[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AHZX2PVB07W7F0S0QKRA9B":3,"skill-same:01M7AHZX2PVB07W7F0S0QKRA9B":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},"01M7AHZX2PVB07W7F0S0QKRA9B","speckit-spex-gates-review-plan",null,"Post-planning quality validation with coverage matrix, red flag scanning, and task quality enforcement","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-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speckit-spex-gates-review-plan\ndescription: Post-planning quality validation with coverage matrix, red flag scanning, and task quality enforcement\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-plan.md\n---\n\n# Post-Planning Quality Validation\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\nThis skill validates plan and task quality after `\u002Fspeckit-plan` and `\u002Fspeckit-tasks` have run. It checks coverage, scans for red flags, and enforces task quality standards.\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**Both plan.md and tasks.md MUST exist before running this skill.** If either is missing, stop with an error:\n\n```bash\nSPEC_DIR=\"specs\u002F[feature-name]\"\n[ -f \"$SPEC_DIR\u002Fplan.md\" ] && echo \"plan.md found\" || echo \"ERROR: plan.md missing - run \u002Fspeckit-plan first\"\n[ -f \"$SPEC_DIR\u002Ftasks.md\" ] && echo \"tasks.md found\" || echo \"ERROR: tasks.md missing - run \u002Fspeckit-tasks first\"\n```\n\nIf either file is missing, stop and instruct the user to generate the missing artifact.\n\n## 0. Scope Check\n\nBefore detailed validation, check whether the plan attempts to cover multiple independent subsystems in a single document. Indicators:\n\n- Tasks span subsystems with no shared interfaces or dependencies\n- The plan has distinct groups of tasks that could each produce working software independently\n- File changes cluster into unrelated areas of the codebase\n\nIf the plan covers multiple independent subsystems, flag it: \"This plan may benefit from being split into separate plans, one per subsystem. Each plan should produce working, testable software on its own.\"\n\nThis is advisory, not blocking. Some plans legitimately span subsystems.\n\n## 1. Task Quality Enforcement\n\nAfter tasks.md exists, verify every task meets these criteria:\n\n- **Actionable**: Clear what to do (not \"figure out...\" or \"investigate...\")\n- **Testable**: Can verify completion objectively\n- **Atomic**: One clear outcome per task\n- **Ordered**: Dependencies between tasks are respected, phases are sequenced correctly\n- **Right-sized**: Setup, configuration, scaffolding, and documentation steps are folded into the task whose deliverable needs them. Split only where a reviewer could meaningfully reject one task while approving its neighbor. Each task ends with an independently testable deliverable.\n\nAlso check:\n- Every task specifies concrete file paths (not \"somewhere\" or \"TBD\")\n- Phase ordering is logical (setup before core, tests before integration)\n- No tasks duplicate work already covered by other tasks\n- Tasks that consume outputs from earlier tasks declare explicit **Interfaces** (function names, parameter types, return types). A task's implementer sees only their own task; the Interfaces block is how they learn the names and types neighboring tasks use.\n- If the spec has project-wide requirements (version floors, dependency limits, naming rules, platform requirements), the plan includes a **Global Constraints** section with those values copied verbatim from the spec. Every task implicitly inherits this section.\n\nVerify the plan includes a file structure mapping:\n- Files to be created or modified are listed with their responsibilities\n- Each file has one clear responsibility (not vague \"utils\" or \"helpers\" without defined scope)\n- Design units have clear boundaries and well-defined interfaces\n- In existing codebases, the plan follows established patterns rather than unilaterally restructuring\n\nIf the plan lacks a file structure mapping, note it as a gap: tasks without a file map are harder to verify for completeness and overlap.\n\nIf tasks fail these checks, note the issues and suggest refinements.