[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEP84WS8AG54PQ7J6G7J73":3,"skill-same:01M6DEP84WS8AG54PQ7J6G7J73":134},{"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":23,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6DEP84WS8AG54PQ7J6G7J73","recall-workflow-agent",null,"Use when you need the exact input PROMPT or final OUTPUT of a specific subagent from a past Workflow \u002F ultracode fan-out run - reviewing or recovering what one fanned-out agent (a lens, a verifier, the synthesizer) actually received or returned after the run scrolled off screen or the session compacted. Identify it by a distinctive phrase, the workflow name, or by listing the run's agents.","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\u002Frecall-workflow-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"workflow","recall","recall workflow agent","run","subagent","prompt","session","use","verifier","2026-11-10 10:12:30",false,"---\nname: recall-workflow-agent\ndescription: Use when you need the exact input PROMPT or final OUTPUT of a specific subagent from a past Workflow \u002F ultracode fan-out run - reviewing or recovering what one fanned-out agent (a lens, a verifier, the synthesizer) actually received or returned after the run scrolled off screen or the session compacted. Identify it by a distinctive phrase, the workflow name, or by listing the run's agents.\n---\n\n# recall-workflow-agent\n\n## Overview\nEvery Workflow subagent's full transcript is written to disk as JSONL. To get one agent's prompt + output you locate its `agent-\u003Cid>.jsonl` and read it — you do NOT re-run the workflow or ask the user. **The reliable locator is a distinctive PHRASE, because the readable agent label is not stored on disk.**\n\n## Where it lives\n```\n~\u002F.claude\u002Fprojects\u002F\u003Cproject>\u002F\u003Csession>\u002Fsubagents\u002Fworkflows\u002F\u003Cwf_id>\u002F\n    journal.jsonl          # per agent: {type, key:\u003CHASH>, agentId, result:\u003Cthe OUTPUT>}\n    agent-\u003CagentId>.jsonl  # per agent: full transcript (prompt = its user msg; + turns)\n~\u002F.claude\u002Fprojects\u002F\u003COTHER-project>\u002F\u003Csession>\u002Fworkflows\u002Fscripts\u002F\u003Cname>-\u003Cwf_id>.js   # the script (holds the labels)\n```\n**Gotcha:** the transcript dir is under the SESSION's project, which is frequently a *different* `\u003Cproject>` than where the `.js` script lives. Never assume co-location — a phrase grep finds it wherever it is.\n\n## Do this — the bundled tool locates + extracts + saves the files\n```bash\nS=~\u002F.agents\u002Fskills\u002Frecall-workflow-agent\u002Fscripts\u002Fextract_workflow_agent.py\n# best: a phrase you SAW in the output, or a phrase from the prompt\u002Flens task:\npython \"$S\" --phrase \"Vaporware-filtered maturity table\" --slug decision --print\n# don't know a phrase? list every agent in the run (previewed by its report HEADLINE), then pick:\npython \"$S\" --workflow multiai-orchestration-research --list\n# scope a phrase to one run if it's ambiguous:\npython \"$S\" --workflow \u003Cname> --phrase \"\u003Cdistinctive>\"\n```\nPrompt is saved to `\u003Cslug>-PROMPT.md`, output to `\u003Cslug>-OUTPUT.md`. The tool takes the output from the journal `result` (the authoritative captured return), so it's clean even for tool-using agents.\n\n## Identify by (most→least reliable)\n1. A phrase from the **OUTPUT you saw** in the UI — unique, best.\n2. **`--list`** the workflow's agents (each previewed by its report headline) → pick.\n3. A phrase from the **PROMPT \u002F lens task** — works, but read the synthesizer gotcha below.\n\n## Common mistakes\n- **Grepping the agent label** (`synthesize:multiai-decision`): it is NOT in the transcript or journal — journal stores a hashed `key`; labels live only in the `.js` script. Grep a content phrase instead.\n- **Searching only under the script's project dir** → 0 files. Grep across ALL of `~\u002F.claude\u002Fprojects` (the tool does).\n- **Fanning out the Grep TOOL across `~\u002F.claude\u002Fprojects`:** on Windows it can die with `ENAMETOOLONG` (giant argv over thousands of files). Use the bundled tool (Python glob + line scan) or `rg` via Bash — not the Grep tool.\n- **A lens phrase matching two agents:** a SYNTHESIZER's prompt embeds every upstream agent's report verbatim, so a lens name\u002Ftag hits the lens agent AND the synthesizer. Use a phrase from that lens's OWN narration\u002Foutput, or `--list` and pick by preview. The tool reports every match so you can narrow.\n- **Decoy — your OWN current session's subagents:** Agent-tool subagents live at `subagents\u002Fagent-*.jsonl` (NO `workflows\u002F\u003Cwf_id>\u002F` layer). If your task text quotes the workflow name\u002Fphrase they self-match. The tool's glob requires `...\u002Fsubagents\u002Fworkflows\u002F\u003Cwf_id>\u002Fagent-*.jsonl`, so it excludes them — a manual grep won't.