[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBZ2TG69JMTPDMQZK9W2AE":3,"skill-same:01M6DBZ2TG69JMTPDMQZK9W2AE":57},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DBZ2TG69JMTPDMQZK9W2AE","source-command-prime",null,"Load relevant knowledge base facts into context before starting work","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\u002Fsource-command-prime\u002FSKILL.md",[],[19,20,21,22,23,24,25],"command","source command prime","knowledge","work","context","base","knowledge base","2026-11-10 10:12:30",false,"---\nname: \"source-command-prime\"\ndescription: \"Load relevant knowledge base facts into context before starting work\"\n---\n\n# source-command-prime\n\nUse this skill when the user asks to run the migrated source command `prime`.\n\n## Command Template\n\n# BEADS Prime\n\n**CRITICAL**: Run this command at the START of any investigation, planning, or implementation work to load relevant knowledge into your context.\n\n## When to Use\n\n- Starting work on a GitHub Issue\n- Beginning investigation\u002Fresearch\n- Before writing a plan\n- Before implementing changes\n- When switching to a new area of the codebase\n\n## How It Works\n\nThis command queries the BEADS knowledge base for facts relevant to your current context and injects them into the conversation, ensuring you:\n\n1. Follow established patterns and rules\n2. Avoid known gotchas and pitfalls\n3. Make decisions aligned with architectural choices\n4. Don't repeat mistakes that have been learned from\n\n## Usage\n\n### Quick Prime (Most Common)\n\nFor general context with automatic detection:\n\n```bash\nbd prime\n```\n\n### Prime for Specific Files\n\nWhen working on specific files:\n\n```bash\nbd prime --files \"src\u002Flib\u002Fservices\u002F**\u002F*.ts\" \"src\u002Fapi\u002Froutes\u002F**\u002F*.ts\"\n```\n\n### Prime for Keywords\n\nWhen working on a specific topic:\n\n```bash\nbd prime --keywords \"authentication\" \"jwt\" \"security\"\n```\n\n### Prime for Work Type\n\nWhen doing a specific type of work:\n\n```bash\nbd prime --work-type planning\nbd prime --work-type implementation\nbd prime --work-type review\nbd prime --work-type debugging\n```\n\n### Prime for Context Recovery\n\nWhen resuming after context compaction or in a new session:\n\n```bash\nbd prime --work-type recovery\n```\n\nThis loads active plan, project context, execution state, and relevant knowledge base facts. See \"Context Recovery\" section below.\n\n### Combined\n\n```bash\nbd prime \\\n  --files \"src\u002Flib\u002Fservices\u002Fai-*.ts\" \\\n  --keywords \"ai\" \"provider\" \"openai\" \\\n  --work-type implementation\n```\n\n## What Gets Loaded\n\n### 1. MUST FOLLOW (Critical Rules)\n\nNon-negotiable rules containing NEVER\u002FALWAYS\u002FMUST:\n\n- \"NEVER use `as any` type casting\"\n- \"ALWAYS use centralized AI config\"\n- Security-critical patterns\n\n### 2. GOTCHAS (Common Pitfalls)\n\nKnown issues to avoid:\n\n- \"Truthy check fails for explicit zero values - use !== undefined\"\n- API behavior quirks\n\n### 3. PATTERNS (Best Practices)\n\nEstablished patterns in this codebase:\n\n- \"Use mock factories from test utilities\"\n- \"Services should follow TDD (Red-Green-Refactor)\"\n\n### 4. DECISIONS (Architectural Choices)\n\nTeam\u002Farchitectural decisions:\n\n- \"State management uses Zustand + TanStack Query\"\n- \"AI providers implement Strategy Pattern\"\n\n### 5. API BEHAVIORS\n\nExternal API quirks:\n\n- \"Prisma findMany returns [] not null\"\n\n## Auto-Priming\n\nThe BEADS system should auto-prime in these scenarios:\n\n1. **Session Start**: When `.beads\u002F` directory is detected\n2. **File Touch**: When reading\u002Fediting files that match knowledge patterns\n3. **Keyword Detection**: When task description matches known topics\n\n## Integration Points\n\n### In Planning Phase\n\nBefore writing a plan, run:\n\n```bash\nbd prime --work-type planning --keywords \"\u003Ctask-keywords>\"\n```\n\n### In Implementation Phase\n\nBefore writing code, run:\n\n```bash\nbd prime --files \"\u003Cfiles-to-touch>\" --work-type implementation\n```\n\n### In Review Phase\n\nBefore reviewing code, run:\n\n```bash\nbd prime --work-type review --files \"\u003Cfiles-changed>\"\n```\n\n## Manual Knowledge Check\n\nIf you need to check for specific knowledge:\n\n```bash\n# Search for specific topic\ncat .beads\u002Fknowledge\u002F*.jsonl | jq -r 'select(.fact | test(\"authentication\"; \"i\")) | .fact'\n\n# Get all gotchas\ncat .beads\u002Fknowledge\u002Fgotchas.jsonl | jq -r '.fact'\n\n# Get all patterns\ncat .beads\u002Fknowledge\u002Fpatterns.jsonl | jq -r '.fact'\n```\n\n## Output Format\n\nThe prime command outputs formatted knowledge that looks like:\n\n```markdown\n# Relevant Knowledge Base Facts\n\n_25 facts loaded for this context_\n\n## MUST FOLLOW (Critical Rules)\n\nThese are non-negotiable rules:\n\n- **[pattern]** NEVER use `as any` type casting...\n- **[security]** Always validate JWT tokens server-side...\n\n## GOTCHAS (Common Pitfalls)\n\nAvoid these known issues:\n\n- **[gotcha]** Truthy check fails for explicit zero values...\n\n## PATTERNS (Best Practices)\n\n- **[pattern]** Use mock factories from test utilities...\n```\n\n## Context Recovery\n\nWhen `--work-type recovery` is used (or when an orchestrator detects it lost context), the prime command loads additional context beyond the standard knowledge base:\n\n### What Gets Loaded\n\n1. **Active Plan** — reads `.beads\u002Fplans\u002Factive-plan.md` if it exists with `status: in-progress`\n2. **Project Context** — reads `.beads\u002Fcontext\u002Fproject-context.md` (completed work units, established patterns, tooling)\n3. **Execution State** — reads `.beads\u002Fcontext\u002Fexecution-state.md` (current work unit, phase, retry count)\n4. **Standard Knowledge** — all the usual MUST FOLLOW, GOTCHAS, PATTERNS, DECISIONS facts\n\n### Recovery Flow\n\n```bash\n# 1. Check for active execution\nif [ -f .beads\u002Fplans\u002Factive-plan.md ]; then\n  grep -q 'status: in-progress' .beads\u002Fplans\u002Factive-plan.md && echo \"ACTIVE PLAN FOUND\"\nfi\n\n# 2. Load all context files\ncat .beads\u002Fplans\u002Factive-plan.md           # The approved plan\ncat .beads\u002Fcontext\u002Fproject-context.md     # Completed work, patterns\ncat .beads\u002Fcontext\u002Fexecution-state.md     # Where we left off\n\n# 3. Load relevant knowledge base facts\ncat .beads\u002Fknowledge\u002F*.jsonl | jq -r '.fact'\n```\n\n### When Recovery Triggers Automatically\n\n- Orchestrated execution starts and finds `.beads\u002Fplans\u002Factive-plan.md` with `status: in-progress` but has no plan in its current context\n- A new session begins with `bd prime` and active execution state is detected\n- After context compaction, when the agent recognizes it has lost plan\u002Fexecution context\n\n### Output Format (Recovery Mode)\n\n```markdown\n# Context Recovery\n\n_Recovered from BEADS persisted state_\n\n## Active Plan\n\u003Cplan summary — title, work unit count, current position>\n\n## Execution State\n- Current work unit: WU-\u003Cid> (\u003Ctitle>)\n- Phase: \u003CIMPLEMENT|VALIDATE|REVIEW|COMMIT>\n- Completed: \u003CN> of \u003Ctotal> work units\n\n## Project Context\n\u003Ctooling, completed work units, established patterns>\n\n## Relevant Knowledge\n\u003Cstandard priming output: MUST FOLLOW, GOTCHAS, PATTERNS, DECISIONS>\n```\n\n## Verification\n\nAfter priming, you should be able to answer:\n\n1. What are the critical rules I must follow?\n2. What gotchas should I watch out for?\n3. What patterns should I apply?\n4. What architectural decisions constrain my options?\n5. (If recovery mode) Where did execution stop and what comes next?\n","# source-command-prime\n\nUse this skill when the user asks to run the migrated source command `prime`.\n\n## Command Template\n\n# BEADS Prime\n\n**CRITICAL**: Run this command at the START of any investigation, planning, or implementation work to load relevant knowledge into your context.