-run regex) and run it **after `json.loads`** —\n   Meta double-escapes ASCII metacharacters too (`\"`→bare `\"`), so raw-byte repair yields\n   JSONDecodeError. NEVER apply it to client-written UTF-8 (Discord, WhatsApp `_chat.txt`) — it\n   CREATES corruption. `build_corpus.py` applies repair only to facebook\u002Fmessenger sources.\n\n2. **The Facebook post path drifted ≥4×**: `posts\u002Fyour_posts.json` → `posts\u002Fyour_posts_1.json` →\n   `your_facebook_activity\u002Fposts\u002Fyour_posts__check_ins__photos_and_videos_1.json` →\n   `your_activity_across_facebook\u002F...`. A pipeline pinned to one path finds **zero** posts in a\n   2024+ archive. `isolate_facebook.py` globs all known roots and exits non-zero (naming the file)\n   on an unrecognised schema — never silently emits empty.\n\n3. **WhatsApp DYI export contains NO message text** (WhatsApp Help Center, verbatim; E2EE means Meta\n   has no plaintext). The owner's WhatsApp history is obtainable ONLY client-side: iPhone → device\n   backup → `ChatStorage.sqlite`; Android → 64-digit-key backup → `crypt15` → `wa-crypt-tools`; or\n   in-app per-chat \"Export chat\" `_chat.txt` (manual, most-recent-N). `isolate_whatsapp.py` reads\n   the `_chat.txt` \u002F DB-JSON, never the DYI zip.\n\n4. **Classify structurally, not by locale keyword.** Meta's auto-generated `title`\u002Fnotification\n   strings are localized; an English regex silently misclassifies a non-English archive. Key on JSON\n   structure + prose length. The min-length floor is the single most load-bearing,\n   language-independent predicate (it removed 99.1% of posts-on-others'-timelines in the reference run).\n\n## Usage\n\n```\npython scripts\u002Fisolate_facebook.py  --owner-name \"Full Name\" --owner-name \"alt spelling\"   # DYI zip\u002Fdir in .\u002FFacebook\npython scripts\u002Fisolate_messenger.py --root .\u002FFacebook --me \"Full Name\"\npython scripts\u002Fisolate_whatsapp.py  \u003Cpath-to-_chat.txt-or-db.json> --owner-name \"\u003Cdisplay name>\"\npython scripts\u002Fbuild_corpus.py       # auto-discovers every per-source .jsonl, writes corpus\u002F{corpus.jsonl,corpus.md,MANIFEST.md}\n```\nEvery script is **stdlib-only, Windows\u002FUnix, streams per-file** (never `json.load` a multi-GB export\nwhole). Owner identity is argv\u002Fenv — no identity is hardcoded. Exit 4 from `isolate_facebook.py` =\nan unrecognised schema; the corpus is INCOMPLETE — read the printed filename, extend the glob.\n\n## Honest limits\n\nFixture-green does NOT prove real-archive-correct — the fixtures encode our assumptions about a Meta\nexport that had not yet arrived when these were written. Treat the first real run as an experiment:\nread `MANIFEST.md`'s drop accounting, and do not treat exit-0 as proof of completeness — proof is the\nowner reading `corpus.md` and recognising their own writing. See `references\u002Fmethod.md`.\n","# social-corpus-extraction\n\nTurn a user's own social-media history into a clean, deduplicated **writing corpus** (for style\nanalysis, fine-tuning, or personal archive). Five stdlib-only Python scripts under `scripts\u002F`, each\nmirroring the same three-output shape (`\u003Cowner>_all.txt`, `\u003Cowner>_substantial.txt`, `\u003Cowner>.jsonl`)\nplus a unifier. **Classify structurally, never by language** — the owner's archive may be in any\nlocale, and every locale-dependent heuristic is a bug (see gotcha 4).\n\n## The rails, and which actually carry the owner's WRITING\n\n| Source | Rail | What you get |\n|---|---|---|\n| Discord | DiscordChatExporter JSON | full history — `isolate_discord.py` (reference impl) |\n| Facebook posts + comments | Meta \"Download Your Information\" (JSON, All-time) | full history — `isolate_facebook.py` |\n| Facebook Messenger | same DYI zip, `messages\u002Finbox\u002F` | full history — `isolate_messenger.py` |\n| WhatsApp | **phone-side only** — per-chat \"Export chat\" `_chat.txt`, or the on-device DB | `isolate_whatsapp.py` |\n| WhatsApp via Meta DYI | ❌ **NO message bodies** — account metadata only (gotcha 3) | — |\n| a live MCP rail (`social-hub`) | partial recent window only (Baileys ~4-5 days) | supplements, never replaces the export |\n\nThen `build_corpus.py` folds every per-source `.jsonl` into one deduplicated corpus with a MANIFEST\nthat accounts for every dropped record under a named reason.\n\n## The four traps (each cost real debugging — do not rediscover)\n\n1. **Meta DYI mojibake is double-encoded UTF-8, and the naive fix silently corrupts.**\n   Meta emits `Ä`+U+0083 where `ă` belongs. `s.encode('latin-1').decode('utf-8')` is the correct\n   *inverse* but NOT safe: on an already-clean string with Latin-1-range chars it raises (so a\n   try\u002Fexcept returns it UNREPAIRED and silent); on a mixed string with any char > U+00FF it raises\n   too. **Gate the repair on a detector** (a UTF-8-run regex) and run it **after `json.loads`** —\n   Meta double-escapes ASCII metacharacters too (`\"`→bare `\"`), so raw-byte repair yields\n   JSONDecodeError. NEVER apply it to client-written UTF-8 (Discord, WhatsApp `_chat.txt`) — it\n   CREATES corruption. `build_corpus.py` applies repair only to facebook\u002Fmessenger sources.\n\n2. **The Facebook post path drifted ≥4×**: `posts\u002Fyour_posts.json` → `posts\u002Fyour_posts_1.json` →\n   `your_facebook_activity\u002Fposts\u002Fyour_posts__check_ins__photos_and_videos_1.json` →\n   `your_activity_across_facebook\u002F...`. A pipeline pinned to one path finds **zero** posts in a\n   2024+ archive. `isolate_facebook.py` globs all known roots and exits non-zero (naming the file)\n   on an unrecognised schema — never silently emits empty.