[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H7ZGC2WK8SEKYHWDNTMDA9":3,"skill-same:01M6H7ZGC2WK8SEKYHWDNTMDA9":61},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner",null,"[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"swarm","planner","swarm planner","execution","multi-agent","parallel","only","dependency","implementation","plans","multi","for","2026-11-10 10:12:30",false,"---\nname: swarm-planner\ndescription: >\n  [EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel\n  multi-agent execution.\nmetadata:\n  invocation: explicit-only\n---\n\n# Swarm-Ready Planner\n\nCreate implementation plans with explicit task dependencies optimized for parallel agent execution. This skill can be ran inside or outside of Plan Mode. \n\n## Core Principles\n\n1. **Explore Codebase**: Investigate architecture, patterns, existing implementations, dependencies, and frameworks in use.\n2. **Fresh Documentation First**: Use Context7 for ANY external library, framework, or API before planning tasks\n3. **Ask Questions**: Clarify ambiguities and seek clarification on scope, constraints, or priorities throughout the planning process. At any time.\n4. **Explicit Dependencies**: Every task declares what it depends on, enabling maximum parallelization\n5. **Atomic Tasks**: Each task is independently executable by a single agent\n6. **Review Before Yield**: A subagent reviews the plan for gaps before finalizing\n\n## Process\n\n### 1. Research\n\n**Codebase investigation:**\n- Architecture, patterns, existing implementations\n- Dependencies and frameworks in use\n\n### 1a. Optional: Stop to Clarification Questions\n\n- If the architecture is unclear or missing STOP AND YIELD to the user, and request user input (AskUserQuestions) before moving on. Always offer recommendations for clarification questions.\n- If architecture is present, skip 1a and move onto next step. \n\n### 2. Documentation\n\n**Documentation retrieval (REQUIRED for external dependencies):**\n\nUse Context7 skill or MCP to fetch current docs for any libraries\u002Fframeworks or APIs that are or will be used in project. If Context7 is not available, use web search.\n\nThis ensures version-accurate APIs, correct parameters, and current best practices.\n\n### 3. STOP and Request User Input\n\nWhen anything is unclear or could reasonably be done multiple ways:\n- Stop and ask clarifying questions immediately\n- Do not make assumptions about scope, constraints, or priorities\n- Questions should reduce risk and eliminate ambiguity\n- Always offer recommendations for clarification questions.\n- Use request_user_input or AskUserQuestion tool if available. \n\n### 4. Create Dependency-Aware Plan\n\nStructure the plan with explicit task dependencies using this format:\n\n#### Task Dependency Format\n\nEach task MUST include:\n- **id**: Unique identifier (e.g., `T1`, `T2.1`)\n- **depends_on**: Array of task IDs that must complete first (empty `[]` for root tasks)\n- **description**: What the task accomplishes\n- **location**: File paths involved\n- **validation**: acceptance criteria\n\n**Example:**\n```\nT1: [depends_on: []] Create database schema migration\nT2: [depends_on: []] Install required packages\nT3: [depends_on: [T1]] Create repository layer\nT4: [depends_on: [T1]] Create service interfaces\nT5: [depends_on: [T3, T4]] Implement business logic\nT6: [depends_on: [T2, T5]] Add API endpoints\nT7: [depends_on: [T6]] Write integration tests\n```\n\nTasks with empty\u002Fsatisfied dependencies can run in parallel (T1, T2 above).\n\n### 4. Save Plan\n\nSave to `\u003Ctopic>-plan.md` in the CWD.\n\n### 5. Subagent Review\n\nAfter saving, spawn a subagent to review the plan:\n\n```\nReview this implementation plan for:\n1. Missing dependencies between tasks\n2. Ordering issues that would cause failures\n3. Missing error handling or edge cases\n4. Gaps, holes, gotchas.\n\nProvide specific, actionable feedback. Do not ask questions.\n\nPlan location: [file path]\nContext: [brief context about the task]\n```\n\nIf the subagent provides actionable feedback, revise the plan before yielding.