[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J58GH1C5KWB9T4DPYVXVV4":3,"skill-same:01M6J58GH1C5KWB9T4DPYVXVV4":79},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6J58GH1C5KWB9T4DPYVXVV4","mk-scout",null,"Fast parallel codebase scouting — searches many directories at once, returning a file map + architecture fingerprint. Use before planning or cross-dir work. NOT for deep single-file reads.","ngocsangyem\u002FMeowKit","ngocsangyem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33769536?v=4","01M6J3FSMJAG9PVQEGRT7AQ9J2","Sang Nguyen","01M6J3FSRTJG0MNP6NV71639RM",16,"MIT","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"scout","mk scout","single","fast","codebase","at","scouting","work","architecture","file","use","map","for","planning","directories","single-file","deep","parallel","2026-11-10 10:12:30",false,"---\nname: \"mk-scout\"\ndescription: \"Fast parallel codebase scouting — searches many directories at once, returning a file map + architecture fingerprint. Use before planning or cross-dir work. NOT for deep single-file reads.\"\n---\n\n# Scout\n\nFast, parallel codebase exploration using Explore sub-task. Divides the project into segments, searches them simultaneously, and returns a consolidated report.\n\n## When to Use\n\n- Starting a feature that spans multiple directories\n- User asks to \"find\", \"locate\", or \"search for\" files\n- Before planning (Phase 1) on complex tasks — understand what exists first\n- Debugging session requiring file relationship understanding\n- User asks about project structure or where functionality lives\n\n## Workflow Integration\n\nOperates in **Phase 0 (Orient)** and **Phase 1 (Plan)**.\n\n- Orchestrator invokes scout before planner on COMPLEX tasks\n- Planner may invoke scout when the technical approach needs codebase understanding\n- Developer may invoke scout when implementation touches unfamiliar areas\n\n## Quick Start\n\n```\nthe scout skill authentication      → find all auth-related files\nthe scout skill database migrations  → find DB migration files\nthe scout skill [any search target]  → parallel search across codebase\n```\n\n## Scout Process\n\n1. **Analyze** — parse user prompt, identify search targets (keywords, file types)\n2. **Determine scale** — calculate SCALE using formula in `references\u002Fscouting-strategy.md`\n3. **Apply search scope** — include Tier 1 always, Tier 2 if task-relevant, exclude Tier 3 always (see `references\u002Fsearch-scope.md`)\n4. **Divide directories** — assign each Explore agent a distinct scope (no overlap)\n5. **Spawn agents** — all in a single message for parallel execution (see `references\u002Fscouting-strategy.md`)\n6. **Collect results** — deduplicate, merge, note gaps\u002Ftimeouts\n7. **Build report** — fill structured template (see `references\u002Freport-and-handoff.md`)\n8. **Execute handoff** — route to next agent per handoff protocol\n\n## References\n\nLoad these **only when executing** the corresponding step — not upfront.\n\n| Reference                                                       | When to load                    | What it contains                                                                                                  |\n| --------------------------------------------------------------- | ------------------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| **[search-scope.md](.\u002Freferences\u002Fsearch-scope.md)**             | Step 3 — applying scope rules   | Tier 1\u002F2\u002F3 directory lists, justification, exclusion patterns                                                     |\n| **[scouting-strategy.md](.\u002Freferences\u002Fscouting-strategy.md)**   | Steps 2, 4, 5 — spawning agents | SCALE formula, directory division rules, Explore agent prompt template, parallel execution, file reading patterns |\n| **[report-and-handoff.md](.\u002Freferences\u002Freport-and-handoff.md)** | Steps 7, 8 — writing output     | Report template with all sections, handoff protocol per phase, memory integration, context budget                 |\n\n## Constraints\n\n- **Read-only** — scout NEVER modifies files\n- **Maximum 6 parallel agents** — beyond this, aggregation cost exceeds benefit\n- **3-minute timeout** per agent — skip non-responders, don't retry\n- **No external tool dependencies** — uses only the host runtime's built-in Explore\n- **Security** — never access .env, credentials, or SSH keys during scouting\n- **Tier 3 always excluded** — no exceptions regardless of task\n\n## Gotchas\n\n- **6-agent cap vs 3-agent rule** — the parallel-execution rules Rule 2 caps parallel agents at 3, but that rule governs write-capable agents (merge-conflict risk). Scout uses read-only Explore sub-task which don't produce conflicts, so the 6-agent ceiling here is intentional, not a rule violation.\n- **sub-task returning partial results**: Context window exceeded, agent returns truncated output → Set explicit file count limits per sub-task; merge results with dedup\n- **Missing hidden files in directory scan**: Default glob patterns skip dotfiles → Include dotfiles explicitly when scanning config directories","# Scout\n\nFast, parallel codebase exploration using Explore sub-task. Divides the project into segments, searches them simultaneously, and returns a consolidated report.\n\n## When to Use\n\n- Starting a feature that spans multiple directories\n- User asks to \"find\", \"locate\", or \"search for\" files\n- Before planning (Phase 1) on complex tasks — understand what exists first\n- Debugging session requiring file relationship understanding\n- User asks about project structure or where functionality lives\n\n## Workflow Integration\n\nOperates in **Phase 0 (Orient)** and **Phase 1 (Plan)**.\n\n- Orchestrator invokes scout before planner on COMPLEX tasks\n- Planner may invoke scout when the technical approach needs codebase understanding\n- Developer may invoke scout when implementation touches unfamiliar areas\n\n## Quick Start\n\n```\nthe scout skill authentication      → find all auth-related files\nthe scout skill database migrations  → find DB migration files\nthe scout skill [any search target]  → parallel search across codebase\n```\n\n## Scout Process\n\n1. **Analyze** — parse user prompt, identify search targets (keywords, file types)\n2. **Determine scale** — calculate SCALE using formula in `references\u002Fscouting-strategy.md`\n3. **Apply search scope** — include Tier 1 always, Tier 2 if task-relevant, exclude Tier 3 always (see `references\u002Fsearch-scope.md`)\n4. **Divide directories** — assign each Explore agent a distinct scope (no overlap)\n5. **Spawn agents** — all in a single message for parallel execution (see `references\u002Fscouting-strategy.md`)\n6. **Collect results** — deduplicate, merge, note gaps\u002Ftimeouts\n7. **Build report** — fill structured template (see `references\u002Freport-and-handoff.md`)\n8. **Execute handoff** — route to next agent per handoff protocol\n\n## References\n\nLoad these **only when executing** the corresponding step — not upfront.