\n- **Treating joined assistant turns as \"the output\":** tool-using agents interleave narration between tool batches. The real output is journal `result` (final return) — what the tool uses.\n- **content is a string OR a list of `{type:text}` blocks** — handle both (the tool does).\n```\n","# recall-workflow-agent\n\n## Overview\nEvery Workflow subagent's full transcript is written to disk as JSONL. To get one agent's prompt + output you locate its `agent-\u003Cid>.jsonl` and read it — you do NOT re-run the workflow or ask the user. **The reliable locator is a distinctive PHRASE, because the readable agent label is not stored on disk.**\n\n## Where it lives\n```\n~\u002F.claude\u002Fprojects\u002F\u003Cproject>\u002F\u003Csession>\u002Fsubagents\u002Fworkflows\u002F\u003Cwf_id>\u002F\n    journal.jsonl          # per agent: {type, key:\u003CHASH>, agentId, result:\u003Cthe OUTPUT>}\n    agent-\u003CagentId>.jsonl  # per agent: full transcript (prompt = its user msg; + turns)\n~\u002F.claude\u002Fprojects\u002F\u003COTHER-project>\u002F\u003Csession>\u002Fworkflows\u002Fscripts\u002F\u003Cname>-\u003Cwf_id>.js   # the script (holds the labels)\n```\n**Gotcha:** the transcript dir is under the SESSION's project, which is frequently a *different* `\u003Cproject>` than where the `.js` script lives. Never assume co-location — a phrase grep finds it wherever it is.\n\n## Do this — the bundled tool locates + extracts + saves the files\n```bash\nS=~\u002F.agents\u002Fskills\u002Frecall-workflow-agent\u002Fscripts\u002Fextract_workflow_agent.py\n# best: a phrase you SAW in the output, or a phrase from the prompt\u002Flens task:\npython \"$S\" --phrase \"Vaporware-filtered maturity table\" --slug decision --print\n# don't know a phrase? list every agent in the run (previewed by its report HEADLINE), then pick:\npython \"$S\" --workflow multiai-orchestration-research --list\n# scope a phrase to one run if it's ambiguous:\npython \"$S\" --workflow \u003Cname> --phrase \"\u003Cdistinctive>\"\n```\nPrompt is saved to `\u003Cslug>-PROMPT.md`, output to `\u003Cslug>-OUTPUT.md`. The tool takes the output from the journal `result` (the authoritative captured return), so it's clean even for tool-using agents.\n\n## Identify by (most→least reliable)\n1. A phrase from the **OUTPUT you saw** in the UI — unique, best.\n2. **`--list`** the workflow's agents (each previewed by its report headline) → pick.\n3. A phrase from the **PROMPT \u002F lens task** — works, but read the synthesizer gotcha below.\n\n## Common mistakes\n- **Grepping the agent label** (`synthesize:multiai-decision`): it is NOT in the transcript or journal — journal stores a hashed `key`; labels live only in the `.js` script. Grep a content phrase instead.\n- **Searching only under the script's project dir** → 0 files. Grep across ALL of `~\u002F.claude\u002Fprojects` (the tool does).\n- **Fanning out the Grep TOOL across `~\u002F.claude\u002Fprojects`:** on Windows it can die with `ENAMETOOLONG` (giant argv over thousands of files). Use the bundled tool (Python glob + line scan) or `rg` via Bash — not the Grep tool.\n- **A lens phrase matching two agents:** a SYNTHESIZER's prompt embeds every upstream agent's report verbatim, so a lens name\u002Ftag hits the lens agent AND the synthesizer. Use a phrase from that lens's OWN narration\u002Foutput, or `--list` and pick by preview. The tool reports every match so you can narrow.\n- **Decoy — your OWN current session's subagents:** Agent-tool subagents live at `subagents\u002Fagent-*.jsonl` (NO `workflows\u002F\u003Cwf_id>\u002F` layer). If your task text quotes the workflow name\u002Fphrase they self-match. The tool's glob requires `...\u002Fsubagents\u002Fworkflows\u002F\u003Cwf_id>\u002Fagent-*.jsonl`, so it excludes them — a manual grep won't.\n- **Treating joined assistant turns as \"the output\":** tool-using agents interleave narration between tool batches. The real output is journal `result` (final return) — what the tool uses.\n- **content is a string OR a list of `{type:text}` blocks** — handle both (the tool does).\n```\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Frecall-workflow-agent","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill recall-workflow-agent",{"tool":50,"command":51},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill recall-workflow-agent",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill recall-workflow-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frecall-workflow-agent\u002FSKILL.md",true,[58,64,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Fextract_workflow_agent.py","SCRIPT","脚本",8190,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frecall-workflow-agent\u002Fscripts\u002Fextract_workflow_agent.py",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"steps\u002Fstep-01-init.md","REFERENCE","参考文档",5785,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-01-init.