[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DTY3ET2RPERM01B38VG57T":3,"skill-same:01M7DTY3ET2RPERM01B38VG57T":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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7DTY3ET2RPERM01B38VG57T","mk-project-context",null,"Generate or update docs\u002Fproject-context.md — the source of truth for conventions, tech stack, and anti-patterns, loaded by all agents as a constitution.","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\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-project-context\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"mk-project-context\"\ndescription: \"Generate or update docs\u002Fproject-context.md — the source of truth for conventions, tech stack, and anti-patterns, loaded by all agents as a constitution.\"\n---\n\n# Project Context Generator\n\nCreates `docs\u002Fproject-context.md` — the agent \"constitution\" that every agent loads on activation.\n\n> To generate the full documentation suite (README, architecture, code standards, etc.), use `mk:docs-init` instead. `mk:project-context` generates only the agent constitution.\n\n## Purpose\n\nEliminate context drift between agents. Without a single authoritative file, agents infer conventions independently and make conflicting decisions. Project context solves this by providing one document all agents read first.\n\n## Actions\n\n### generate\n\nScan the codebase and create `docs\u002Fproject-context.md` from scratch.\n\n**Scan targets:**\n\n- `package.json` \u002F `Cargo.toml` \u002F `go.mod` \u002F `pyproject.toml` → tech stack\n- `tsconfig.json` \u002F `eslint.*` \u002F `prettier.*` → code conventions\n- `**\u002Ftest\u002F**` \u002F `**\u002F*.test.*` \u002F `**\u002F*.spec.*` \u002F `**\u002F*.cy.*` → testing patterns\n- Existing `docs\u002F` → architecture decisions, prior context\n- `.env.example` → environment variables (names only, not values)\n\n**Output:** `docs\u002Fproject-context.md` using `templates\u002Fproject-context-template.md`\n\n### update\n\nRe-scan codebase and update existing `docs\u002Fproject-context.md`. Preserves manual edits in sections marked `\u003C!-- manual -->`.\n\n### init\n\nWrite a TODO-filled skeleton to `docs\u002Fproject-context.md` for greenfield projects\nwhere `generate` would produce empty sections (no codebase to scan yet).\n\n**Behaviour:**\n- If `docs\u002Fproject-context.md` already exists → **refuse with error**. Use `update` instead.\n- If absent → write `templates\u002Fskeleton.md` to `docs\u002Fproject-context.md`.\n- Creates `docs\u002F` directory if it does not exist.\n\n**When to use `init` vs `generate`:**\n| Situation | Action |\n|-----------|--------|\n| Empty or near-empty project, \u003C 5 source files | `init` — fill manually |\n| Established project with real code | `generate` — auto-derive |\n| Existing `docs\u002Fproject-context.md` is stale | `update` — re-scan, preserve manual edits |\n\n## When to Run\n\n- **First time:** After `mk:bootstrap` or `mk:docs-init`\n- **After architecture changes:** New framework, new database, major refactor\n- **Periodically:** When agents produce inconsistent code (symptom of stale context)\n\n## Focus on the Unobvious\n\nThe template emphasizes facts agents **cannot infer from code**:\n\n- WHY a framework was chosen (not just what it is)\n- Rejected alternatives (\"use Zustand, NOT Redux\")\n- Anti-patterns specific to this project\n- Testing boundaries (what to unit test vs e2e)\n\n## Template\n\nSee `templates\u002Fproject-context-template.md` for the full structure.\n\n## Gotchas\n\n- Stale context is worse than no context — re-run `update` after major architecture changes\n- The template asks for \"rejected alternatives\" — this is the highest-value content. If you chose Zustand over Redux, say WHY\n- Don't list every file path — agents can Glob for that. Focus on RULES and CONVENTIONS\n- `\u003C!-- manual -->` sections survive `update` action but NOT `generate` — backup before regenerating from scratch\n- If project-context.md conflicts with AGENTS.md, AGENTS.md wins (it's the higher-priority document)\n- `init` refuses to overwrite an existing `docs\u002Fproject-context.md` — this is intentional. Delete the file manually if you truly want to reset to a blank skeleton.\n\n## Integration\n\nAll agents load `docs\u002Fproject-context.md` in their Required Context section. If the file doesn't exist, agents behave exactly as before (graceful degradation).\n\n## Files in this skill\n\n- `SKILL.md` — you are here\n- `templates\u002Fproject-context-template.md` — output template used by `generate` action\n- `templates\u002Fskeleton.md` — TODO-placeholder constitution template used by `init` action","# Project Context Generator\n\nCreates `docs\u002Fproject-context.md` — the agent \"constitution\" that every agent loads on activation.\n\n> To generate the full documentation suite (README, architecture, code standards, etc.), use `mk:docs-init` instead. `mk:project-context` generates only the agent constitution.\n\n## Purpose\n\nEliminate context drift between agents. Without a single authoritative file, agents infer conventions independently and make conflicting decisions. Project context solves this by providing one document all agents read first.\n\n## Actions\n\n### generate\n\nScan the codebase and create `docs\u002Fproject-context.md` from scratch.\n\n**Scan targets:**\n\n- `package.json` \u002F `Cargo.toml` \u002F `go.mod` \u002F `pyproject.toml` → tech stack\n- `tsconfig.json` \u002F `eslint.*` \u002F `prettier.*` → code conventions\n- `**\u002Ftest\u002F**` \u002F `**\u002F*.test.*` \u002F `**\u002F*.spec.*` \u002F `**\u002F*.cy.