[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J5AXA37M43FCHAERX9RCGE":3,"skill-same:01M6J5AXA37M43FCHAERX9RCGE":67},{"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":23,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M6J5AXA37M43FCHAERX9RCGE","mk-validate-plan",null,"Validates an approved plan across 8 dimensions before build — incomplete acceptance criteria, missing dependencies, unresolved risks. Use after Gate 1, before Test.","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-validate-plan\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"validate plan","plan","validate","mk validate plan","missing","true","use","acceptance","dimensions","across","test","acceptance criteria","build","dependencies","gate","2026-11-10 10:12:30",false,"---\nname: \"mk-validate-plan\"\ndescription: \"Validates an approved plan across 8 dimensions before build — incomplete acceptance criteria, missing dependencies, unresolved risks. Use after Gate 1, before Test.\"\ndisable-model-invocation: true\n---\n\n# Plan Validation — 8-Dimension Quality Check\n\nAudits an approved plan against 8 dimensions to catch gaps before implementation begins.\nDoes NOT replace Gate 1 (human approval), modify plans, or route edits itself. If it\nfinds an Insert or Split mutation is needed, the planner performs it and returns to\nGate 1 for re-approval; Skip and Reorder changes require notification plus audit log.\n\n> For green-field harness sprints (generator↔evaluator loop), use `mk:sprint-contract` instead. `mk:validate-plan` operates on plans from `mk:plan-creator` (cook flow only).\n\n## When to Use\n\n- After Gate 1 approval, before Phase 2 (Test)\n- When `the cook skill` detects a COMPLEX task (auto-suggested)\n- When user wants to stress-test a plan before committing to implementation\n- When user says \"validate this plan\", \"check my plan\", \"is this plan complete\"\n\n## 8 Validation Dimensions\n\n| #   | Dimension                   | Pass Criteria                                                        | Common Failure                                               |\n| --- | --------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------ |\n| 1   | **Scope Clarity**           | In-scope and out-of-scope sections are explicit and non-overlapping  | Vague scope: \"improve the auth system\" without boundaries    |\n| 2   | **Acceptance Criteria**     | Every criterion is binary (pass\u002Ffail), not subjective                | Subjective: \"should feel fast\" vs binary: \"response \u003C 200ms\" |\n| 3   | **Dependencies Resolved**   | All external dependencies identified with status (available\u002Fblocked) | Missing: needs DB migration but not listed as dependency     |\n| 4   | **Risks Identified**        | At least 1 risk flag with mitigation strategy                        | No risks listed (every plan has risks; zero = not evaluated) |\n| 5   | **Architecture Documented** | Technical approach references existing patterns or includes ADR      | \"We'll figure out the architecture during implementation\"    |\n| 6   | **Test Strategy**           | Test approach covers acceptance criteria; edge cases identified      | \"We'll add tests after\" (violates TDD)                       |\n| 7   | **Security Considered**     | Auth, data access, input validation addressed (or explicitly N\u002FA)    | No mention of security for a feature handling user data      |\n| 8   | **Effort Estimated**        | Time\u002Fcomplexity estimate with confidence level                       | No estimate or \"it depends\" without qualification            |\n\n## Workflow\n\n1. **Load plan file** — Read from `tasks\u002Fplans\u002FYYMMDD-name\u002Fplan.md`\n2. **Check each dimension** — Evaluate against pass criteria\n3. **Produce validation report** — Pass\u002Ffail per dimension with findings\n4. **Route result:**\n   - All 8 PASS → proceed to Phase 2\n   - Any FAIL → return to planner with specific revision requests\n   - WARN (partially met) → user decides: proceed or revise\n\n## Output Format\n\n```markdown\n## Plan Validation: [Plan Name]\n\n| #   | Dimension               | Status         | Finding            |\n| --- | ----------------------- | -------------- | ------------------ |\n| 1   | Scope Clarity           | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 2   | Acceptance Criteria     | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 3   | Dependencies Resolved   | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 4   | Risks Identified        | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 5   | Architecture Documented | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 6   | Test Strategy           | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 7   | Security Considered     | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 8   | Effort Estimated        | PASS\u002FFAIL\u002FWARN | [specific finding] |\n\n**Result:** [N]\u002F8 passed | [Action: proceed \u002F revise dimensions X,Y]\n```\n\n## Whole-Plan Consistency Sweep (final pre-emit step)\n\nAfter scoring the 8 dimensions and BEFORE emitting the validation report, run a cross-file consistency check on the plan directory.\n\n**Why:** Distributed plans (`plan.md` + N × `phase-*.md`) drift after edits. One phase gets renamed; another phase still references the old name. Each phase reads as self-consistent but the plan as a whole is contradictory.