\n\n## 2. Coverage Matrix\n\nProduce a coverage matrix mapping every spec requirement to its implementing tasks:\n\n```\nRequirement 1 -> Tasks [X,Y]\nRequirement 2 -> Tasks [Z]\nNFR 1         -> Tasks [W]\n...\n```\n\nFlag any requirement without task coverage. All requirements must have at least one implementing task.\n\nAlso verify:\n- Every error case in the spec has a handling approach\n- Every edge case from the spec is addressed\n- Success criteria have verification approaches\n\n## 3. Red Flag Scanning\n\nSearch plan.md and tasks.md for vague or incomplete language:\n\n```bash\nSPEC_DIR=\"specs\u002F[feature-name]\"\nrg -i \"figure out|tbd|todo|implement later|somehow|somewhere|not sure|maybe|probably|add appropriate|add validation|handle edge cases|similar to task\" \"$SPEC_DIR\u002Fplan.md\" \"$SPEC_DIR\u002Ftasks.md\" || echo \"No red flags found\"\n```\n\nReview any matches:\n- \"Figure out...\" = missing research, needs concrete approach\n- \"TBD\" \u002F \"TODO\" = incomplete planning, must be resolved\n- \"Implement later\" = deferred work, scope explicitly\n- \"Add appropriate error handling\" \u002F \"add validation\" \u002F \"handle edge cases\" = vague placeholders, must show actual code\n- \"Write tests for the above\" (without actual test code) = test code must be included\n- \"Similar to Task N\" = repeat the code, the engineer may read tasks out of order\n- Steps that describe what to do without showing how = code blocks required for code steps\n- Missing file paths = tasks are not actionable\n\n## 4. Type and Name Consistency\n\nCheck that types, method signatures, property names, and function names used across tasks are consistent:\n\n- If a function is called `clearLayers()` in Task 3, it must not be called `clearFullLayers()` in Task 7\n- If a type is defined in an early task, later tasks must reference the same type name\n- If a constant or config key is introduced, verify spelling is consistent across all tasks\n- If an API endpoint path is defined, verify all references use the same path\n\nInconsistencies between tasks are plan bugs that will become code bugs during implementation.\n\n## 5. NFR Validation\n\nFor each non-functional requirement in the spec, verify the plan includes:\n- A concrete measurement method (not just \"should be fast\")\n- A validation approach (how will you verify the NFR is met?)\n- Acceptance thresholds where applicable\n\nIf any NFR lacks a measurement method, flag it.\n\n## 6. Present Results\n\nReport to the user:\n- Task quality check results (pass\u002Fissues)\n- Coverage matrix summary\n- Red flag scan results\n- NFR validation results\n\n## 7. Offer Remediation\n\nAfter presenting results, collect ALL findings from steps 0-4 into a numbered list. Include both blocking and non-blocking issues. Present them as a consolidated findings summary:\n\n```\nFindings:\n\n  1. [BLOCKING] Task T003 is not actionable: \"figure out auth approach\"\n  2. [advisory] Plan may benefit from splitting (2 independent subsystems)\n  3. [gap] FR-007 has no implementing task in the coverage matrix\n  4. [red-flag] tasks.md line 42: \"TBD\" placeholder\n  5. [nfr] NFR-002 \"response time \u003C 200ms\" has no measurement method\n```\n\nThen ask the user how to proceed (skip in autonomous mode, default to \"Fix all\"):\n\n{harness:interactive-choice}:\n- header: \"Findings\"\n- Options (single-select):\n  - \"Fix all\": \"Address every finding automatically\"\n  - \"Let me pick\": \"Select specific findings to fix (you can add comments)\"\n  - \"Skip\": \"Proceed without changes\"\n\n**If \"Fix all\"**: Apply fixes to plan.md and\u002For tasks.md for each finding, then re-run the relevant checks to confirm resolution.\n\n**If \"Let me pick\"**: Present a multi-select prompt, listing up to 4 findings as options (if more than 4, batch them across multiple rounds). Each option's label is the short finding (e.g., \"#1 Task T003 not actionable\") and the description is the detail. The user can select which to fix and use \"Other\" to add comments or instructions for specific findings.