\n\n## When to Use\n\n- Starting work on a GitHub Issue\n- Beginning investigation\u002Fresearch\n- Before writing a plan\n- Before implementing changes\n- When switching to a new area of the codebase\n\n## How It Works\n\nThis command queries the BEADS knowledge base for facts relevant to your current context and injects them into the conversation, ensuring you:\n\n1. Follow established patterns and rules\n2. Avoid known gotchas and pitfalls\n3. Make decisions aligned with architectural choices\n4. Don't repeat mistakes that have been learned from\n\n## Usage\n\n### Quick Prime (Most Common)\n\nFor general context with automatic detection:\n\n```bash\nbd prime\n```\n\n### Prime for Specific Files\n\nWhen working on specific files:\n\n```bash\nbd prime --files \"src\u002Flib\u002Fservices\u002F**\u002F*.ts\" \"src\u002Fapi\u002Froutes\u002F**\u002F*.ts\"\n```\n\n### Prime for Keywords\n\nWhen working on a specific topic:\n\n```bash\nbd prime --keywords \"authentication\" \"jwt\" \"security\"\n```\n\n### Prime for Work Type\n\nWhen doing a specific type of work:\n\n```bash\nbd prime --work-type planning\nbd prime --work-type implementation\nbd prime --work-type review\nbd prime --work-type debugging\n```\n\n### Prime for Context Recovery\n\nWhen resuming after context compaction or in a new session:\n\n```bash\nbd prime --work-type recovery\n```\n\nThis loads active plan, project context, execution state, and relevant knowledge base facts. See \"Context Recovery\" section below.\n\n### Combined\n\n```bash\nbd prime \\\n  --files \"src\u002Flib\u002Fservices\u002Fai-*.ts\" \\\n  --keywords \"ai\" \"provider\" \"openai\" \\\n  --work-type implementation\n```\n\n## What Gets Loaded\n\n### 1. MUST FOLLOW (Critical Rules)\n\nNon-negotiable rules containing NEVER\u002FALWAYS\u002FMUST:\n\n- \"NEVER use `as any` type casting\"\n- \"ALWAYS use centralized AI config\"\n- Security-critical patterns\n\n### 2. GOTCHAS (Common Pitfalls)\n\nKnown issues to avoid:\n\n- \"Truthy check fails for explicit zero values - use !== undefined\"\n- API behavior quirks\n\n### 3. PATTERNS (Best Practices)\n\nEstablished patterns in this codebase:\n\n- \"Use mock factories from test utilities\"\n- \"Services should follow TDD (Red-Green-Refactor)\"\n\n### 4. DECISIONS (Architectural Choices)\n\nTeam\u002Farchitectural decisions:\n\n- \"State management uses Zustand + TanStack Query\"\n- \"AI providers implement Strategy Pattern\"\n\n### 5. API BEHAVIORS\n\nExternal API quirks:\n\n- \"Prisma findMany returns [] not null\"\n\n## Auto-Priming\n\nThe BEADS system should auto-prime in these scenarios:\n\n1. **Session Start**: When `.beads\u002F` directory is detected\n2. **File Touch**: When reading\u002Fediting files that match knowledge patterns\n3. **Keyword Detection**: When task description matches known topics\n\n## Integration Points\n\n### In Planning Phase\n\nBefore writing a plan, run:\n\n```bash\nbd prime --work-type planning --keywords \"\u003Ctask-keywords>\"\n```\n\n### In Implementation Phase\n\nBefore writing code, run:\n\n```bash\nbd prime --files \"\u003Cfiles-to-touch>\" --work-type implementation\n```\n\n### In Review Phase\n\nBefore reviewing code, run:\n\n```bash\nbd prime --work-type review --files \"\u003Cfiles-changed>\"\n```\n\n## Manual Knowledge Check\n\nIf you need to check for specific knowledge:\n\n```bash\n# Search for specific topic\ncat .beads\u002Fknowledge\u002F*.jsonl | jq -r 'select(.fact | test(\"authentication\"; \"i\")) | .fact'\n\n# Get all gotchas\ncat .beads\u002Fknowledge\u002Fgotchas.jsonl | jq -r '.fact'\n\n# Get all patterns\ncat .beads\u002Fknowledge\u002Fpatterns.jsonl | jq -r '.fact'\n```\n\n## Output Format\n\nThe prime command outputs formatted knowledge that looks like:\n\n```markdown\n# Relevant Knowledge Base Facts\n\n_25 facts loaded for this context_\n\n## MUST FOLLOW (Critical Rules)\n\nThese are non-negotiable rules:\n\n- **[pattern]** NEVER use `as any` type casting...\n- **[security]** Always validate JWT tokens server-side...\n\n## GOTCHAS (Common Pitfalls)\n\nAvoid these known issues:\n\n- **[gotcha]** Truthy check fails for explicit zero values...\n\n## PATTERNS (Best Practices)\n\n- **[pattern]** Use mock factories from test utilities...