\n\n\n## Plan Template\n\n```markdown\n# Plan: [Task Name]\n\n**Generated**: [Date]\n\n## Overview\n[Summary of task and approach]\n\n## Prerequisites\n- [Tools, libraries, access needed]\n\n## Dependency Graph\n\n```\n[Visual representation of task dependencies]\nT1 ──┬── T3 ──┐\n     │        ├── T5 ── T6 ── T7\nT2 ──┴── T4 ──┘\n```\n\n## Tasks\n\n### T1: [Name]\n- **depends_on**: []\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n### T2: [Name]\n- **depends_on**: []\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n### T3: [Name]\n- **depends_on**: [T1]\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n[... continue for all tasks ...]\n\n## Parallel Execution Groups\n\n| Wave | Tasks | Can Start When |\n|------|-------|----------------|\n| 1 | T1, T2 | Immediately |\n| 2 | T3, T4 | Wave 1 complete |\n| 3 | T5 | T3, T4 complete |\n| ... | ... | ... |\n\n## Testing Strategy\n- [How to test]\n- [What to verify]\n\n## Risks & Mitigations\n- [What could go wrong + how to handle]\n```\n\n## Important\n\n- Every task must have explicit `depends_on` field\n- Root tasks (no dependencies) can be executed in parallel immediately\n- Do NOT implement - only create the plan\n- Always use Context7 for external dependencies before finalizing tasks\n- Always ask questions where ambiguity exists\n","# Swarm-Ready Planner\n\nCreate implementation plans with explicit task dependencies optimized for parallel agent execution. This skill can be ran inside or outside of Plan Mode. \n\n## Core Principles\n\n1. **Explore Codebase**: Investigate architecture, patterns, existing implementations, dependencies, and frameworks in use.\n2. **Fresh Documentation First**: Use Context7 for ANY external library, framework, or API before planning tasks\n3. **Ask Questions**: Clarify ambiguities and seek clarification on scope, constraints, or priorities throughout the planning process. At any time.\n4. **Explicit Dependencies**: Every task declares what it depends on, enabling maximum parallelization\n5. **Atomic Tasks**: Each task is independently executable by a single agent\n6. **Review Before Yield**: A subagent reviews the plan for gaps before finalizing\n\n## Process\n\n### 1. Research\n\n**Codebase investigation:**\n- Architecture, patterns, existing implementations\n- Dependencies and frameworks in use\n\n### 1a. Optional: Stop to Clarification Questions\n\n- If the architecture is unclear or missing STOP AND YIELD to the user, and request user input (AskUserQuestions) before moving on. Always offer recommendations for clarification questions.\n- If architecture is present, skip 1a and move onto next step. \n\n### 2. Documentation\n\n**Documentation retrieval (REQUIRED for external dependencies):**\n\nUse Context7 skill or MCP to fetch current docs for any libraries\u002Fframeworks or APIs that are or will be used in project. If Context7 is not available, use web search.\n\nThis ensures version-accurate APIs, correct parameters, and current best practices.\n\n### 3. STOP and Request User Input\n\nWhen anything is unclear or could reasonably be done multiple ways:\n- Stop and ask clarifying questions immediately\n- Do not make assumptions about scope, constraints, or priorities\n- Questions should reduce risk and eliminate ambiguity\n- Always offer recommendations for clarification questions.\n- Use request_user_input or AskUserQuestion tool if available. \n\n### 4. Create Dependency-Aware Plan\n\nStructure the plan with explicit task dependencies using this format:\n\n#### Task Dependency Format\n\nEach task MUST include:\n- **id**: Unique identifier (e.g., `T1`, `T2.1`)\n- **depends_on**: Array of task IDs that must complete first (empty `[]` for root tasks)\n- **description**: What the task accomplishes\n- **location**: File paths involved\n- **validation**: acceptance criteria\n\n**Example:**\n```\nT1: [depends_on: []] Create database schema migration\nT2: [depends_on: []] Install required packages\nT3: [depends_on: [T1]] Create repository layer\nT4: [depends_on: [T1]] Create service interfaces\nT5: [depends_on: [T3, T4]] Implement business logic\nT6: [depends_on: [T2, T5]] Add API endpoints\nT7: [depends_on: [T6]] Write integration tests\n```\n\nTasks with empty\u002Fsatisfied dependencies can run in parallel (T1, T2 above).\n\n### 4. Save Plan\n\nSave to `\u003Ctopic>-plan.md` in the CWD.