[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J4RDJZ9HA8MP33EGCGCTE1":3,"skill-same:01M6J4RDJZ9HA8MP33EGCGCTE1":73},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6J4RDJZ9HA8MP33EGCGCTE1","mk-verify",null,"Unified verification: build → lint → test → type-check → coverage. Use for 'is it green' \u002F 'run all checks'; auto-called by mk:cook. NOT for lint only (mk:lint-and-validate).","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\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-verify\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"mk verify","verify","it","mk:cook","cook","type-check","validate","run","build","test","verification","type","check","lint","use","auto","only","for","green","coverage","2026-11-10 10:12:30",false,"---\nname: \"mk-verify\"\ndescription: \"Unified verification: build → lint → test → type-check → coverage. Use for 'is it green' \u002F 'run all checks'; auto-called by mk:cook. NOT for lint only (mk:lint-and-validate).\"\n---\n\n# Verify — Unified Verification Loop\n\nRuns build → lint → type-check → tests → coverage in sequence. Fails fast on first failure.\nProduces a single PASS\u002FFAIL verdict with per-step results.\n\n## When to Use\n\n- After Phase 3 (Build GREEN) completes, before Phase 4 (Review)\n- Before creating a PR (`mk:ship` pre-flight)\n- Standalone: \"is everything green?\", \"run all checks\", \"verify build\"\n\n## Phase Anchor\n\n**Phase: 3→4 transition (Build → Review)**\n**Handoff:** If PASS → proceed to `mk:review`. If FAIL → developer fixes, re-run verify.\n\n## Project Detection\n\nDetect project type by checking for marker files in this order:\n\n| Marker File      | Language | Build                    | Lint                       | Type-check                            | Test                | Coverage                            |\n| ---------------- | -------- | ------------------------ | -------------------------- | ------------------------------------- | ------------------- | ----------------------------------- |\n| `package.json`   | JS\u002FTS    | `npm run build`          | `npm run lint`             | `npm run typecheck` or `tsc --noEmit` | `npm test`          | `.nycrc` or `jest.config` threshold |\n| `pyproject.toml` | Python   | `python -m build`        | `ruff check .` or `flake8` | `mypy .`                              | `pytest`            | `pyproject.toml` coverage threshold |\n| `go.mod`         | Go       | `go build .\u002F...`         | `golangci-lint run`        | (built-in to build)                   | `go test .\u002F...`     | coverage report                     |\n| `Gemfile`        | Ruby     | `bundle exec rake build` | `rubocop`                  | (N\u002FA)                                 | `bundle exec rspec` | `.simplecov`                        |\n| `Cargo.toml`     | Rust     | `cargo build`            | `cargo clippy`             | (built-in to build)                   | `cargo test`        | `cargo tarpaulin`                   |\n\n**Multiple markers found:** Use the most specific one (e.g., `Cargo.toml` over `package.json` if both exist in a mixed repo).\n\n**No marker found:** Ask user — \"What build and test commands should I use for this project?\"\n\nSee `references\u002Fproject-detection.md` for detailed detection logic and edge cases.\n\n## Scope: Changed Files (default)\n\nBy default this skill checks only what changed — it does NOT lint or test the whole\nproject. Post-change verification stays fast and focused on the current work; the\ncomplete whole-project gate runs later at ship time (`pre-ship.cjs`).\n\n1. Collect the changed files from git — union of committed-since-base + staged +\n   unstaged + untracked:\n\n   ```bash\n   BASE=$(git merge-base HEAD origin\u002FHEAD 2>\u002Fdev\u002Fnull \\\n       || git merge-base HEAD main 2>\u002Fdev\u002Fnull \\\n       || git merge-base HEAD master 2>\u002Fdev\u002Fnull)\n   { [ -n \"$BASE\" ] && git diff --name-only \"$BASE\"...HEAD\n     git diff --name-only\n     git diff --name-only --cached\n     git ls-files --others --exclude-standard\n   } | sort -u\n   ```\n\n2. **Lint** runs on the changed files only (e.g. `npx eslint \u003Cfiles>`, `ruff check \u003Cfiles>`).\n3. **Tests** run only those related to the changed files (e.g. `jest --findRelatedTests`,\n   `vitest related`, the changed test files for pytest).\n4. **Build** and **type-check** stay whole-program — a partial build or `tsc --noEmit`\n   pass is unsound and would miss cross-file breakage.\n5. **Coverage** is skipped in scoped mode (a related-tests run does not reflect global\n   coverage) and reported as `SCOPED`.\n\n**Fallbacks:** if git is unavailable, or no changed files are detected, run the whole\nproject (equivalent to `--full`). Pass `--full` to force a complete whole-project run —\nuse it for releases and CI.\n\nSee `references\u002Fproject-detection.md` for per-language scoped command mappings.