[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBDXMA1JSGFHASXHT1S3MN":3,"skill-same:01M6DBDXMA1JSGFHASXHT1S3MN":70},{"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":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DBDXMA1JSGFHASXHT1S3MN","gem-hunt",null,"Use when the user wants to DISCOVER high-value improvements to their OWN agentic workspace\u002Ftoolkit - new hooks, behaviors, gems, skills, MCPs, or frontier-harness patterns - via a wide multi-lens agent fan-out, then a consolidated adopt\u002Fprune decision. The named \"agentic-perfection sweep\" \u002F \"extensive gem search\". Triggers: \"find more gems\", \"what are we missing vs other tools\".","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\u002F.agents\u002Fskills\u002Fgem-hunt\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"gem hunt","gem","hunt","user","triggers","adopt","discover","patterns","hooks","use","agentic","find","workspace","decision","sweep","prune","Tools","search","harness","toolkit","2026-11-10 10:12:30",false,"---\nname: gem-hunt\ndescription: \"Use when the user wants to DISCOVER high-value improvements to their OWN agentic workspace\u002Ftoolkit - new hooks, behaviors, gems, skills, MCPs, or frontier-harness patterns - via a wide multi-lens agent fan-out, then a consolidated adopt\u002Fprune decision. The named \\\"agentic-perfection sweep\\\" \u002F \\\"extensive gem search\\\". Triggers: \\\"find more gems\\\", \\\"what are we missing vs other tools\\\".\"\n---\n\n# Gem-Hunt — extensive multi-lens workspace self-improvement sweep\n\nThe repeatable form of the process that produced the agentic-perfection gems (open-loops,\ncontraindication-registry, iatrogenics-gate, the closed self-improvement loop, ACE, …).\nRe-run it whenever the landscape moves (new papers, new tools, new domains) — the lenses\nand discipline below are the winning formula; only the findings change.\n\n**Core philosophy (the user's standing intent):** fan out **LARGE** and wide — *\"there's no\nreason to limit the search; a gold gem unfound is a waste.\"* Breadth-first across diverse,\nindependent lenses beats one deep pass, because the best finds come from angles you wouldn't\nhave prompted for. Be adversarially honest, cite, grade confidence, and converge to a\ndecision the user steers — never silently adopt.\n\n## The method (7 steps)\n\n1. **GROUND — build the dedup-set first.** Read the live workspace state (hooks in\n   `~\u002F.claude\u002Fhooks` + `settings.json`, skills, `~\u002F.mcp.json`, `MEMORY.md`, the\n   `AGENTIC-PERFECTION-PLAN.md` \u002F `OPEN-THREADS.md` \u002F `CONSOLIDATED-GEM-DECISIONS.md` docs)\n   and recall memory. Assemble the explicit lists: **BUILT · PLANNED-unbuilt · ABSORBED ·\n   ALREADY-FOUND-this-hunt**. Every lens agent gets this set so it dedups instead of\n   re-proposing what exists. Without it, 80% of finds are duplicates.\n\n2. **FAN OUT — one agent per DISTINCT lens** (the menu that works; pick\u002Fscale to the ask,\n   default 6-9, go to 15-20+ for \"be exhaustive\"):\n   - **cross-domain borrows** — mechanisms from unmined fields (clinical medicine, intel\n     tradecraft, economics\u002Fmechanism-design, control theory, law\u002Fevidence, neuroscience).\n     *Historically the highest-yield lens* (iatrogenics-gate, contraindication-registry, ACH).\n   - **frontier-harness** — latest agent-reliability\u002Fmemory\u002Forchestration papers + repos\n     (arXiv + GitHub): ACE, MaAS, Agent-as-a-Judge, GEPA, G-Memory, etc.\n   - **competitive-teardown** — what the best harnesses (Cursor\u002FDevin\u002FCline\u002FOpenHands\u002FAider\u002F\n     Goose\u002FAmp\u002FCodex\u002FWindsurf\u002FZed\u002FJunie) have that we lack; **tag NATIVE-vs-BUILD**.\n   - **native-capability audit** — what *our own tool* (Claude Code + Agent SDK) natively\n     supports but we under-use (so we ENABLE, not BUILD). Load-bearing; do it every time.\n   - **user-domain tools** — domain-specific gems for the user's actual work (here:\n     RE\u002Fsecurity, media\u002Fvideo, drug-discovery, BC-modding).\n   - **meta** — the next self-improvement level (auto-gem-mining, capability-score, the\n     closed failure→gem→verify→retire loop).\n   - **prune\u002Forganize** — leanness: redundant hooks\u002Fskills\u002FMCPs, latency, memory-layer\n     consolidation. (A gem-hunt that only ADDS is a bloat engine — always prune too.)