\n\n3. **WhatsApp DYI export contains NO message text** (WhatsApp Help Center, verbatim; E2EE means Meta\n   has no plaintext). The owner's WhatsApp history is obtainable ONLY client-side: iPhone → device\n   backup → `ChatStorage.sqlite`; Android → 64-digit-key backup → `crypt15` → `wa-crypt-tools`; or\n   in-app per-chat \"Export chat\" `_chat.txt` (manual, most-recent-N). `isolate_whatsapp.py` reads\n   the `_chat.txt` \u002F DB-JSON, never the DYI zip.\n\n4. **Classify structurally, not by locale keyword.** Meta's auto-generated `title`\u002Fnotification\n   strings are localized; an English regex silently misclassifies a non-English archive. Key on JSON\n   structure + prose length. The min-length floor is the single most load-bearing,\n   language-independent predicate (it removed 99.1% of posts-on-others'-timelines in the reference run).\n\n## Usage\n\n```\npython scripts\u002Fisolate_facebook.py  --owner-name \"Full Name\" --owner-name \"alt spelling\"   # DYI zip\u002Fdir in .\u002FFacebook\npython scripts\u002Fisolate_messenger.py --root .\u002FFacebook --me \"Full Name\"\npython scripts\u002Fisolate_whatsapp.py  \u003Cpath-to-_chat.txt-or-db.json> --owner-name \"\u003Cdisplay name>\"\npython scripts\u002Fbuild_corpus.py       # auto-discovers every per-source .jsonl, writes corpus\u002F{corpus.jsonl,corpus.md,MANIFEST.md}\n```\nEvery script is **stdlib-only, Windows\u002FUnix, streams per-file** (never `json.load` a multi-GB export\nwhole). Owner identity is argv\u002Fenv — no identity is hardcoded. Exit 4 from `isolate_facebook.py` =\nan unrecognised schema; the corpus is INCOMPLETE — read the printed filename, extend the glob.\n\n## Honest limits\n\nFixture-green does NOT prove real-archive-correct — the fixtures encode our assumptions about a Meta\nexport that had not yet arrived when these were written. Treat the first real run as an experiment:\nread `MANIFEST.md`'s drop accounting, and do not treat exit-0 as proof of completeness — proof is the\nowner reading `corpus.md` and recognising their own writing. See `references\u002Fmethod.md`.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fsocial-corpus-extraction","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill social-corpus-extraction",{"tool":66,"command":67},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill social-corpus-extraction",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill social-corpus-extraction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002FSKILL.md",true,[74,80,86,92,96,100,104,108,112],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"assets\u002Ftemplate.tsx","ASSET","资产文件",3252,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Freact-flow-node-ts\u002Fassets\u002Ftemplate.tsx",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"assets\u002Ftypes.template.ts","SCRIPT","脚本",847,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Freact-flow-node-ts\u002Fassets\u002Ftypes.template.ts",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Facceptance-criteria.md","REFERENCE","参考文档",8893,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Freact-flow-node-ts\u002Freferences\u002Facceptance-criteria.md",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fmethod.md",2664,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Freferences\u002Fmethod.md",{"path":97,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fbuild_corpus.py",71377,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Fscripts\u002Fbuild_corpus.py",{"path":101,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fisolate_discord.py",4173,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Fscripts\u002Fisolate_discord.py",{"path":105,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fisolate_facebook.py",54824,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Fscripts\u002Fisolate_facebook.py",{"path":109,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fisolate_messenger.py",57958,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Fscripts\u002Fisolate_messenger.py",{"path":113,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Fisolate_whatsapp.py",62838,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsocial-corpus-extraction\u002Fscripts\u002Fisolate_whatsapp.py",[117,138,167,194,208,224],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":49},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[124,125,126,127,128,129,130,131,132,39,133,134,135,136,137],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":49},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[148,149,150,151,152,153,154,155,156,157,158,159,160,161,39,162,163,164,165,166],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":179,"publishedAt":49},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[173,176],{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[180,181,182,183,184,185,186,187,188,189,149,190,191,192,193],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":49},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[196,201,202,203,204,205,206,207],"setup","report","project","installation","project setup","issues","state",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":215,"publishedAt":49},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[214],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},[210,216,129,217,218,219,39,220,221,222,223],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":225,"name":201,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":229,"publishedAt":49},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[201,203,164,230,205,231],"files","interactive"]