[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AJ0G09FAQQ2Z4QGRKV5EVK":3,"skill-same:01M7AJ0G09FAQQ2Z4QGRKV5EVK":51},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7AJ0G09FAQQ2Z4QGRKV5EVK","speckit-spex-gates-review-spec",null,"Review specifications for soundness, completeness, and implementability","jimmidyson\u002Fkcp-cluster-api","jimmidyson","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F464659?v=4","01M7AHMAJZVCKJFJ493ENNT2AF","Jimmi Dyson","01M7AHMAKKXY03Y7QK73HWEQQN",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-gates\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-gates-review-spec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speckit-spex-gates-review-spec\ndescription: Review specifications for soundness, completeness, and implementability\ncompatibility: Requires spec-kit project structure with .specify\u002F directory\nmetadata:\n  author: github-spec-kit\n  source: spex-gates:commands\u002Fspeckit.spex-gates.review-spec.md\n---\n\n# Reviewing Specifications for Soundness\n\n## Ship Pipeline Guard\n\nIf `.specify\u002F.spex-state` exists and its `status` is `running`, this command is part of an autonomous pipeline. Check the `ask` field:\n- If `ask` is `\"smart\"` or `\"never\"`: suppress all user prompts (do NOT prompt the user interactively), complete the review autonomously, and return immediately so the pipeline can advance.\n- If `ask` is `\"always\"`: prompt the user as normal.\n\n```bash\nif [ -f \".specify\u002F.spex-state\" ]; then\n  STATUS=$(jq -r '.status \u002F\u002F empty' .specify\u002F.spex-state 2>\u002Fdev\u002Fnull)\n  ASK=$(jq -r '.ask \u002F\u002F \"always\"' .specify\u002F.spex-state 2>\u002Fdev\u002Fnull)\n  if [ \"$STATUS\" = \"running\" ] && [ \"$ASK\" != \"always\" ]; then\n    echo \"AUTONOMOUS_MODE=true\"\n  else\n    echo \"AUTONOMOUS_MODE=false\"\n  fi\nelse\n  echo \"AUTONOMOUS_MODE=false\"\nfi\n```\n\nIn autonomous mode: do NOT output a completion summary, do NOT ask \"Shall I proceed?\", do NOT suggest next steps. Complete the review and return.\n\n## Overview\n\nValidate specification quality before implementation begins.\n\nA poor spec leads to confusion, rework, and spec\u002Fcode drift. A sound spec enables smooth implementation.\n\nThis skill checks: completeness, clarity, implementability, and testability.\n\n## When to Use\n\n- After spec creation (before implementation)\n- Before generating implementation plan\n- When spec seems unclear or incomplete\n- Periodically for important specs\n\n## Prerequisites\n\nSpec-kit must be initialized. If `.specify\u002F` directory does not exist, tell the user to run `\u002Fspex:init` first and stop.\n\n## Spec Selection\n\nIf a spec path is provided as an argument, use it directly.\n\nOtherwise, attempt branch-based resolution:\n\n```bash\n.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only 2>\u002Fdev\u002Fnull\n```\n\nIf this succeeds (outputs JSON with `FEATURE_SPEC`), use the resolved spec path. Parse the JSON to extract `FEATURE_SPEC` and `FEATURE_DIR`.\n\nIf this fails (not on a feature branch, no matching spec directory), fall back to interactive selection:\n\n```bash\nfind specs\u002F -name \"spec.md\" -type f 2>\u002Fdev\u002Fnull | head -20\n```\n\n**If specs found:** Present list and ask user to select one using the agent's interactive prompt mechanism (skip in autonomous mode).\n\n**If no specs found:** Inform user:\n```\nNo specs found in specs\u002F directory.\n\nTo create a spec first:\n- Use `speckit-spex-brainstorm` to refine ideas into a spec\n- Use `\u002Fspeckit-specify` to create a spec from clear requirements\n\nCannot review without a spec to review.\n```\n\n## spec-kit Integration\n\nThis skill can use `\u002Fspeckit-*` slash commands when available:\n\n- `\u002Fspeckit-clarify` - Find underspecified areas in the spec\n- `\u002Fspeckit-analyze` - Cross-artifact consistency check (if plan\u002Ftasks exist)\n\n**If `\u002Fspeckit-*` commands are available:**\nUse them to assist with review, but always perform manual review as well.