*` → testing patterns\n- Existing `docs\u002F` → architecture decisions, prior context\n- `.env.example` → environment variables (names only, not values)\n\n**Output:** `docs\u002Fproject-context.md` using `templates\u002Fproject-context-template.md`\n\n### update\n\nRe-scan codebase and update existing `docs\u002Fproject-context.md`. Preserves manual edits in sections marked `\u003C!-- manual -->`.\n\n### init\n\nWrite a TODO-filled skeleton to `docs\u002Fproject-context.md` for greenfield projects\nwhere `generate` would produce empty sections (no codebase to scan yet).\n\n**Behaviour:**\n- If `docs\u002Fproject-context.md` already exists → **refuse with error**. Use `update` instead.\n- If absent → write `templates\u002Fskeleton.md` to `docs\u002Fproject-context.md`.\n- Creates `docs\u002F` directory if it does not exist.\n\n**When to use `init` vs `generate`:**\n| Situation | Action |\n|-----------|--------|\n| Empty or near-empty project, \u003C 5 source files | `init` — fill manually |\n| Established project with real code | `generate` — auto-derive |\n| Existing `docs\u002Fproject-context.md` is stale | `update` — re-scan, preserve manual edits |\n\n## When to Run\n\n- **First time:** After `mk:bootstrap` or `mk:docs-init`\n- **After architecture changes:** New framework, new database, major refactor\n- **Periodically:** When agents produce inconsistent code (symptom of stale context)\n\n## Focus on the Unobvious\n\nThe template emphasizes facts agents **cannot infer from code**:\n\n- WHY a framework was chosen (not just what it is)\n- Rejected alternatives (\"use Zustand, NOT Redux\")\n- Anti-patterns specific to this project\n- Testing boundaries (what to unit test vs e2e)\n\n## Template\n\nSee `templates\u002Fproject-context-template.md` for the full structure.\n\n## Gotchas\n\n- Stale context is worse than no context — re-run `update` after major architecture changes\n- The template asks for \"rejected alternatives\" — this is the highest-value content. If you chose Zustand over Redux, say WHY\n- Don't list every file path — agents can Glob for that. Focus on RULES and CONVENTIONS\n- `\u003C!-- manual -->` sections survive `update` action but NOT `generate` — backup before regenerating from scratch\n- If project-context.md conflicts with AGENTS.md, AGENTS.md wins (it's the higher-priority document)\n- `init` refuses to overwrite an existing `docs\u002Fproject-context.md` — this is intentional. Delete the file manually if you truly want to reset to a blank skeleton.\n\n## Integration\n\nAll agents load `docs\u002Fproject-context.md` in their Required Context section. If the file doesn't exist, agents behave exactly as before (graceful degradation).\n\n## Files in this skill\n\n- `SKILL.md` — you are here\n- `templates\u002Fproject-context-template.md` — output template used by `generate` action\n- `templates\u002Fskeleton.md` — TODO-placeholder constitution template used by `init` action",{"name":5,"description":7},"main","c7ff0a9e672de2c0590b03f6459385c2d7a63c1a","kit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-project-context",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-15 03:54:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-project-context",{"tool":39,"command":40},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-project-context",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-project-context","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-project-context\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"templates\u002Fproject-context-template.md","REFERENCE","参考文档",1676,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-project-context\u002Ftemplates\u002Fproject-context-template.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"templates\u002Fskeleton.md",1808,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-project-context\u002Ftemplates\u002Fskeleton.md",[58,65,72,79,86,93],{"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":19},"01M7DVHF481B4J41T4855KGM50","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\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7DVHAWVKDKPB1EA3F1NC4JC","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\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DVH6SYBHWW00TRZXCC56JW","mk-web-to-markdown","Fetch a URL and return clean markdown, for arbitrary external pages (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Static-only by default; opt-in JS rendering available.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-web-to-markdown\u002FSKILL.md",[],[],{"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":85,"publishedAt":19},"01M7DVH3HGW47BX3PEF30JV6EJ","mk-vulnerability-scanner","Vulnerability analysis: OWASP Top 10, current threat landscape, supply chain security, attack surface mapping, risk prioritization. Use for security audits. NOT for STRIDE\u002FCSO infra audits (mk:cso).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vulnerability-scanner\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7DVGZBKMB9WDFH9MFMA99FV","mk-vue","Vue 3 authoring\u002Freview: components, composables, reactivity, Pinia, Pinia Colada, file routing, forms. Composition API + script setup. Auto-activates on .vue files. Deep review: mk:vue-best-practices.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DVGSE12AA1M7599HB8HRCT","mk-vue-testing-best-practices","Vue 3 testing best-practices review: Vitest + Vue Test Utils for components, composables, Pinia, Router, async\u002FSuspense, forms, a11y, plus Playwright E2E strategy. Advisory only.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue-testing-best-practices\u002FSKILL.md",[],[]]