\n   - **skills-in-wild · MCPs-in-wild** — high-value OSS skills\u002FMCP servers to adopt.\n   - **wildcard\u002Fgold-gem** — one agent told to find the genuinely novel cross-field thing.\n\n3. **DON'T LET THEM DIE.** Transient API errors (429\u002F529\u002Fsocket-close) kill agents\n   mid-run, especially in big fan-outs. The work usually persists in the transcript.\n   **Resume from partial via SendMessage** (force synthesis from what they have) — recover,\n   don't redo ([[feedback_workflow_orchestration]]). Watch for write-freeze >25min with\n   quiet children = real stall → TaskStop + recover.\n\n4. **SYNTHESIZE.** Dedup across lenses; **note cross-lens convergence** (a find surfaced by\n   two independent lenses is highest-confidence — e.g. ACH appeared in cross-domain AND\n   wildcard). Roll up into a **tiered consolidated decision-queue**: TIER-0 just-do-it\n   (reversible) · top-gems · strong-techniques · tooling · planned-unbuilt · skip · with a\n   per-item REC and value×effort tag.\n\n5. **VERIFY before acting (peer-review).** Subagent findings are claims, not truth. Before\n   adopting, verify the load-bearing factual claims against the real config\u002Fcode — a prune\n   audit once called a file \"safe to delete\" that the router actually referenced. Cross-model\n   review for big calls ([[feedback_peer_review]]).\n\n6. **DECIDE.** Present the decision-queue + a low-fatigue `AskUserQuestion` steer (recognition\n   over recall). Write the queue to a **durable doc** (`CONSOLIDATED-GEM-DECISIONS.md`) so it\n   survives compaction and is the audit trail + input to the build phase. A gem-hunt is\n   discovery, not a build — don't implement mid-hunt.\n\n7. **CAPTURE.** Version adopted gems + this process's learnings to the agent-skills-toolchain\n   repo and write durable memory notes, so the next hunt starts from a richer dedup-set.\n\n## The anti-overfit meta-anchor (gate every adopt decision)\n\nMinimal architecture is deliberate (mini-SWE-agent: a 100-line bash loop scores 74% on\nSWE-bench — elaborate scaffolding *overfits* as models improve). A find only counts if it\n**(a) rides the existing hook\u002Fskill\u002FMCP bus**, and **(b) does NOT reintroduce a rejected\ncomponent** (2nd orchestration runtime, vector-DB\u002FKG memory, durable-execution engine,\ntrained critic, observability SaaS, guardrail framework, OpenRouter MCP, LiteLLM,\nCursor BYOK, LangGraph, duplicate Sentry). OpenRouter stays a spend-capped CLI\u002FCodex\nsidecar (`openrouter-routing`); fold T0\u002FT1 there, never as a new MCP. Prefer \"enable a native feature\"\nand \"fold into the existing dispatcher\" over \"new hook file \u002F new MCP.\"\n\n## Hard-won lessons (do these, they cost real reruns to learn)\n\n- **Loose schema or plain-text agents, not strict StructuredOutput.** Broad\u002Fdeep lenses\n  produce long, shape-varying output that fails strict schemas and burns the retry-cap.\n  Use a single `findings_markdown` string field, or plain-text agents.\n- **Fan out LARGE** (the user wants 50-100 on \"be exhaustive\"); each lens blind to the\n  others is a feature (independent coverage).\n- **Per-find rubric:** name \u002F what \u002F why-THIS-user(-domain) \u002F how-to-build-or-adopt \u002F\n  source(cite) \u002F value×effort \u002F novelty(-for-us) \u002F NATIVE-vs-BUILD tag.\n- **Cite + grade confidence;** flag post-cutoff\u002Fsecondary-source items as lower-confidence.\n- **Workflow vs Agents:** a `Workflow` (pipeline\u002Fparallel) is cleanest for a fixed lens set;\n  parallel `Agent` calls are fine and easier to resume individually when one dies.\n\n## Deliverable\n\nA consolidated, tiered adopt\u002Fprune **decision-queue doc** + a steering `AskUserQuestion`,\nfrom which the user picks the build wave. Related: [[grill-me-extensive]] (interrogate one\nplan), `deep-research` (single-topic). This skill is the *discovery+decide* front-end to the\nagentic-perfection program.\n","# Gem-Hunt — extensive multi-lens workspace self-improvement sweep\n\nThe repeatable form of the process that produced the agentic-perfection gems (open-loops,\ncontraindication-registry, iatrogenics-gate, the closed self-improvement loop, ACE, …).