\n\n**If `\u002Fspeckit-*` commands are not available:**\nProceed with manual review only. This is acceptable.\n\n## Review Dimensions\n\n### 1. Completeness\n- All sections filled\n- No TBD or placeholder text\n- All requirements defined\n- Success criteria specified\n\n### 2. Clarity\n- No ambiguous language\n- Concrete, specific requirements\n- Edge cases explicitly defined\n- Error handling specified\n\n### 3. Implementability\n- Can generate implementation plan\n- Dependencies identified\n- Constraints realistic\n- Scope manageable\n\n### 4. Testability\n- Success criteria measurable\n- Requirements verifiable\n- Acceptance criteria clear\n\n## The Process\n\n### 1. Load and Read Spec\n\n**Read the spec:**\n\n```bash\ncat specs\u002F[feature-name]\u002Fspec.md\n```\n\nRead thoroughly, take notes on issues.\n\n### 2. Check Structure\n\n**Required sections (should exist):**\n- [ ] Purpose\u002FOverview\n- [ ] Functional Requirements\n- [ ] Success Criteria\n- [ ] Error Handling\n\n**Recommended sections:**\n- [ ] Non-Functional Requirements\n- [ ] Edge Cases\n- [ ] Dependencies\n- [ ] Constraints\n- [ ] Out of Scope\n\n**If sections missing:**\n- Note which ones\n- Assess if truly needed for this spec\n- Recommend additions\n\n### 3. Review Completeness\n\n**For each section, check:**\n\n**Purpose:**\n- [ ] Clearly states why feature exists\n- [ ] Describes problem being solved\n- [ ] Avoids implementation details\n\n**Functional Requirements:**\n- [ ] Numbered\u002Flisted clearly\n- [ ] Each requirement is specific\n- [ ] No \"TBD\" or placeholders\n- [ ] All aspects covered\n\n**Success Criteria:**\n- [ ] Measurable outcomes defined\n- [ ] Clear completion indicators\n- [ ] Testable assertions\n\n**Error Handling:**\n- [ ] All error cases identified\n- [ ] Handling approach specified\n- [ ] Error messages\u002Fcodes defined\n\n**Edge Cases:**\n- [ ] Boundary conditions listed\n- [ ] Expected behavior specified\n- [ ] Not marked as \"TBD\"\n\n### 4. Check for Ambiguities\n\n**Red flag words\u002Fphrases:**\n- \"should\" (vs \"must\")\n- \"might\", \"could\", \"probably\"\n- \"fast\", \"slow\" (without metrics)\n- \"user-friendly\" (vague)\n- \"handle appropriately\" (non-specific)\n- \"etc.\" (incomplete list)\n- \"similar to...\" (unclear)\n\n**For each ambiguity:**\n- Identify the vague requirement\n- Note what's unclear\n- Suggest specific alternative\n\n### 5. Validate Implementability\n\n**Ask:**\n- Can I generate an implementation plan from this?\n- Are file locations\u002Fcomponents identifiable?\n- Are dependencies clear?\n- Is scope reasonable?\n\n**Check for:**\n- Unknown dependencies\n- Unrealistic constraints\n- Scope too large\n- Conflicting requirements\n\n### 6. Assess Testability\n\n**For each requirement:**\n- How will this be tested?\n- Is the outcome verifiable?\n- Can success be measured?\n\n**For success criteria:**\n- Are they specific enough to test?\n- Can they be automated?\n- Are they objective (not subjective)?\n\n### 7. Check Against Constitution\n\n**If constitution exists:**\n\n```bash\nif [ -f \".specify\u002Fmemory\u002Fconstitution.md\" ]; then\n  cat .specify\u002Fmemory\u002Fconstitution.md\nelse\n  echo \"no-constitution\"\nfi\n```\n\n**Validate:**\n- Does spec follow project principles?\n- Are patterns consistent?\n- Does error handling match standards?\n- Are architectural decisions aligned?\n\n**Note any violations with reasoning.**\n\n### 8. Run Cross-Artifact Consistency Check (Optional)\n\n**If plan or tasks exist and `\u002Fspeckit-analyze` is available:**\n\nInvoke `\u002Fspeckit-analyze` to check consistency between:\n- spec.md (requirements)\n- plan.md (implementation approach)\n- tasks.md (task list)\n\n**Report any mismatches or gaps found.**\n\n### 9. Generate Review Report\n\nOutput the review findings to the console. Do NOT write a `REVIEW-SPEC.md` file. All review information is presented directly in the conversation output.