\n\nAfter the user selects findings, apply fixes to plan.md and\u002For tasks.md. For each selected finding:\n1. Read the user's comment (if any) to understand their intent\n2. Make the minimal targeted edit to resolve the finding\n3. Report what was changed\n\nAfter all selected fixes are applied, re-present any remaining unaddressed findings as informational (no further prompting).\n\n**If \"Skip\"**: Proceed without changes. Note that blocking issues remain unresolved.\n\n## 8. Suggest Collaboration Skills\n\nSkip this step in autonomous mode.\n\nAfter plan review completes, check whether the plan has characteristics that benefit from collaboration skills. Suggest them when ANY of these apply:\n\n- The plan has **multiple phases** or the tasks group into distinct stages\n- The plan mentions **reviewers, stakeholders, or collaborators**\n- The feature touches **multiple subsystems** (flagged in step 0)\n\nWhen applicable, print:\n\n```\nBefore implementation, consider:\n  \u002Fspeckit-spex-collab-phase-split  - propose how to split into separate PRs\n  \u002Fspeckit-spex-collab-reviewers    - generate a review guide for PR reviewers\n```\n\nThis is informational, not blocking. Do not prompt or gate on it.\n\n## 9. Update Flow State\n\n**MANDATORY: Update flow state.** This MUST run on every exit path, including early returns (e.g., \"already passed\", \"no findings\"). 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-plan\n```\n\nThis updates the status line to show `P ✓`.\n\n## 10. 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=$(yq -r '.auto_commit.after_tasks.enabled \u002F\u002F .auto_commit.default \u002F\u002F false' \"$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-plan: gate passed, artifacts updated\n\nAssisted-By: 🤖 Claude Code\"\nfi\n```\n\nDo NOT suggest manual commit commands or next steps. The workflow continues automatically (either via the ship pipeline or the user's next command).\n\n## Integration\n\n**This command is invoked by:**\n- The spex-gates extension hook for `after_tasks`\n- Users directly via `speckit.spex-gates.review-plan`\n\n**This command invokes:**\n- Prerequisite check for `.specify\u002F` directory","# Post-Planning Quality Validation\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\nThis skill validates plan and task quality after `\u002Fspeckit-plan` and `\u002Fspeckit-tasks` have run. It checks coverage, scans for red flags, and enforces task quality standards.\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**Both plan.md and tasks.md MUST exist before running this skill.** If either is missing, stop with an error:\n\n```bash\nSPEC_DIR=\"specs\u002F[feature-name]\"\n[ -f \"$SPEC_DIR\u002Fplan.md\" ] && echo \"plan.md found\" || echo \"ERROR: plan.md missing - run \u002Fspeckit-plan first\"\n[ -f \"$SPEC_DIR\u002Ftasks.md\" ] && echo \"tasks.md found\" || echo \"ERROR: tasks.md missing - run \u002Fspeckit-tasks first\"\n```\n\nIf either file is missing, stop and instruct the user to generate the missing artifact.\n\n## 0. Scope Check\n\nBefore detailed validation, check whether the plan attempts to cover multiple independent subsystems in a single document. Indicators:\n\n- Tasks span subsystems with no shared interfaces or dependencies\n- The plan has distinct groups of tasks that could each produce working software independently\n- File changes cluster into unrelated areas of the codebase\n\nIf the plan covers multiple independent subsystems, flag it: \"This plan may benefit from being split into separate plans, one per subsystem. Each plan should produce working, testable software on its own.\"\n\nThis is advisory, not blocking. Some plans legitimately span subsystems.\n\n## 1. Task Quality Enforcement\n\nAfter tasks.md exists, verify every task meets these criteria:\n\n- **Actionable**: Clear what to do (not \"figure out...\" or \"investigate...\")\n- **Testable**: Can verify completion objectively\n- **Atomic**: One clear outcome per task\n- **Ordered**: Dependencies between tasks are respected, phases are sequenced correctly\n- **Right-sized**: Setup, configuration, scaffolding, and documentation steps are folded into the task whose deliverable needs them. Split only where a reviewer could meaningfully reject one task while approving its neighbor. Each task ends with an independently testable deliverable.