\n\n### 5. Subagent Review\n\nAfter saving, spawn a subagent to review the plan:\n\n```\nReview this implementation plan for:\n1. Missing dependencies between tasks\n2. Ordering issues that would cause failures\n3. Missing error handling or edge cases\n4. Gaps, holes, gotchas.\n\nProvide specific, actionable feedback. Do not ask questions.\n\nPlan location: [file path]\nContext: [brief context about the task]\n```\n\nIf the subagent provides actionable feedback, revise the plan before yielding.\n\n\n## Plan Template\n\n```markdown\n# Plan: [Task Name]\n\n**Generated**: [Date]\n\n## Overview\n[Summary of task and approach]\n\n## Prerequisites\n- [Tools, libraries, access needed]\n\n## Dependency Graph\n\n```\n[Visual representation of task dependencies]\nT1 ──┬── T3 ──┐\n     │        ├── T5 ── T6 ── T7\nT2 ──┴── T4 ──┘\n```\n\n## Tasks\n\n### T1: [Name]\n- **depends_on**: []\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n### T2: [Name]\n- **depends_on**: []\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n### T3: [Name]\n- **depends_on**: [T1]\n- **location**: [file paths]\n- **description**: [what to do]\n- **validation**: [how to verify]\n- **status**: Not Completed\n- **log**: [leave empty, to be filled out later]\n- **files edited\u002Fcreated**: [leave empty, to be filled out later]\n\n[... continue for all tasks ...]\n\n## Parallel Execution Groups\n\n| Wave | Tasks | Can Start When |\n|------|-------|----------------|\n| 1 | T1, T2 | Immediately |\n| 2 | T3, T4 | Wave 1 complete |\n| 3 | T5 | T3, T4 complete |\n| ... | ... | ... |\n\n## Testing Strategy\n- [How to test]\n- [What to verify]\n\n## Risks & Mitigations\n- [What could go wrong + how to handle]\n```\n\n## Important\n\n- Every task must have explicit `depends_on` field\n- Root tasks (no dependencies) can be executed in parallel immediately\n- Do NOT implement - only create the plan\n- Always use Context7 for external dependencies before finalizing tasks\n- Always ask questions where ambiguity exists\n",{"name":5,"metadata":36,"description":38},{"invocation":37},"explicit-only","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.\n","main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","skills\u002Fswarm-planner",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill swarm-planner",{"tool":53,"command":54},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill swarm-planner",{"tool":56,"command":57},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill swarm-planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",true,[],[62,94,104,130,158,176],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":73,"publishedAt":31},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"react","vercel react best practices","best practices","react best practices","vercel","code","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","tasks","guidelines","react components","components","performance","writing",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":31},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[101,19,102,25,103],"spark","super swarm spark","commands",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":31},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"role","creator","role creator","codex","developer","keys","model","users","instructions","roles","install","toml","guide","files","reasoning","enforce","create","config","generate",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":139,"publishedAt":31},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000023","Skill与智能体开发",[140,141,142,143,144,30,145,146,147,148,149,150,151,152,153,154,79,155,156,157],"read github","github","read","use","when to use","URL","via","io","service","do","user","repo","format","repository","search","documentation","docs","MCP",{"skillNo":159,"name":20,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":31},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[20,164,165,166,167,81,28,103,168,169,170,143,30,171,172,173,174,127,88,175],"write","atomic","with","sprints","outline","draft","me","phased implementation","plan","help","planning","design",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":31},"01M6H7YZCDDY5H7F4CQM2RVQTZ","plan-harder","Use when user specfically says 'plan harder'.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplan-harder\u002FSKILL.md",[],[183,172,143,150],"plan harder"]