\n\n### 10. Make Recommendation\n\n**If sound (minor issues only):**\n- Ready for implementation\n- Proceed with `\u002Fspeckit-implement`\n\n**If needs work (important issues):**\n- Fix issues before implementing\n- Update spec, re-review\n\n**If major issues:**\n- Not ready for implementation\n- Significant rework needed\n- May need re-brainstorming\n\n### 11. Offer to Fix Issues\n\nAfter presenting the review report:\n\n**Autonomous mode:** Fix all issues (both Important and Minor) automatically without prompting.\n\n**If Important issues exist (with or without Minor):**\n\nPresent a summary of all Important findings as a numbered list, then ask the user (single-select prompt, header: \"Fix\"):\n\n**\"Found N Important issue(s). Fix them now?\"**\n\nOptions (if Minor issues also exist):\n1. **\"Fix Important issues\"**: \"Apply fixes to the spec for all Important findings\"\n2. **\"Fix all (Important + Minor)\"**: \"Also fix Minor issues in the same pass\"\n3. **\"Skip fixes\"**: \"Proceed without fixing, review the findings manually\"\n\nOptions (if no Minor issues):\n1. **\"Fix Important issues\"**: \"Apply fixes to the spec for all Important findings\"\n2. **\"Skip fixes\"**: \"Proceed without fixing, review the findings manually\"\n\nIf the user selects to fix: apply the fixes directly to `spec.md`, then re-display only the changed sections so the user can verify.\n\n**If only Minor issues exist (no Important):**\n\nPresent a summary of all Minor findings, then ask the user (single-select prompt, header: \"Fix\"):\n\n**\"Found N Minor issue(s). Fix them now?\"**\n\nOptions:\n1. **\"Fix Minor issues\"**: \"Apply fixes to the spec\"\n2. **\"Skip fixes\"**: \"Proceed without fixing\"\n\nIf the user selects to fix: apply the fixes directly to `spec.md`, then re-display only the changed sections.\n\n**If no issues:** Skip this step entirely.\n\n## Review Checklist\n\n- [ ] Load and read spec thoroughly\n- [ ] Check structure (all sections present)\n- [ ] Review completeness (no TBD, all covered)\n- [ ] Identify ambiguities (vague language)\n- [ ] Validate implementability (can plan from this)\n- [ ] Assess testability (can verify requirements)\n- [ ] Check constitution alignment (if exists)\n- [ ] Run `\u002Fspeckit-analyze` for cross-artifact consistency (if available)\n- [ ] Generate review report\n- [ ] Make recommendation (ready\u002Fneeds work\u002Fmajor issues)\n- [ ] Offer to fix Important\u002FMinor issues\n\n## Quality Standards\n\n**A sound spec has:**\n- All sections complete\n- No ambiguous language\n- Specific, measurable requirements\n- Identified dependencies\n- Realistic constraints\n- Clear error handling\n- Defined edge cases\n- Testable success criteria\n\n**A poor spec has:**\n- Missing sections\n- Vague language\n- Unmeasurable requirements\n- Unknown dependencies\n- Unrealistic constraints\n- Unclear error handling\n- Ignored edge cases\n- Subjective criteria\n\n## Remember\n\n**Reviewing specs saves time in implementation.**\n\n- 1 hour reviewing spec saves 10 hours debugging\n- Ambiguities caught early prevent rework\n- Complete specs enable smooth TDD\n- Sound specs reduce spec\u002Fcode drift\n\n**Be thorough but not pedantic:**\n- Flag real issues, not nitpicks\n- Focus on what blocks implementation\n- Suggest specific improvements\n- Balance perfection with pragmatism\n\n**The goal is implementability, not perfection.**\n\n## Update Flow State\n\n**MANDATORY: Update flow state.** This MUST run on every exit path, including early returns (e.g., \"already passed\"). Use the flow state script:\n\n```bash\nFLOW_STATE=\".specify\u002Fextensions\u002Fspex-gates\u002Fscripts\u002Fspex-flow-state.sh\" && [ -x \"$FLOW_STATE\" ] && \"$FLOW_STATE\" gate review-spec\n```\n\nThis updates the status line to show `S ✓`.