\n\n**Procedure:**\n1. Re-read `plan.md` and every `phase-*.md` in the plan dir\n2. Build a delta of: renamed entities, scope changes, dropped features, decision changes\n3. grep every plan file for stale references to renamed\u002Fdropped items\n4. Reconcile contradictions across files (not only the file that surfaced them)\n\n**Output:** Append a `sweep_failures` block to the validation report. Sweep failures DO NOT auto-FAIL — they surface inconsistencies the human must reconcile before Phase 3.\n\n```\nsweep_failures:\n  - phase-02.md:18  references `userController` (renamed to `authController` in plan.md:42)\n  - phase-04.md:8   declares scope item that plan.md:62 marks out-of-scope\n```\n\n**Skip conditions:** plan has only `plan.md` (no phase files); plan dir not found.\n\n**Source:** Adapted from external verification-role guidance for whole-plan consistency sweeps.\n\n## Integration with Cook Workflow\n\nIn `the cook skill`, validation runs automatically for COMPLEX tasks:\n\n```\nGate 1 (plan approved) → mk:validate-plan → Phase 2 (Test)\n```\n\nFor STANDARD tasks, validation is optional (user-triggered).\nFor TRIVIAL tasks, validation is skipped.\n\n## Gotchas\n\n- **Not the same as the structural check**: `npx mewkit plan check --structural` validates plan file *structure* (required sections exist). This skill validates plan *content quality* (are acceptance criteria binary? are risks identified?). Both can run — they check different things.\n\n## Relationship to plan-creator v2.3.1\n\nNote: plan-creator's step-06 now includes an enhanced validation interview with detection keywords and section mapping. mk:validate-plan focuses on 8-dimension structural validation, which is complementary — not a replacement.\n\n## What This Skill Does NOT Do\n\n- Does NOT replace Gate 1 — human approval still required\n- Does NOT modify plan files — read-only analysis\n- Does NOT generate tests — that's Phase 2 (tester agent)\n- Does NOT block Gate 1 — runs after Gate 1, before Phase 2\n","# Plan Validation — 8-Dimension Quality Check\n\nAudits an approved plan against 8 dimensions to catch gaps before implementation begins.\nDoes NOT replace Gate 1 (human approval), modify plans, or route edits itself. If it\nfinds an Insert or Split mutation is needed, the planner performs it and returns to\nGate 1 for re-approval; Skip and Reorder changes require notification plus audit log.\n\n> For green-field harness sprints (generator↔evaluator loop), use `mk:sprint-contract` instead. `mk:validate-plan` operates on plans from `mk:plan-creator` (cook flow only).\n\n## When to Use\n\n- After Gate 1 approval, before Phase 2 (Test)\n- When `the cook skill` detects a COMPLEX task (auto-suggested)\n- When user wants to stress-test a plan before committing to implementation\n- When user says \"validate this plan\", \"check my plan\", \"is this plan complete\"\n\n## 8 Validation Dimensions\n\n| #   | Dimension                   | Pass Criteria                                                        | Common Failure                                               |\n| --- | --------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------ |\n| 1   | **Scope Clarity**           | In-scope and out-of-scope sections are explicit and non-overlapping  | Vague scope: \"improve the auth system\" without boundaries    |\n| 2   | **Acceptance Criteria**     | Every criterion is binary (pass\u002Ffail), not subjective                | Subjective: \"should feel fast\" vs binary: \"response \u003C 200ms\" |\n| 3   | **Dependencies Resolved**   | All external dependencies identified with status (available\u002Fblocked) | Missing: needs DB migration but not listed as dependency     |\n| 4   | **Risks Identified**        | At least 1 risk flag with mitigation strategy                        | No risks listed (every plan has risks; zero = not evaluated) |\n| 5   | **Architecture Documented** | Technical approach references existing patterns or includes ADR      | \"We'll figure out the architecture during implementation\"    |\n| 6   | **Test Strategy**           | Test approach covers acceptance criteria; edge cases identified      | \"We'll add tests after\" (violates TDD)                       |\n| 7   | **Security Considered**     | Auth, data access, input validation addressed (or explicitly N\u002FA)    | No mention of security for a feature handling user data      |\n| 8   | **Effort Estimated**        | Time\u002Fcomplexity estimate with confidence level                       | No estimate or \"it depends\" without qualification            |\n\n## Workflow\n\n1. **Load plan file** — Read from `tasks\u002Fplans\u002FYYMMDD-name\u002Fplan.md`\n2. **Check each dimension** — Evaluate against pass criteria\n3. **Produce validation report** — Pass\u002Ffail per dimension with findings\n4. **Route result:**\n   - All 8 PASS → proceed to Phase 2\n   - Any FAIL → return to planner with specific revision requests\n   - WARN (partially met) → user decides: proceed or revise\n\n## Output Format\n\n```markdown\n## Plan Validation: [Plan Name]\n\n| #   | Dimension               | Status         | Finding            |\n| --- | ----------------------- | -------------- | ------------------ |\n| 1   | Scope Clarity           | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 2   | Acceptance Criteria     | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 3   | Dependencies Resolved   | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 4   | Risks Identified        | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 5   | Architecture Documented | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 6   | Test Strategy           | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 7   | Security Considered     | PASS\u002FFAIL\u002FWARN | [specific finding] |\n| 8   | Effort Estimated        | PASS\u002FFAIL\u002FWARN | [specific finding] |\n\n**Result:** [N]\u002F8 passed | [Action: proceed \u002F revise dimensions X,Y]\n```\n\n## Whole-Plan Consistency Sweep (final pre-emit step)\n\nAfter scoring the 8 dimensions and BEFORE emitting the validation report, run a cross-file consistency check on the plan directory.