\n\n## Process (Fail Fast)\n\nExecute each step in order. **Stop immediately on first failure** — do not continue to the next step.\n\n1. **Resolve scope** — collect changed files (above). Lint + tests run against the\n   changed set; build + type-check run whole-program. `--full` runs every step across\n   the whole project.\n2. **Detect** project type from marker files\n3. **Build** — compile\u002Fbundle the project (whole-program)\n4. **Lint** — static analysis on the changed files (whole project under `--full`)\n5. **Type-check** — static type validation, whole-program (if applicable to language)\n6. **Test** — run tests related to the changed files (full suite under `--full`)\n7. **Coverage** — `--full` only (a related-tests run does not reflect global coverage)\n\n## Coverage Threshold\n\n1. Check project config for threshold (`.nycrc`, `jest.config`, `pyproject.toml [tool.coverage]`, etc.)\n2. If no project config: use default **80%**\n3. If `--coverage-threshold N` flag provided: override with N%\n\n## Output Format\n\n```\n## Verification Report\n\n- Build:      PASS (npm run build, 4.2s)\n- Lint:       PASS (0 errors, 2 warnings)\n- Type-check: PASS (0 errors)\n- Tests:      PASS (142 passed, 0 failed, 3 skipped)\n- Coverage:   PASS (87% vs 80% threshold)\n\n**Overall: PASS** — ready for review\n```\n\nIn scoped (default) mode, Lint and Tests note the changed-file count and Coverage shows\n`SCOPED`:\n\n```\n- Lint:       PASS (3 changed files, 0 errors)\n- Tests:      PASS (related to 3 changed files — 18 passed, 0 failed)\n- Coverage:   SCOPED (run with --full for global coverage)\n```\n\nFailure example (stops after lint):\n\n```\n## Verification Report\n\n- Build:      PASS (npm run build, 3.8s)\n- Lint:       FAIL (3 errors in src\u002Fauth.ts:12, src\u002Fuser.ts:45)\n- Type-check: SKIPPED (lint failed)\n- Tests:      SKIPPED (lint failed)\n- Coverage:   SKIPPED (lint failed)\n\n**Overall: FAIL** — fix lint errors before proceeding\n\nErrors:\n  src\u002Fauth.ts:12  error  'password' is assigned but never used  no-unused-vars\n  src\u002Fuser.ts:45  error  Expected '===' but saw '=='            eqeqeq\n```\n\n## Flags\n\n| Flag                     | Effect                                                                                                                   |\n| ------------------------ | ------------------------------------------------------------------------------------------------------------------------ |\n| `--full`                 | Check the whole project (build+lint+test+coverage across all files). Use for releases\u002FCI. Default is changed-files scope |\n| `--coverage-threshold N` | Override coverage threshold with N%                                                                                      |\n| `--skip-build`           | Skip build step (use if build runs separately)                                                                           |\n| `--skip-coverage`        | Skip coverage check (use for quick verification)                                                                         |\n\n## Gotchas\n\n- **Config changes escalate to `--full`:** when the changed set includes build\u002Flint\u002Ftype\u002Ftest\n  config or dependencies (`package.json`, lockfiles, `tsconfig*`, ESLint\u002FPrettier config,\n  `jest`\u002F`vitest`\u002F`pytest`\u002F`ruff` config, CI workflows, oxlint), scoping is unsafe — those affect the\n  whole project. Run the whole project instead.\n- **Deleted-only changes:** if the changed set is only deletions\u002Frenames with no surviving\n  source files, related-tests scoping finds nothing — fall back to `--full` to confirm nothing\n  downstream broke.\n- **Package manager detection:** For JS\u002FTS, check for `pnpm-lock.yaml`, `yarn.lock`, or `bun.lockb` before defaulting to `npm`\n- **Monorepo:** If multiple `package.json` found, ask user which workspace to verify or run from root\n- **Type-check for Go\u002FRust:** Covered by the build step — mark as PASS if build passed\n- **Coverage for Ruby:** `.simplecov` config may not exist; default to 80% threshold if missing\n- **Flaky tests:** If tests fail intermittently, re-run once before reporting FAIL","# Verify — Unified Verification Loop\n\nRuns build → lint → type-check → tests → coverage in sequence. Fails fast on first failure.\nProduces a single PASS\u002FFAIL verdict with per-step results.\n\n## When to Use\n\n- After Phase 3 (Build GREEN) completes, before Phase 4 (Review)\n- Before creating a PR (`mk:ship` pre-flight)\n- Standalone: \"is everything green?\", \"run all checks\", \"verify build\"\n\n## Phase Anchor\n\n**Phase: 3→4 transition (Build → Review)**\n**Handoff:** If PASS → proceed to `mk:review`. If FAIL → developer fixes, re-run verify.