\n\n## Auto-Commit (if enabled)\n\nCheck the git extension's auto-commit config. Only commit if the user has enabled auto-commit for this stage:\n\n```bash\nGIT_CONFIG=\".specify\u002Fextensions\u002Fgit\u002Fgit-config.yml\"\nAUTO_COMMIT=$(yq -r '.auto_commit.after_specify.enabled \u002F\u002F .auto_commit.default \u002F\u002F false' \"$GIT_CONFIG\" 2>\u002Fdev\u002Fnull)\nAUTO_COMMIT=${AUTO_COMMIT:-false}\n```\n\nIf `AUTO_COMMIT` is `true` and there are uncommitted changes:\n\n```bash\nif ! git diff --quiet || ! git diff --cached --quiet || [ -n \"$(git ls-files --others --exclude-standard specs\u002F .specify\u002F 2>\u002Fdev\u002Fnull)\" ]; then\n  git add -u\n  git add specs\u002F .specify\u002F 2>\u002Fdev\u002Fnull || true\n  git commit -m \"review-spec: gate passed, spec updated\n\nAssisted-By: 🤖 Claude Code\"\nfi\n```\n\nDo NOT suggest manual commit commands or next steps. The workflow continues automatically.","# Reviewing Specifications for Soundness\n\n## Ship Pipeline Guard\n\nIf `.specify\u002F.spex-state` exists and its `status` is `running`, this command is part of an autonomous pipeline. Check the `ask` field:\n- If `ask` is `\"smart\"` or `\"never\"`: suppress all user prompts (do NOT prompt the user interactively), complete the review autonomously, and return immediately so the pipeline can advance.\n- If `ask` is `\"always\"`: prompt the user as normal.\n\n```bash\nif [ -f \".specify\u002F.spex-state\" ]; then\n  STATUS=$(jq -r '.status \u002F\u002F empty' .specify\u002F.spex-state 2>\u002Fdev\u002Fnull)\n  ASK=$(jq -r '.ask \u002F\u002F \"always\"' .specify\u002F.spex-state 2>\u002Fdev\u002Fnull)\n  if [ \"$STATUS\" = \"running\" ] && [ \"$ASK\" != \"always\" ]; then\n    echo \"AUTONOMOUS_MODE=true\"\n  else\n    echo \"AUTONOMOUS_MODE=false\"\n  fi\nelse\n  echo \"AUTONOMOUS_MODE=false\"\nfi\n```\n\nIn autonomous mode: do NOT output a completion summary, do NOT ask \"Shall I proceed?\", do NOT suggest next steps. Complete the review and return.\n\n## Overview\n\nValidate specification quality before implementation begins.\n\nA poor spec leads to confusion, rework, and spec\u002Fcode drift. A sound spec enables smooth implementation.\n\nThis skill checks: completeness, clarity, implementability, and testability.\n\n## When to Use\n\n- After spec creation (before implementation)\n- Before generating implementation plan\n- When spec seems unclear or incomplete\n- Periodically for important specs\n\n## Prerequisites\n\nSpec-kit must be initialized. If `.specify\u002F` directory does not exist, tell the user to run `\u002Fspex:init` first and stop.\n\n## Spec Selection\n\nIf a spec path is provided as an argument, use it directly.\n\nOtherwise, attempt branch-based resolution:\n\n```bash\n.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only 2>\u002Fdev\u002Fnull\n```\n\nIf this succeeds (outputs JSON with `FEATURE_SPEC`), use the resolved spec path. Parse the JSON to extract `FEATURE_SPEC` and `FEATURE_DIR`.\n\nIf this fails (not on a feature branch, no matching spec directory), fall back to interactive selection:\n\n```bash\nfind specs\u002F -name \"spec.md\" -type f 2>\u002Fdev\u002Fnull | head -20\n```\n\n**If specs found:** Present list and ask user to select one using the agent's interactive prompt mechanism (skip in autonomous mode).\n\n**If no specs found:** Inform user:\n```\nNo specs found in specs\u002F directory.\n\nTo create a spec first:\n- Use `speckit-spex-brainstorm` to refine ideas into a spec\n- Use `\u002Fspeckit-specify` to create a spec from clear requirements\n\nCannot review without a spec to review.\n```\n\n## spec-kit Integration\n\nThis skill can use `\u002Fspeckit-*` slash commands when available:\n\n- `\u002Fspeckit-clarify` - Find underspecified areas in the spec\n- `\u002Fspeckit-analyze` - Cross-artifact consistency check (if plan\u002Ftasks exist)\n\n**If `\u002Fspeckit-*` commands are available:**\nUse them to assist with review, but always perform manual review as well.