\n```\n\n## Context Recovery\n\nWhen `--work-type recovery` is used (or when an orchestrator detects it lost context), the prime command loads additional context beyond the standard knowledge base:\n\n### What Gets Loaded\n\n1. **Active Plan** — reads `.beads\u002Fplans\u002Factive-plan.md` if it exists with `status: in-progress`\n2. **Project Context** — reads `.beads\u002Fcontext\u002Fproject-context.md` (completed work units, established patterns, tooling)\n3. **Execution State** — reads `.beads\u002Fcontext\u002Fexecution-state.md` (current work unit, phase, retry count)\n4. **Standard Knowledge** — all the usual MUST FOLLOW, GOTCHAS, PATTERNS, DECISIONS facts\n\n### Recovery Flow\n\n```bash\n# 1. Check for active execution\nif [ -f .beads\u002Fplans\u002Factive-plan.md ]; then\n  grep -q 'status: in-progress' .beads\u002Fplans\u002Factive-plan.md && echo \"ACTIVE PLAN FOUND\"\nfi\n\n# 2. Load all context files\ncat .beads\u002Fplans\u002Factive-plan.md           # The approved plan\ncat .beads\u002Fcontext\u002Fproject-context.md     # Completed work, patterns\ncat .beads\u002Fcontext\u002Fexecution-state.md     # Where we left off\n\n# 3. Load relevant knowledge base facts\ncat .beads\u002Fknowledge\u002F*.jsonl | jq -r '.fact'\n```\n\n### When Recovery Triggers Automatically\n\n- Orchestrated execution starts and finds `.beads\u002Fplans\u002Factive-plan.md` with `status: in-progress` but has no plan in its current context\n- A new session begins with `bd prime` and active execution state is detected\n- After context compaction, when the agent recognizes it has lost plan\u002Fexecution context\n\n### Output Format (Recovery Mode)\n\n```markdown\n# Context Recovery\n\n_Recovered from BEADS persisted state_\n\n## Active Plan\n\u003Cplan summary — title, work unit count, current position>\n\n## Execution State\n- Current work unit: WU-\u003Cid> (\u003Ctitle>)\n- Phase: \u003CIMPLEMENT|VALIDATE|REVIEW|COMMIT>\n- Completed: \u003CN> of \u003Ctotal> work units\n\n## Project Context\n\u003Ctooling, completed work units, established patterns>\n\n## Relevant Knowledge\n\u003Cstandard priming output: MUST FOLLOW, GOTCHAS, PATTERNS, DECISIONS>\n```\n\n## Verification\n\nAfter priming, you should be able to answer:\n\n1. What are the critical rules I must follow?\n2. What gotchas should I watch out for?\n3. What patterns should I apply?\n4. What architectural decisions constrain my options?\n5. (If recovery mode) Where did execution stop and what comes next?\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fsource-command-prime","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-prime",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-prime",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-prime","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsource-command-prime\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Freview-output-template.md","REFERENCE","参考文档",2465,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fhermes\u002Fgithub-code-review\u002Freferences\u002Freview-output-template.md",[58,79,110,137,151,166],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":26},"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",[],[65,66,67,68,69,70,71,72,73,74,23,75,76,77,78],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","repo","injection","execution","file",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":26},"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,94,95,96,97,98,99,100,101,102,103,104,74,105,106,107,108,109],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":122,"publishedAt":26},"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",[116,119],{"categoryNo":117,"categoryName":118,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":120,"categoryName":121,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000008","测试与质量",[123,124,125,126,127,128,129,130,131,132,92,133,134,135,136],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":26},"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",[],[139,144,145,146,147,148,149,150],"setup","report","project","installation","project setup","issues","state",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"publishedAt":26},"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",[157],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[153,159,70,160,161,162,74,163,22,164,165],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":167,"name":144,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":26},"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",[],[144,146,107,172,148,173],"files","interactive"]