\nRe-run it whenever the landscape moves (new papers, new tools, new domains) — the lenses\nand discipline below are the winning formula; only the findings change.\n\n**Core philosophy (the user's standing intent):** fan out **LARGE** and wide — *\"there's no\nreason to limit the search; a gold gem unfound is a waste.\"* Breadth-first across diverse,\nindependent lenses beats one deep pass, because the best finds come from angles you wouldn't\nhave prompted for. Be adversarially honest, cite, grade confidence, and converge to a\ndecision the user steers — never silently adopt.\n\n## The method (7 steps)\n\n1. **GROUND — build the dedup-set first.** Read the live workspace state (hooks in\n   `~\u002F.claude\u002Fhooks` + `settings.json`, skills, `~\u002F.mcp.json`, `MEMORY.md`, the\n   `AGENTIC-PERFECTION-PLAN.md` \u002F `OPEN-THREADS.md` \u002F `CONSOLIDATED-GEM-DECISIONS.md` docs)\n   and recall memory. Assemble the explicit lists: **BUILT · PLANNED-unbuilt · ABSORBED ·\n   ALREADY-FOUND-this-hunt**. Every lens agent gets this set so it dedups instead of\n   re-proposing what exists. Without it, 80% of finds are duplicates.\n\n2. **FAN OUT — one agent per DISTINCT lens** (the menu that works; pick\u002Fscale to the ask,\n   default 6-9, go to 15-20+ for \"be exhaustive\"):\n   - **cross-domain borrows** — mechanisms from unmined fields (clinical medicine, intel\n     tradecraft, economics\u002Fmechanism-design, control theory, law\u002Fevidence, neuroscience).\n     *Historically the highest-yield lens* (iatrogenics-gate, contraindication-registry, ACH).\n   - **frontier-harness** — latest agent-reliability\u002Fmemory\u002Forchestration papers + repos\n     (arXiv + GitHub): ACE, MaAS, Agent-as-a-Judge, GEPA, G-Memory, etc.\n   - **competitive-teardown** — what the best harnesses (Cursor\u002FDevin\u002FCline\u002FOpenHands\u002FAider\u002F\n     Goose\u002FAmp\u002FCodex\u002FWindsurf\u002FZed\u002FJunie) have that we lack; **tag NATIVE-vs-BUILD**.\n   - **native-capability audit** — what *our own tool* (Claude Code + Agent SDK) natively\n     supports but we under-use (so we ENABLE, not BUILD). Load-bearing; do it every time.\n   - **user-domain tools** — domain-specific gems for the user's actual work (here:\n     RE\u002Fsecurity, media\u002Fvideo, drug-discovery, BC-modding).\n   - **meta** — the next self-improvement level (auto-gem-mining, capability-score, the\n     closed failure→gem→verify→retire loop).\n   - **prune\u002Forganize** — leanness: redundant hooks\u002Fskills\u002FMCPs, latency, memory-layer\n     consolidation. (A gem-hunt that only ADDS is a bloat engine — always prune too.)\n   - **skills-in-wild · MCPs-in-wild** — high-value OSS skills\u002FMCP servers to adopt.\n   - **wildcard\u002Fgold-gem** — one agent told to find the genuinely novel cross-field thing.\n\n3. **DON'T LET THEM DIE.** Transient API errors (429\u002F529\u002Fsocket-close) kill agents\n   mid-run, especially in big fan-outs. The work usually persists in the transcript.\n   **Resume from partial via SendMessage** (force synthesis from what they have) — recover,\n   don't redo ([[feedback_workflow_orchestration]]). Watch for write-freeze >25min with\n   quiet children = real stall → TaskStop + recover.\n\n4. **SYNTHESIZE.** Dedup across lenses; **note cross-lens convergence** (a find surfaced by\n   two independent lenses is highest-confidence — e.g. ACH appeared in cross-domain AND\n   wildcard). Roll up into a **tiered consolidated decision-queue**: TIER-0 just-do-it\n   (reversible) · top-gems · strong-techniques · tooling · planned-unbuilt · skip · with a\n   per-item REC and value×effort tag.\n\n5. **VERIFY before acting (peer-review).** Subagent findings are claims, not truth. Before\n   adopting, verify the load-bearing factual claims against the real config\u002Fcode — a prune\n   audit once called a file \"safe to delete\" that the router actually referenced. Cross-model\n   review for big calls ([[feedback_peer_review]]).\n\n6. **DECIDE.** Present the decision-queue + a low-fatigue `AskUserQuestion` steer (recognition\n   over recall). Write the queue to a **durable doc** (`CONSOLIDATED-GEM-DECISIONS.md`) so it\n   survives compaction and is the audit trail + input to the build phase. A gem-hunt is\n   discovery, not a build — don't implement mid-hunt.\n\n7. **CAPTURE.