\n\n## Project Detection\n\nDetect project type by checking for marker files in this order:\n\n| Marker File      | Language | Build                    | Lint                       | Type-check                            | Test                | Coverage                            |\n| ---------------- | -------- | ------------------------ | -------------------------- | ------------------------------------- | ------------------- | ----------------------------------- |\n| `package.json`   | JS\u002FTS    | `npm run build`          | `npm run lint`             | `npm run typecheck` or `tsc --noEmit` | `npm test`          | `.nycrc` or `jest.config` threshold |\n| `pyproject.toml` | Python   | `python -m build`        | `ruff check .` or `flake8` | `mypy .`                              | `pytest`            | `pyproject.toml` coverage threshold |\n| `go.mod`         | Go       | `go build .\u002F...`         | `golangci-lint run`        | (built-in to build)                   | `go test .\u002F...`     | coverage report                     |\n| `Gemfile`        | Ruby     | `bundle exec rake build` | `rubocop`                  | (N\u002FA)                                 | `bundle exec rspec` | `.simplecov`                        |\n| `Cargo.toml`     | Rust     | `cargo build`            | `cargo clippy`             | (built-in to build)                   | `cargo test`        | `cargo tarpaulin`                   |\n\n**Multiple markers found:** Use the most specific one (e.g., `Cargo.toml` over `package.json` if both exist in a mixed repo).\n\n**No marker found:** Ask user — \"What build and test commands should I use for this project?\"\n\nSee `references\u002Fproject-detection.md` for detailed detection logic and edge cases.\n\n## Scope: Changed Files (default)\n\nBy default this skill checks only what changed — it does NOT lint or test the whole\nproject. Post-change verification stays fast and focused on the current work; the\ncomplete whole-project gate runs later at ship time (`pre-ship.cjs`).\n\n1. Collect the changed files from git — union of committed-since-base + staged +\n   unstaged + untracked:\n\n   ```bash\n   BASE=$(git merge-base HEAD origin\u002FHEAD 2>\u002Fdev\u002Fnull \\\n       || git merge-base HEAD main 2>\u002Fdev\u002Fnull \\\n       || git merge-base HEAD master 2>\u002Fdev\u002Fnull)\n   { [ -n \"$BASE\" ] && git diff --name-only \"$BASE\"...HEAD\n     git diff --name-only\n     git diff --name-only --cached\n     git ls-files --others --exclude-standard\n   } | sort -u\n   ```\n\n2. **Lint** runs on the changed files only (e.g. `npx eslint \u003Cfiles>`, `ruff check \u003Cfiles>`).\n3. **Tests** run only those related to the changed files (e.g. `jest --findRelatedTests`,\n   `vitest related`, the changed test files for pytest).\n4. **Build** and **type-check** stay whole-program — a partial build or `tsc --noEmit`\n   pass is unsound and would miss cross-file breakage.\n5. **Coverage** is skipped in scoped mode (a related-tests run does not reflect global\n   coverage) and reported as `SCOPED`.\n\n**Fallbacks:** if git is unavailable, or no changed files are detected, run the whole\nproject (equivalent to `--full`). Pass `--full` to force a complete whole-project run —\nuse it for releases and CI.\n\nSee `references\u002Fproject-detection.md` for per-language scoped command mappings.\n\n## Process (Fail Fast)\n\nExecute each step in order. **Stop immediately on first failure** — do not continue to the next step.\n\n1. **Resolve scope** — collect changed files (above). Lint + tests run against the\n   changed set; build + type-check run whole-program. `--full` runs every step across\n   the whole project.\n2. **Detect** project type from marker files\n3. **Build** — compile\u002Fbundle the project (whole-program)\n4. **Lint** — static analysis on the changed files (whole project under `--full`)\n5. **Type-check** — static type validation, whole-program (if applicable to language)\n6. **Test** — run tests related to the changed files (full suite under `--full`)\n7. **Coverage** — `--full` only (a related-tests run does not reflect global coverage)\n\n## Coverage Threshold\n\n1. Check project config for threshold (`.nycrc`, `jest.config`, `pyproject.toml [tool.coverage]`, etc.)\n2. If no project config: use default **80%**\n3. If `--coverage-threshold N` flag provided: override with N%\n\n## Output Format\n\n```\n## Verification Report\n\n- Build:      PASS (npm run build, 4.2s)\n- Lint:       PASS (0 errors, 2 warnings)\n- Type-check: PASS (0 errors)\n- Tests:      PASS (142 passed, 0 failed, 3 skipped)\n- Coverage:   PASS (87% vs 80% threshold)\n\n**Overall: PASS** — ready for review\n```\n\nIn scoped (default) mode, Lint and Tests note the changed-file count and Coverage shows\n`SCOPED`:\n\n```\n- Lint:       PASS (3 changed files, 0 errors)\n- Tests:      PASS (related to 3 changed files — 18 passed, 0 failed)\n- Coverage:   SCOPED (run with --full for global coverage)\n```\n\nFailure example (stops after lint):\n\n```\n## Verification Report\n\n- Build:      PASS (npm run build, 3.8s)\n- Lint:       FAIL (3 errors in src\u002Fauth.ts:12, src\u002Fuser.ts:45)\n- Type-check: SKIPPED (lint failed)\n- Tests:      SKIPPED (lint