\n\n**If `\u002Fspeckit-*` commands are not available:**\nProceed with manual review only. This is acceptable.\n\n## Review Dimensions\n\n### 1. Completeness\n- All sections filled\n- No TBD or placeholder text\n- All requirements defined\n- Success criteria specified\n\n### 2. Clarity\n- No ambiguous language\n- Concrete, specific requirements\n- Edge cases explicitly defined\n- Error handling specified\n\n### 3. Implementability\n- Can generate implementation plan\n- Dependencies identified\n- Constraints realistic\n- Scope manageable\n\n### 4. Testability\n- Success criteria measurable\n- Requirements verifiable\n- Acceptance criteria clear\n\n## The Process\n\n### 1. Load and Read Spec\n\n**Read the spec:**\n\n```bash\ncat specs\u002F[feature-name]\u002Fspec.md\n```\n\nRead thoroughly, take notes on issues.\n\n### 2. Check Structure\n\n**Required sections (should exist):**\n- [ ] Purpose\u002FOverview\n- [ ] Functional Requirements\n- [ ] Success Criteria\n- [ ] Error Handling\n\n**Recommended sections:**\n- [ ] Non-Functional Requirements\n- [ ] Edge Cases\n- [ ] Dependencies\n- [ ] Constraints\n- [ ] Out of Scope\n\n**If sections missing:**\n- Note which ones\n- Assess if truly needed for this spec\n- Recommend additions\n\n### 3. Review Completeness\n\n**For each section, check:**\n\n**Purpose:**\n- [ ] Clearly states why feature exists\n- [ ] Describes problem being solved\n- [ ] Avoids implementation details\n\n**Functional Requirements:**\n- [ ] Numbered\u002Flisted clearly\n- [ ] Each requirement is specific\n- [ ] No \"TBD\" or placeholders\n- [ ] All aspects covered\n\n**Success Criteria:**\n- [ ] Measurable outcomes defined\n- [ ] Clear completion indicators\n- [ ] Testable assertions\n\n**Error Handling:**\n- [ ] All error cases identified\n- [ ] Handling approach specified\n- [ ] Error messages\u002Fcodes defined\n\n**Edge Cases:**\n- [ ] Boundary conditions listed\n- [ ] Expected behavior specified\n- [ ] Not marked as \"TBD\"\n\n### 4. Check for Ambiguities\n\n**Red flag words\u002Fphrases:**\n- \"should\" (vs \"must\")\n- \"might\", \"could\", \"probably\"\n- \"fast\", \"slow\" (without metrics)\n- \"user-friendly\" (vague)\n- \"handle appropriately\" (non-specific)\n- \"etc.\" (incomplete list)\n- \"similar to...\" (unclear)\n\n**For each ambiguity:**\n- Identify the vague requirement\n- Note what's unclear\n- Suggest specific alternative\n\n### 5. Validate Implementability\n\n**Ask:**\n- Can I generate an implementation plan from this?\n- Are file locations\u002Fcomponents identifiable?\n- Are dependencies clear?\n- Is scope reasonable?\n\n**Check for:**\n- Unknown dependencies\n- Unrealistic constraints\n- Scope too large\n- Conflicting requirements\n\n### 6. Assess Testability\n\n**For each requirement:**\n- How will this be tested?\n- Is the outcome verifiable?\n- Can success be measured?\n\n**For success criteria:**\n- Are they specific enough to test?\n- Can they be automated?\n- Are they objective (not subjective)?\n\n### 7. Check Against Constitution\n\n**If constitution exists:**\n\n```bash\nif [ -f \".specify\u002Fmemory\u002Fconstitution.md\" ]; then\n  cat .specify\u002Fmemory\u002Fconstitution.md\nelse\n  echo \"no-constitution\"\nfi\n```\n\n**Validate:**\n- Does spec follow project principles?\n- Are patterns consistent?\n- Does error handling match standards?\n- Are architectural decisions aligned?\n\n**Note any violations with reasoning.**\n\n### 8. Run Cross-Artifact Consistency Check (Optional)\n\n**If plan or tasks exist and `\u002Fspeckit-analyze` is available:**\n\nInvoke `\u002Fspeckit-analyze` to check consistency between:\n- spec.md (requirements)\n- plan.md (implementation approach)\n- tasks.md (task list)\n\n**Report any mismatches or gaps found.**\n\n### 9. Generate Review Report\n\nOutput the review findings to the console. Do NOT write a `REVIEW-SPEC.md` file. All review information is presented directly in the conversation output.