\n\nAlso check:\n- Every task specifies concrete file paths (not \"somewhere\" or \"TBD\")\n- Phase ordering is logical (setup before core, tests before integration)\n- No tasks duplicate work already covered by other tasks\n- Tasks that consume outputs from earlier tasks declare explicit **Interfaces** (function names, parameter types, return types). A task's implementer sees only their own task; the Interfaces block is how they learn the names and types neighboring tasks use.\n- If the spec has project-wide requirements (version floors, dependency limits, naming rules, platform requirements), the plan includes a **Global Constraints** section with those values copied verbatim from the spec. Every task implicitly inherits this section.\n\nVerify the plan includes a file structure mapping:\n- Files to be created or modified are listed with their responsibilities\n- Each file has one clear responsibility (not vague \"utils\" or \"helpers\" without defined scope)\n- Design units have clear boundaries and well-defined interfaces\n- In existing codebases, the plan follows established patterns rather than unilaterally restructuring\n\nIf the plan lacks a file structure mapping, note it as a gap: tasks without a file map are harder to verify for completeness and overlap.\n\nIf tasks fail these checks, note the issues and suggest refinements.\n\n## 2. Coverage Matrix\n\nProduce a coverage matrix mapping every spec requirement to its implementing tasks:\n\n```\nRequirement 1 -> Tasks [X,Y]\nRequirement 2 -> Tasks [Z]\nNFR 1         -> Tasks [W]\n...\n```\n\nFlag any requirement without task coverage. All requirements must have at least one implementing task.\n\nAlso verify:\n- Every error case in the spec has a handling approach\n- Every edge case from the spec is addressed\n- Success criteria have verification approaches\n\n## 3. Red Flag Scanning\n\nSearch plan.md and tasks.md for vague or incomplete language:\n\n```bash\nSPEC_DIR=\"specs\u002F[feature-name]\"\nrg -i \"figure out|tbd|todo|implement later|somehow|somewhere|not sure|maybe|probably|add appropriate|add validation|handle edge cases|similar to task\" \"$SPEC_DIR\u002Fplan.md\" \"$SPEC_DIR\u002Ftasks.md\" || echo \"No red flags found\"\n```\n\nReview any matches:\n- \"Figure out...\" = missing research, needs concrete approach\n- \"TBD\" \u002F \"TODO\" = incomplete planning, must be resolved\n- \"Implement later\" = deferred work, scope explicitly\n- \"Add appropriate error handling\" \u002F \"add validation\" \u002F \"handle edge cases\" = vague placeholders, must show actual code\n- \"Write tests for the above\" (without actual test code) = test code must be included\n- \"Similar to Task N\" = repeat the code, the engineer may read tasks out of order\n- Steps that describe what to do without showing how = code blocks required for code steps\n- Missing file paths = tasks are not actionable\n\n## 4. Type and Name Consistency\n\nCheck that types, method signatures, property names, and function names used across tasks are consistent:\n\n- If a function is called `clearLayers()` in Task 3, it must not be called `clearFullLayers()` in Task 7\n- If a type is defined in an early task, later tasks must reference the same type name\n- If a constant or config key is introduced, verify spelling is consistent across all tasks\n- If an API endpoint path is defined, verify all references use the same path\n\nInconsistencies between tasks are plan bugs that will become code bugs during implementation.\n\n## 5. NFR Validation\n\nFor each non-functional requirement in the spec, verify the plan includes:\n- A concrete measurement method (not just \"should be fast\")\n- A validation approach (how will you verify the NFR is met?)\n- Acceptance thresholds where applicable\n\nIf any NFR lacks a measurement method, flag it.