failed)\n- Coverage:   SKIPPED (lint failed)\n\n**Overall: FAIL** — fix lint errors before proceeding\n\nErrors:\n  src\u002Fauth.ts:12  error  'password' is assigned but never used  no-unused-vars\n  src\u002Fuser.ts:45  error  Expected '===' but saw '=='            eqeqeq\n```\n\n## Flags\n\n| Flag                     | Effect                                                                                                                   |\n| ------------------------ | ------------------------------------------------------------------------------------------------------------------------ |\n| `--full`                 | Check the whole project (build+lint+test+coverage across all files). Use for releases\u002FCI. Default is changed-files scope |\n| `--coverage-threshold N` | Override coverage threshold with N%                                                                                      |\n| `--skip-build`           | Skip build step (use if build runs separately)                                                                           |\n| `--skip-coverage`        | Skip coverage check (use for quick verification)                                                                         |\n\n## Gotchas\n\n- **Config changes escalate to `--full`:** when the changed set includes build\u002Flint\u002Ftype\u002Ftest\n  config or dependencies (`package.json`, lockfiles, `tsconfig*`, ESLint\u002FPrettier config,\n  `jest`\u002F`vitest`\u002F`pytest`\u002F`ruff` config, CI workflows, oxlint), scoping is unsafe — those affect the\n  whole project. Run the whole project instead.\n- **Deleted-only changes:** if the changed set is only deletions\u002Frenames with no surviving\n  source files, related-tests scoping finds nothing — fall back to `--full` to confirm nothing\n  downstream broke.\n- **Package manager detection:** For JS\u002FTS, check for `pnpm-lock.yaml`, `yarn.lock`, or `bun.lockb` before defaulting to `npm`\n- **Monorepo:** If multiple `package.json` found, ask user which workspace to verify or run from root\n- **Type-check for Go\u002FRust:** Covered by the build step — mark as PASS if build passed\n- **Coverage for Ruby:** `.simplecov` config may not exist; default to 80% threshold if missing\n- **Flaky tests:** If tests fail intermittently, re-run once before reporting FAIL",{"name":5,"description":7},"main","c2c69c674e8c62fe9634bfb360b5f9f14c70e1a5","packages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-verify",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-verify",{"tool":59,"command":60},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-verify",{"tool":62,"command":63},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-verify\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fproject-detection.md","REFERENCE","参考文档",6624,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-verify\u002Freferences\u002Fproject-detection.md",[74,92,109,115,127,151],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":39},"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",[],[81,82,83,84,85,86,87,88,89,36,90,91],"mk sequential thinking","sequential thinking","thinking","structured","problem","problem-solving","analysis","hypothesis","reasoning","debugging","multi",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":39},"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",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[104,105,106,20,107,108],"mk:fixture valid","fixture","valid","structure","validator",{"skillNo":110,"name":111,"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":112,"categories":113,"keywords":114,"publishedAt":39},"01M6J5CZRVSN8T4BZM0Y42CXJY","invalid","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Finvalid\u002FSKILL.md",[],[111],{"skillNo":116,"name":117,"nameZh":6,"description":118,"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":122,"publishedAt":39},"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",[121],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[123,124,125,126,105,36],"mk:sample skill","sample","sample skill","land",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":39},"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",[133],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[135,136,137,138,33,139,140,141,142,143,144,145,36,146,147,148,149,150],"mk worktree","worktree","user","git worktrees","worktrees","branches","conflict","feature","isolation","name","with","parallel","timestamp","git","detection","git worktree",{"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":39},"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",[157],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[159,160,161,162,163,164,165,34,166,167,37,142,168,169,36,170,171,22,172,173,174,175],"mk workflow orchestrator","workflow orchestrator","orchestrator","workflow","green-field","tasks","fix","simple","intent","autobuild","mode","fixes","mk:autobuild","mk:fix","fasttrack","complex-feature","phase"]