\n\n### 10. Make Recommendation\n\n**If sound (minor issues only):**\n- Ready for implementation\n- Proceed with `\u002Fspeckit-implement`\n\n**If needs work (important issues):**\n- Fix issues before implementing\n- Update spec, re-review\n\n**If major issues:**\n- Not ready for implementation\n- Significant rework needed\n- May need re-brainstorming\n\n### 11. Offer to Fix Issues\n\nAfter presenting the review report:\n\n**Autonomous mode:** Fix all issues (both Important and Minor) automatically without prompting.\n\n**If Important issues exist (with or without Minor):**\n\nPresent a summary of all Important findings as a numbered list, then ask the user (single-select prompt, header: \"Fix\"):\n\n**\"Found N Important issue(s). Fix them now?\"**\n\nOptions (if Minor issues also exist):\n1. **\"Fix Important issues\"**: \"Apply fixes to the spec for all Important findings\"\n2. **\"Fix all (Important + Minor)\"**: \"Also fix Minor issues in the same pass\"\n3. **\"Skip fixes\"**: \"Proceed without fixing, review the findings manually\"\n\nOptions (if no Minor issues):\n1. **\"Fix Important issues\"**: \"Apply fixes to the spec for all Important findings\"\n2. **\"Skip fixes\"**: \"Proceed without fixing, review the findings manually\"\n\nIf the user selects to fix: apply the fixes directly to `spec.md`, then re-display only the changed sections so the user can verify.\n\n**If only Minor issues exist (no Important):**\n\nPresent a summary of all Minor findings, then ask the user (single-select prompt, header: \"Fix\"):\n\n**\"Found N Minor issue(s). Fix them now?\"**\n\nOptions:\n1. **\"Fix Minor issues\"**: \"Apply fixes to the spec\"\n2. **\"Skip fixes\"**: \"Proceed without fixing\"\n\nIf the user selects to fix: apply the fixes directly to `spec.md`, then re-display only the changed sections.\n\n**If no issues:** Skip this step entirely.\n\n## Review Checklist\n\n- [ ] Load and read spec thoroughly\n- [ ] Check structure (all sections present)\n- [ ] Review completeness (no TBD, all covered)\n- [ ] Identify ambiguities (vague language)\n- [ ] Validate implementability (can plan from this)\n- [ ] Assess testability (can verify requirements)\n- [ ] Check constitution alignment (if exists)\n- [ ] Run `\u002Fspeckit-analyze` for cross-artifact consistency (if available)\n- [ ] Generate review report\n- [ ] Make recommendation (ready\u002Fneeds work\u002Fmajor issues)\n- [ ] Offer to fix Important\u002FMinor issues\n\n## Quality Standards\n\n**A sound spec has:**\n- All sections complete\n- No ambiguous language\n- Specific, measurable requirements\n- Identified dependencies\n- Realistic constraints\n- Clear error handling\n- Defined edge cases\n- Testable success criteria\n\n**A poor spec has:**\n- Missing sections\n- Vague language\n- Unmeasurable requirements\n- Unknown dependencies\n- Unrealistic constraints\n- Unclear error handling\n- Ignored edge cases\n- Subjective criteria\n\n## Remember\n\n**Reviewing specs saves time in implementation.**\n\n- 1 hour reviewing spec saves 10 hours debugging\n- Ambiguities caught early prevent rework\n- Complete specs enable smooth TDD\n- Sound specs reduce spec\u002Fcode drift\n\n**Be thorough but not pedantic:**\n- Flag real issues, not nitpicks\n- Focus on what blocks implementation\n- Suggest specific improvements\n- Balance perfection with pragmatism\n\n**The goal is implementability, not perfection.**\n\n## Update Flow State\n\n**MANDATORY: Update flow state.** This MUST run on every exit path, including early returns (e.g., \"already passed\"). Use the flow state script:\n\n```bash\nFLOW_STATE=\".specify\u002Fextensions\u002Fspex-gates\u002Fscripts\u002Fspex-flow-state.sh\" && [ -x \"$FLOW_STATE\" ] && \"$FLOW_STATE\" gate review-spec\n```\n\nThis updates the status line to show `S ✓`.