[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R7SBDGT9KFCV2DVKBMA5P":3,"skill-same:01M79R7SBDGT9KFCV2DVKBMA5P":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79R7SBDGT9KFCV2DVKBMA5P","conductor-validate-review",null,"Validate a code review document against the repository, finding by finding, before it becomes a Conductor remediation programme. Use when the user asks to validate a review in conductor\u002Freviews\u002F.","newtonmunene99\u002Fclaudekit","newtonmunene99","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29271333?v=4","01M79R6BB4AWRGZNKNSRC1SF50","Newton Munene","01M79R6BBWZPWCNJBW8VXZMD4Z",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fconductor\u002Fskills\u002Fconductor-validate-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: conductor-validate-review\ndescription: Validate a code review document against the repository, finding by finding, before it becomes a Conductor remediation programme. Use when the user asks to validate a review in conductor\u002Freviews\u002F.\n---\n\nFollow `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fconductor-protocol.md` for file resolution, git policy, and output style.\n\n# Conductor Validate Review\n\n## Claude Tool Mapping\n\n- **User Prompt Protocol** for structured user prompts (AskUserQuestion tool when available, else numbered options in chat; wait for reply)\n- **Read** \u002F **Write** \u002F **Edit** for file operations\n- **Bash** for shell commands\n- **Grep** \u002F **Glob** for search\n- Use relative paths under `conductor\u002F` for all Conductor artifacts\n\n\n## Output Style\n\nFollow **Agent Output Style** in templates\u002Fconductor-protocol.md. Line 1 = validation status and count of findings checked.\n\n## Plugin Template Path\n\nLocate installed plugin templates:\n1. `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002F`\n2. Fallback (local dev): `.\u002Fplugins\u002Fconductor\u002Ftemplates\u002F` from claudekit repo root\n3. Fallback: `.\u002Fplugins\u002Fconductor\u002Ftemplates\u002F` from repo root\n\n## 1.0 SYSTEM DIRECTIVE\n\nValidate a review document in **Reviews Directory** against the codebase. Produce a validation addendum before `\u002Fconductor:conductor-new-track` programme creation.\n\n**Read-only** until writing validation output. Git write operations follow **Git Write Policy**.\n\n---\n\n## 2.0 VALIDATION PROTOCOL\n\n### 2.1 Resolve review\n\n1. If `{{args}}` is non-empty, use as review path (relative to repo root or under `conductor\u002Freviews\u002F`).\n2. Otherwise **User Prompt Protocol** — header \"Review path\", type text, placeholder `conductor\u002Freviews\u002Ffoo_YYYYMMDD-review.md`.\n3. Verify file exists via Universal File Resolution.\n\n### 2.2 Extract findings\n\nParse review for:\n\n- **Location:** lines with file paths and line numbers\n- **Severity** claims (Critical, High, ARCH-N, §X.Y)\n- Inline backtick paths in finding bodies\n\nLoad `templates\u002Freview-document-header.md` for expected structure.\n\n### 2.3 Verify paths\n\n1. Run `python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fconductor_state.py\" verify-paths \u003Creview path>` (**Deterministic Plumbing Protocol**). It checks every cited path and `file:line` reference and suggests corrections for missing files.\n2. For paths marked `verified` with a line ref, `Read` the cited lines to confirm the symbol\u002Fcontext still matches the claim.\n3. Record: **Verified** | **Wrong path** (use the script's `suggestions`) | **Not found**\n4. Fallback without `python3`: `test -f` \u002F `test -d`, glob variants, and `Read` for line refs.\n\n### 2.4 Verify severity claims\n\nFor each finding with code citation:\n\n1. Read cited code\n2. Mark: **Confirmed** | **Partially confirmed** | **Disputed** | **Obsolete**\n3. Drop claims you cannot validate — do not flag uncertain items\n\n### 2.5 Write validation addendum\n\nDefault: sibling file `\u003Creview-stem>_validation.md` (preserves original review).\n\n**User Prompt Protocol** if user prefers append to review instead.\n\nAddendum structure:\n\n```markdown\n# Validation — \u003Creview title>\n\n**Source:** `conductor\u002Freviews\u002F\u003Cfile>`\n**Validated:** YYYY-MM-DD\n\n## Path verification\n\n| Finding | Cited path | Status | Correction |\n| ------- | ---------- | ------ | ---------- |\n\n## Severity confirmation\n\n| ID | Verdict | Notes |\n| -- | ------- | ----- |\n\n## Blocking issues\n\nList wrong paths or disputed Critical findings that must resolve before programme creation.\n\n## Programme readiness\n\n**Ready** | **Not ready** — \u003Creason>\n```\n\n### 2.6 Halt rules\n\n- **Blocking wrong paths** on Critical findings → announce halt; programme creation blocked until fixed\n- User may opt out via the **User Prompt Protocol** when running `\u002Fconductor:conductor-new-track` (document opt-out in programme metadata)\n\n### 2.7 Completion\n\nAnnounce: \"Validation written to `\u003Cpath>`. Next: `\u002Fconductor:conductor-new-track` from this review.\"\n","Follow `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fconductor-protocol.md` for file resolution, git policy, and output style.\n\n# Conductor Validate Review\n\n## Claude Tool Mapping\n\n- **User Prompt Protocol** for structured user prompts (AskUserQuestion tool when available, else numbered options in chat; wait for reply)\n- **Read** \u002F **Write** \u002F **Edit** for file operations\n- **Bash** for shell commands\n- **Grep** \u002F **Glob** for search\n- Use relative paths under `conductor\u002F` for all Conductor artifacts\n\n\n## Output Style\n\nFollow **Agent Output Style** in templates\u002Fconductor-protocol.md. Line 1 = validation status and count of findings checked.