\n\n## 6. Present Results\n\nReport to the user:\n- Task quality check results (pass\u002Fissues)\n- Coverage matrix summary\n- Red flag scan results\n- NFR validation results\n\n## 7. Offer Remediation\n\nAfter presenting results, collect ALL findings from steps 0-4 into a numbered list. Include both blocking and non-blocking issues. Present them as a consolidated findings summary:\n\n```\nFindings:\n\n  1. [BLOCKING] Task T003 is not actionable: \"figure out auth approach\"\n  2. [advisory] Plan may benefit from splitting (2 independent subsystems)\n  3. [gap] FR-007 has no implementing task in the coverage matrix\n  4. [red-flag] tasks.md line 42: \"TBD\" placeholder\n  5. [nfr] NFR-002 \"response time \u003C 200ms\" has no measurement method\n```\n\nThen ask the user how to proceed (skip in autonomous mode, default to \"Fix all\"):\n\n{harness:interactive-choice}:\n- header: \"Findings\"\n- Options (single-select):\n  - \"Fix all\": \"Address every finding automatically\"\n  - \"Let me pick\": \"Select specific findings to fix (you can add comments)\"\n  - \"Skip\": \"Proceed without changes\"\n\n**If \"Fix all\"**: Apply fixes to plan.md and\u002For tasks.md for each finding, then re-run the relevant checks to confirm resolution.\n\n**If \"Let me pick\"**: Present a multi-select prompt, listing up to 4 findings as options (if more than 4, batch them across multiple rounds). Each option's label is the short finding (e.g., \"#1 Task T003 not actionable\") and the description is the detail. The user can select which to fix and use \"Other\" to add comments or instructions for specific findings.\n\nAfter the user selects findings, apply fixes to plan.md and\u002For tasks.md. For each selected finding:\n1. Read the user's comment (if any) to understand their intent\n2. Make the minimal targeted edit to resolve the finding\n3. Report what was changed\n\nAfter all selected fixes are applied, re-present any remaining unaddressed findings as informational (no further prompting).\n\n**If \"Skip\"**: Proceed without changes. Note that blocking issues remain unresolved.\n\n## 8. Suggest Collaboration Skills\n\nSkip this step in autonomous mode.\n\nAfter plan review completes, check whether the plan has characteristics that benefit from collaboration skills. Suggest them when ANY of these apply:\n\n- The plan has **multiple phases** or the tasks group into distinct stages\n- The plan mentions **reviewers, stakeholders, or collaborators**\n- The feature touches **multiple subsystems** (flagged in step 0)\n\nWhen applicable, print:\n\n```\nBefore implementation, consider:\n  \u002Fspeckit-spex-collab-phase-split  - propose how to split into separate PRs\n  \u002Fspeckit-spex-collab-reviewers    - generate a review guide for PR reviewers\n```\n\nThis is informational, not blocking. Do not prompt or gate on it.\n\n## 9. Update Flow State\n\n**MANDATORY: Update flow state.** This MUST run on every exit path, including early returns (e.g., \"already passed\", \"no findings\"). 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-plan\n```\n\nThis updates the status line to show `P ✓`.\n\n## 10. 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=$(yq -r '.auto_commit.after_tasks.enabled \u002F\u002F .auto_commit.default \u002F\u002F false' \"$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-plan: gate passed, artifacts updated\n\nAssisted-By: 🤖 Claude Code\"\nfi\n```\n\nDo NOT suggest manual commit commands or next steps. The workflow continues automatically (either via the ship pipeline or the user's next command).\n\n## Integration\n\n**This command is invoked by:**\n- The spex-gates extension hook for `after_tasks`\n- Users directly via `speckit.spex-gates.review-plan`\n\n**This command invokes:**\n- Prerequisite check for `.specify\u002F` directory",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","spex-gates:commands\u002Fspeckit.spex-gates.review-plan.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-plan",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-plan",{"tool":43,"command":44},"bunx","bunx skills add jimmidyson\u002Fkcp-cluster-api --skill speckit-spex-gates-review-plan",{"tool":46,"command":47},"pnpm","pnpm dlx skills add jimmidyson\u002Fkcp-cluster-api --skill speckit-spex-gates-review-plan","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-plan\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",[],[]]