** Version adopted gems + this process's learnings to the agent-skills-toolchain\n   repo and write durable memory notes, so the next hunt starts from a richer dedup-set.\n\n## The anti-overfit meta-anchor (gate every adopt decision)\n\nMinimal architecture is deliberate (mini-SWE-agent: a 100-line bash loop scores 74% on\nSWE-bench — elaborate scaffolding *overfits* as models improve). A find only counts if it\n**(a) rides the existing hook\u002Fskill\u002FMCP bus**, and **(b) does NOT reintroduce a rejected\ncomponent** (2nd orchestration runtime, vector-DB\u002FKG memory, durable-execution engine,\ntrained critic, observability SaaS, guardrail framework, OpenRouter MCP, LiteLLM,\nCursor BYOK, LangGraph, duplicate Sentry). OpenRouter stays a spend-capped CLI\u002FCodex\nsidecar (`openrouter-routing`); fold T0\u002FT1 there, never as a new MCP. Prefer \"enable a native feature\"\nand \"fold into the existing dispatcher\" over \"new hook file \u002F new MCP.\"\n\n## Hard-won lessons (do these, they cost real reruns to learn)\n\n- **Loose schema or plain-text agents, not strict StructuredOutput.** Broad\u002Fdeep lenses\n  produce long, shape-varying output that fails strict schemas and burns the retry-cap.\n  Use a single `findings_markdown` string field, or plain-text agents.\n- **Fan out LARGE** (the user wants 50-100 on \"be exhaustive\"); each lens blind to the\n  others is a feature (independent coverage).\n- **Per-find rubric:** name \u002F what \u002F why-THIS-user(-domain) \u002F how-to-build-or-adopt \u002F\n  source(cite) \u002F value×effort \u002F novelty(-for-us) \u002F NATIVE-vs-BUILD tag.\n- **Cite + grade confidence;** flag post-cutoff\u002Fsecondary-source items as lower-confidence.\n- **Workflow vs Agents:** a `Workflow` (pipeline\u002Fparallel) is cleanest for a fixed lens set;\n  parallel `Agent` calls are fine and easier to resume individually when one dies.\n\n## Deliverable\n\nA consolidated, tiered adopt\u002Fprune **decision-queue doc** + a steering `AskUserQuestion`,\nfrom which the user picks the build wave. Related: [[grill-me-extensive]] (interrogate one\nplan), `deep-research` (single-topic). This skill is the *discovery+decide* front-end to the\nagentic-perfection program.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fgem-hunt","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill gem-hunt",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill gem-hunt",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill gem-hunt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgem-hunt\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"SKILL.sm","OTHER","其他",276,"https:\u002F\u002Fgithub.com\u002Fcrystian\u002Fskill-map\u002Fblob\u002Fmain\u002Ffixtures\u002Fclaude\u002F.claude\u002Fskills\u002Fcheck-links\u002FSKILL.sm",[71,92,122,149,163,178],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":39},"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",[],[78,79,80,81,82,83,84,85,86,28,87,88,89,90,91],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":39},"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",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[104,105,32,106,107,108,109,110,111,112,113,114,115,116,28,117,118,119,120,121],"openmm md","how","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":134,"publishedAt":39},"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",[128,131],{"categoryNo":129,"categoryName":130,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":132,"categoryName":133,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000008","测试与质量",[135,136,137,138,139,140,141,142,143,144,105,145,146,147,148],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":39},"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",[],[151,156,157,158,159,160,161,162],"setup","report","project","installation","project setup","issues","state",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":39},"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",[169],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[165,171,83,172,173,174,28,22,175,176,177],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":179,"name":156,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":39},"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",[],[156,158,119,184,160,185],"files","interactive"]