\n\n**Why:** Distributed plans (`plan.md` + N × `phase-*.md`) drift after edits. One phase gets renamed; another phase still references the old name. Each phase reads as self-consistent but the plan as a whole is contradictory.\n\n**Procedure:**\n1. Re-read `plan.md` and every `phase-*.md` in the plan dir\n2. Build a delta of: renamed entities, scope changes, dropped features, decision changes\n3. grep every plan file for stale references to renamed\u002Fdropped items\n4. Reconcile contradictions across files (not only the file that surfaced them)\n\n**Output:** Append a `sweep_failures` block to the validation report. Sweep failures DO NOT auto-FAIL — they surface inconsistencies the human must reconcile before Phase 3.\n\n```\nsweep_failures:\n  - phase-02.md:18  references `userController` (renamed to `authController` in plan.md:42)\n  - phase-04.md:8   declares scope item that plan.md:62 marks out-of-scope\n```\n\n**Skip conditions:** plan has only `plan.md` (no phase files); plan dir not found.\n\n**Source:** Adapted from external verification-role guidance for whole-plan consistency sweeps.\n\n## Integration with Cook Workflow\n\nIn `the cook skill`, validation runs automatically for COMPLEX tasks:\n\n```\nGate 1 (plan approved) → mk:validate-plan → Phase 2 (Test)\n```\n\nFor STANDARD tasks, validation is optional (user-triggered).\nFor TRIVIAL tasks, validation is skipped.\n\n## Gotchas\n\n- **Not the same as the structural check**: `npx mewkit plan check --structural` validates plan file *structure* (required sections exist). This skill validates plan *content quality* (are acceptance criteria binary? are risks identified?). Both can run — they check different things.\n\n## Relationship to plan-creator v2.3.1\n\nNote: plan-creator's step-06 now includes an enhanced validation interview with detection keywords and section mapping. mk:validate-plan focuses on 8-dimension structural validation, which is complementary — not a replacement.\n\n## What This Skill Does NOT Do\n\n- Does NOT replace Gate 1 — human approval still required\n- Does NOT modify plan files — read-only analysis\n- Does NOT generate tests — that's Phase 2 (tester agent)\n- Does NOT block Gate 1 — runs after Gate 1, before Phase 2\n",{"name":5,"description":7,"disable-model-invocation":44},true,"main","c2c69c674e8c62fe9634bfb360b5f9f14c70e1a5","packages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-validate-plan",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":55,"prompt":65,"zipAvailable":44},[56,59,62],{"tool":57,"command":58},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-validate-plan",{"tool":60,"command":61},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-validate-plan",{"tool":63,"command":64},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-validate-plan","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-validate-plan\u002FSKILL.md",[],[68,87,101,107,119,143],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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",[],[75,76,77,78,79,80,81,82,83,84,85,86],"mk sequential thinking","sequential thinking","thinking","structured","problem","problem-solving","analysis","hypothesis","reasoning","for","debugging","multi",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":94,"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",[93],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,96,97,98,99,100],"mk:fixture valid","fixture","valid","verify","structure","validator",{"skillNo":102,"name":103,"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":104,"categories":105,"keywords":106,"publishedAt":39},"01M6J5CZRVSN8T4BZM0Y42CXJY","invalid","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Finvalid\u002FSKILL.md",[],[103],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"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",[113],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,96,84],"mk:sample skill","sample","sample skill","land",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"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",[125],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[127,128,129,130,30,131,132,133,134,135,136,137,84,138,139,140,141,142],"mk worktree","worktree","user","git worktrees","worktrees","branches","conflict","feature","isolation","name","with","parallel","timestamp","git","detection","git worktree",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":150,"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",[149],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[151,152,153,154,155,156,157,158,159,160,161,134,162,163,84,164,165,166,167,168,169,170],"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"]