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"steps\u002Fstep-01b-continue.md",4862,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-01b-continue.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"steps\u002Fstep-02-discovery.md",6761,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-02-discovery.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"steps\u002Fstep-03-core-experience.md",8208,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-03-core-experience.md",{"path":83,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":84,"sourceHtmlUrl":85},"steps\u002Fstep-04-emotional-response.md",8247,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-04-emotional-response.md",{"path":87,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":88,"sourceHtmlUrl":89},"steps\u002Fstep-05-inspiration.md",8649,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-05-inspiration.md",{"path":91,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":92,"sourceHtmlUrl":93},"steps\u002Fstep-06-design-system.md",8749,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-06-design-system.md",{"path":95,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":96,"sourceHtmlUrl":97},"steps\u002Fstep-07-defining-experience.md",8751,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-07-defining-experience.md",{"path":99,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":100,"sourceHtmlUrl":101},"steps\u002Fstep-08-visual-foundation.md",8351,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-08-visual-foundation.md",{"path":103,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":104,"sourceHtmlUrl":105},"steps\u002Fstep-09-design-directions.md",8536,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-09-design-directions.md",{"path":107,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":108,"sourceHtmlUrl":109},"steps\u002Fstep-10-user-journeys.md",8367,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-10-user-journeys.md",{"path":111,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":112,"sourceHtmlUrl":113},"steps\u002Fstep-11-component-strategy.md",8660,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-11-component-strategy.md",{"path":115,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":116,"sourceHtmlUrl":117},"steps\u002Fstep-12-ux-patterns.md",7912,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-12-ux-patterns.md",{"path":119,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":120,"sourceHtmlUrl":121},"steps\u002Fstep-13-responsive-accessibility.md",9012,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-13-responsive-accessibility.md",{"path":123,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":124,"sourceHtmlUrl":125},"steps\u002Fstep-14-complete.md",6834,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-14-complete.md",{"path":127,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":128,"sourceHtmlUrl":129},"ux-design-template.md",236,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fux-design-template.md",{"path":131,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":132,"sourceHtmlUrl":133},"workflow.md",1400,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-ux-design\u002Fworkflow.md",[135,156,182,209,223,239],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":33},"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",[],[142,143,144,145,146,147,148,149,150,31,151,152,153,154,155],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":33},"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",[162],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[164,165,166,167,168,169,170,171,172,173,174,175,24,176,31,177,178,179,180,181],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","windows","free","molecular dynamics","local","do","MCP",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":194,"publishedAt":33},"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",[188,191],{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[195,196,197,198,199,200,201,202,203,204,165,205,206,207,208],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":215,"publishedAt":33},"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",[],[211,216,217,218,219,220,221,222],"setup","report","project","installation","project setup","issues","state",{"skillNo":224,"name":225,"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":230,"publishedAt":33},"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",[229],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[225,231,147,232,233,234,31,235,236,237,238],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":240,"name":216,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":33},"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",[],[216,218,179,245,220,246],"files","interactive"]