\n\n## Auto-Commit (if enabled)\n\nCheck the git extension's auto-commit config. Only commit if the user has enabled auto-commit for this stage:\n\n```bash\nGIT_CONFIG=\".specify\u002Fextensions\u002Fgit\u002Fgit-config.yml\"\nAUTO_COMMIT=$(yq -r '.auto_commit.after_specify.enabled \u002F\u002F .auto_commit.default \u002F\u002F false' \"$GIT_CONFIG\" 2>\u002Fdev\u002Fnull)\nAUTO_COMMIT=${AUTO_COMMIT:-false}\n```\n\nIf `AUTO_COMMIT` is `true` and there are uncommitted changes:\n\n```bash\nif ! git diff --quiet || ! git diff --cached --quiet || [ -n \"$(git ls-files --others --exclude-standard specs\u002F .specify\u002F 2>\u002Fdev\u002Fnull)\" ]; then\n  git add -u\n  git add specs\u002F .specify\u002F 2>\u002Fdev\u002Fnull || true\n  git commit -m \"review-spec: gate passed, spec updated\n\nAssisted-By: 🤖 Claude Code\"\nfi\n```\n\nDo NOT suggest manual commit commands or next steps. The workflow continues automatically.",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","spex-gates:commands\u002Fspeckit.spex-gates.review-spec.md","Requires spec-kit project structure with .specify\u002F directory","main","bf2af6077064ba2889ff548f6745f7a89096b9e7",".specify\u002Fextensions\u002Fspex-gates\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-gates-review-spec",0,"https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api","https:\u002F\u002Fgithub.com\u002Fjimmidyson","https:\u002F\u002Feng.d2iq.com\u002F","Principal Engineer at Nutanix ","2026-11-14 13:13:21",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add jimmidyson\u002Fkcp-cluster-api --skill speckit-spex-gates-review-spec",{"tool":43,"command":44},"bunx","bunx skills add jimmidyson\u002Fkcp-cluster-api --skill speckit-spex-gates-review-spec",{"tool":46,"command":47},"pnpm","pnpm dlx skills add jimmidyson\u002Fkcp-cluster-api --skill speckit-spex-gates-review-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-gates\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-gates-review-spec\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7AJ1CGXH74ZSZPQ1DP8RQA2","speckit-spex-worktrees-manage","Manage git worktrees for isolated feature development - create after specify, list active worktrees, finish and cleanup","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-worktrees\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-worktrees-manage\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7AJ18QSWTJ2SAGX0CWJGTRF","speckit-spex-teams-research","Parallel codebase research for planning via parallel agent teams","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-teams\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-teams-research\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7AJ14V817SCP3YPDSR9E968","speckit-spex-teams-orchestrate","Unified team orchestration: parallel task implementation with spec guardian review pattern via parallel agent teams","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-teams\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-teams-orchestrate\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7AJ12G1WGNDSGBVX73ADMTR","speckit-spex-teams-implement","Parallel implementation via agent teams for independent tasks","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-teams\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-teams-implement\u002FSKILL.md",[],[],{"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":19},"01M7AJ0ZAAP2EDC2DV873YDND9","speckit-spex-gates-verify","Final verification gate: tests, code hygiene, spec compliance, and drift check","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-gates\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-gates-verify\u002FSKILL.md",[],[],{"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":93,"publishedAt":19},"01M7AJ0W0J07D6X6M77FAYJYPE","speckit-spex-gates-stamp","Final gate before completion - invokes verification for tests, code hygiene, spec compliance, and drift check","https:\u002F\u002Fgithub.com\u002Fjimmidyson\u002Fkcp-cluster-api\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fspex-gates\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-spex-gates-stamp\u002FSKILL.md",[],[]]