\n\n## Plugin Template Path\n\nLocate installed plugin templates:\n1. `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002F`\n2. Fallback (local dev): `.\u002Fplugins\u002Fconductor\u002Ftemplates\u002F` from claudekit repo root\n3. Fallback: `.\u002Fplugins\u002Fconductor\u002Ftemplates\u002F` from repo root\n\n## 1.0 SYSTEM DIRECTIVE\n\nValidate a review document in **Reviews Directory** against the codebase. Produce a validation addendum before `\u002Fconductor:conductor-new-track` programme creation.\n\n**Read-only** until writing validation output. Git write operations follow **Git Write Policy**.\n\n---\n\n## 2.0 VALIDATION PROTOCOL\n\n### 2.1 Resolve review\n\n1. If `{{args}}` is non-empty, use as review path (relative to repo root or under `conductor\u002Freviews\u002F`).\n2. Otherwise **User Prompt Protocol** — header \"Review path\", type text, placeholder `conductor\u002Freviews\u002Ffoo_YYYYMMDD-review.md`.\n3. Verify file exists via Universal File Resolution.\n\n### 2.2 Extract findings\n\nParse review for:\n\n- **Location:** lines with file paths and line numbers\n- **Severity** claims (Critical, High, ARCH-N, §X.Y)\n- Inline backtick paths in finding bodies\n\nLoad `templates\u002Freview-document-header.md` for expected structure.\n\n### 2.3 Verify paths\n\n1. Run `python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fconductor_state.py\" verify-paths \u003Creview path>` (**Deterministic Plumbing Protocol**). It checks every cited path and `file:line` reference and suggests corrections for missing files.\n2. For paths marked `verified` with a line ref, `Read` the cited lines to confirm the symbol\u002Fcontext still matches the claim.\n3. Record: **Verified** | **Wrong path** (use the script's `suggestions`) | **Not found**\n4. Fallback without `python3`: `test -f` \u002F `test -d`, glob variants, and `Read` for line refs.\n\n### 2.4 Verify severity claims\n\nFor each finding with code citation:\n\n1. Read cited code\n2. Mark: **Confirmed** | **Partially confirmed** | **Disputed** | **Obsolete**\n3. Drop claims you cannot validate — do not flag uncertain items\n\n### 2.5 Write validation addendum\n\nDefault: sibling file `\u003Creview-stem>_validation.md` (preserves original review).\n\n**User Prompt Protocol** if user prefers append to review instead.\n\nAddendum structure:\n\n```markdown\n# Validation — \u003Creview title>\n\n**Source:** `conductor\u002Freviews\u002F\u003Cfile>`\n**Validated:** YYYY-MM-DD\n\n## Path verification\n\n| Finding | Cited path | Status | Correction |\n| ------- | ---------- | ------ | ---------- |\n\n## Severity confirmation\n\n| ID | Verdict | Notes |\n| -- | ------- | ----- |\n\n## Blocking issues\n\nList wrong paths or disputed Critical findings that must resolve before programme creation.\n\n## Programme readiness\n\n**Ready** | **Not ready** — \u003Creason>\n```\n\n### 2.6 Halt rules\n\n- **Blocking wrong paths** on Critical findings → announce halt; programme creation blocked until fixed\n- User may opt out via the **User Prompt Protocol** when running `\u002Fconductor:conductor-new-track` (document opt-out in programme metadata)\n\n### 2.7 Completion\n\nAnnounce: \"Validation written to `\u003Cpath>`. Next: `\u002Fconductor:conductor-new-track` from this review.\"\n",{"name":5,"description":7},"main","37782d73f0da5e452ba50cd173c0901aac87e01c","plugins\u002Fconductor\u002Fskills\u002Fconductor-validate-review",0,"https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99","https:\u002F\u002Fwww.newtonmunene.bio\u002F","The Variable Man","2026-11-05 20:30:27",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add newtonmunene99\u002Fclaudekit --skill conductor-validate-review",{"tool":39,"command":40},"bunx","bunx skills add newtonmunene99\u002Fclaudekit --skill conductor-validate-review",{"tool":42,"command":43},"pnpm","pnpm dlx skills add newtonmunene99\u002Fclaudekit --skill conductor-validate-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fconductor\u002Fskills\u002Fconductor-validate-review\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79R86JA5GHFV6HCJ19N3CRR","research","Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79R84KDM38DBBTBFEZ4N3XT","prototype","Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fprototype\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M79R82P2NZ6ZKQ5ARM9DE8EC","improve-codebase-architecture","Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M79R810215AGSDJ1WW781QGK","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79R7ZMHKENESB4171DGNXAV","grill-with-docs","A relentless interview to sharpen a plan or design, which also creates OKF repo knowledge as we go.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fgrill-with-docs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79R7W3FC384BJG49443YYBD","domain-modeling","Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing the glossary (conductor\u002Fcontext\u002Fproduct.md or a GLOSSARY.md), or recording or editing a decision concept.","https:\u002F\u002Fgithub.com\u002Fnewtonmunene99\u002Fclaudekit\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Fdomain-modeling\u002FSKILL.md",[],[]]