\n\n| Reference                                                       | When to load                    | What it contains                                                                                                  |\n| --------------------------------------------------------------- | ------------------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| **[search-scope.md](.\u002Freferences\u002Fsearch-scope.md)**             | Step 3 — applying scope rules   | Tier 1\u002F2\u002F3 directory lists, justification, exclusion patterns                                                     |\n| **[scouting-strategy.md](.\u002Freferences\u002Fscouting-strategy.md)**   | Steps 2, 4, 5 — spawning agents | SCALE formula, directory division rules, Explore agent prompt template, parallel execution, file reading patterns |\n| **[report-and-handoff.md](.\u002Freferences\u002Freport-and-handoff.md)** | Steps 7, 8 — writing output     | Report template with all sections, handoff protocol per phase, memory integration, context budget                 |\n\n## Constraints\n\n- **Read-only** — scout NEVER modifies files\n- **Maximum 6 parallel agents** — beyond this, aggregation cost exceeds benefit\n- **3-minute timeout** per agent — skip non-responders, don't retry\n- **No external tool dependencies** — uses only the host runtime's built-in Explore\n- **Security** — never access .env, credentials, or SSH keys during scouting\n- **Tier 3 always excluded** — no exceptions regardless of task\n\n## Gotchas\n\n- **6-agent cap vs 3-agent rule** — the parallel-execution rules Rule 2 caps parallel agents at 3, but that rule governs write-capable agents (merge-conflict risk). Scout uses read-only Explore sub-task which don't produce conflicts, so the 6-agent ceiling here is intentional, not a rule violation.\n- **sub-task returning partial results**: Context window exceeded, agent returns truncated output → Set explicit file count limits per sub-task; merge results with dedup\n- **Missing hidden files in directory scan**: Default glob patterns skip dotfiles → Include dotfiles explicitly when scanning config directories",{"name":5,"description":7},"main","c2c69c674e8c62fe9634bfb360b5f9f14c70e1a5","packages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-12 20:22:02",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-scout",{"tool":57,"command":58},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-scout",{"tool":60,"command":61},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-scout","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout\u002FSKILL.md",true,[65,71,75],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Freport-and-handoff.md","REFERENCE","参考文档",3844,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout\u002Freferences\u002Freport-and-handoff.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fscouting-strategy.md",7941,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout\u002Freferences\u002Fscouting-strategy.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fsearch-scope.md",2846,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-scout\u002Freferences\u002Fsearch-scope.md",[80,98,116,122,134,157],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":37},"01M6J4NFDY0KY3XXJ6E5WBASAF","mk-sequential-thinking","Structured step-by-step reasoning before acting, to avoid guessing. For complex debugging, multi-step analysis, hypothesis checks. NOT for being stuck on approach (mk:problem-solving).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-sequential-thinking\u002FSKILL.md",[],[87,88,89,90,91,92,93,94,95,31,96,97],"mk sequential thinking","sequential thinking","thinking","structured","problem","problem-solving","analysis","hypothesis","reasoning","debugging","multi",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":109,"publishedAt":37},"01M6J5D3G7C0V3BZ97Y61WB172","mk:fixture-valid","A valid fixture used to verify the skill structure validator.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Fvalid\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[110,111,112,113,114,115],"mk:fixture valid","fixture","valid","verify","structure","validator",{"skillNo":117,"name":118,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":37},"01M6J5CZRVSN8T4BZM0Y42CXJY","invalid","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Finvalid\u002FSKILL.md",[],[118],{"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":129,"publishedAt":37},"01M6J5CVN0N8KP9JFAWCV2PC2T","mk:sample-skill","Sample skill for fixture purposes — small enough to land below noise floor.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Ftests\u002Ffixtures\u002Fcontext-audit\u002F.claude\u002Fskills\u002Fsample-skill\u002FSKILL.md",[128],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[130,131,132,133,111,31],"mk:sample skill","sample","sample skill","land",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":37},"01M6J5CP99X9S0B7XCSBX6H5P2","mk-worktree","Manages git worktrees for parallel agent isolation: creates parallel\u002F{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[140],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[142,143,144,145,29,146,147,148,149,150,151,152,31,36,153,154,155,156],"mk worktree","worktree","user","git worktrees","worktrees","branches","conflict","feature","isolation","name","with","timestamp","git","detection","git worktree",{"skillNo":158,"name":159,"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":164,"publishedAt":37},"01M6J5CJT8ZGXH9YYJ7GV3R2B4","mk-workflow-orchestrator","Auto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[163],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[165,166,167,168,169,170,171,172,173,174,175,149,176,177,31,178,179,180,181,182,183,184],"mk workflow orchestrator","workflow orchestrator","orchestrator","workflow","green-field","tasks","fix","auto","simple","intent","green","autobuild","mode","fixes","mk:autobuild","mk:cook","mk:fix","fasttrack","complex-feature","phase"]