[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F316SW8ZX7MB277QS51HZV":3,"skill-same:01M7F316SW8ZX7MB277QS51HZV":48},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":12,"updatedAt":34,"install":35,"resources":47},"01M7F316SW8ZX7MB277QS51HZV","review-pr",null,"Perform a comprehensive code review of a pull request","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Freview-pr\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: review-pr\ndescription: Perform a comprehensive code review of a pull request\nargument-hint: \"[PR_number|URL]\"\neffort: high\ndisable-model-invocation: true\n---\n\n# Review pull request\n\nPerform a comprehensive code review of a pull request.\n\n## Instructions\n\n1. Get PR information: `gh pr view $ARGUMENTS --json title,body,files,additions,deletions`\n2. Review each changed file\n3. Provide structured feedback\n\n## Review checklist\n\n### Code quality\n- [ ] Code is readable and well-organized\n- [ ] Functions are appropriately sized\n- [ ] No code duplication\n- [ ] Meaningful variable\u002Ffunction names\n\n### Functionality\n- [ ] Logic is correct\n- [ ] Edge cases handled\n- [ ] Error handling is comprehensive\n- [ ] No obvious bugs\n\n### Security\n- [ ] No hardcoded secrets\n- [ ] Input validation present\n- [ ] No injection vulnerabilities\n- [ ] Authorization checks in place\n\n### Testing\n- [ ] Tests added for new code\n- [ ] Existing tests still pass\n- [ ] Edge cases tested\n\n### Documentation\n- [ ] Code is self-documenting or commented\n- [ ] README updated if needed\n- [ ] API changes documented\n\n## Output format\n\n```markdown\n## PR Review: #[number] - [title]\n\n### Summary\n[1-2 sentence overview]\n\n### Approval Status\n[ ] Approved\n[ ] Approved with suggestions\n[ ] Changes requested\n\n### Findings\n\n#### Critical (Must Fix)\n- [ ] [Issue description] - `file:line`\n\n#### Suggestions (Should Consider)\n- [ ] [Improvement] - `file:line`\n\n#### Nitpicks (Optional)\n- [ ] [Minor suggestion] - `file:line`\n\n### Positive Highlights\n- [What's done well]\n\n### Questions\n- [Clarifications needed]\n```\n\n## Usage\n\n```\n\u002Freview-pr 123\n\u002Freview-pr https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\u002Fpull\u002F123\n```\n\n---\n\n## Advanced: Multi-Agent review\n\nFor production-grade reviews requiring specialized perspectives and anti-hallucination safeguards.\n\n### Pre-flight Check\n\nBefore reviewing, check if this is a follow-up pass to avoid repeating suggestions:\n\n```bash\n# Detect if Claude already reviewed this PR\ngit log --oneline -10 | grep \"Co-Authored-By: Claude\"\n```\n\nIf detected, note: \"This appears to be a follow-up pass. I'll focus on new issues and avoid repeating previous suggestions.\"\n\n### Scope drift detection\n\nCross-reference the PR diff against the original plan to catch unintended changes.\n\n```bash\n# Detect current branch\nBRANCH=$(git branch --show-current)\n\n# Search for a plan file associated with this branch\nls ~\u002F.claude\u002Fplans\u002F 2>\u002Fdev\u002Fnull | grep -i \"$BRANCH\" | head -3\n\n# Files actually changed in this PR\ngit diff --stat origin\u002Fmain...HEAD | head -30\n```\n\nIf a plan file exists for this branch:\n1. Read the plan file: what was the stated scope?\n2. Compare stated scope vs actual `git diff --stat`\n3. Flag files changed that were NOT mentioned in the plan\n\nOutput format:\n```\nSCOPE DRIFT CHECK\n─────────────────────────────────────────\nPlan scope:    [what the plan said would change]\nActual diff:   [files actually changed]\nDrift:         [files changed outside plan scope, if any]\nVerdict:       IN SCOPE \u002F DRIFT DETECTED\n```\n\nIf no plan file exists: note \"No plan file found for this branch, skipping scope drift check.\"\n\n### Multi-agent specialization\n\nLaunch 3 parallel specialized agents (see [Split Role Sub-Agents](..\u002F..\u002F..\u002Fguide\u002Fultimate-guide.md#split-role-sub-agents)):\n\n**Agent 1: Consistency Auditor**\n```\nFocus: DRY violations, duplicate logic, pattern inconsistencies\nCheck for:\n- Duplicated code blocks (>5 lines similar)\n- Inconsistent naming conventions\n- Pattern violations (if project uses X pattern, enforce it)\n```\n\n**Agent 2: SOLID Principles Analyst**\n```\nFocus: Single Responsibility Principle violations, complexity\nCheck for:\n- Functions >50 lines (likely doing too much)\n- Nested conditionals >3 levels deep\n- Cyclomatic complexity >10\n- Mixed concerns in single component\n```\n\n**Agent 3: Defensive Code Auditor**\n```\nFocus: Silent failures, masked bugs, hidden fallbacks, LLM output trust boundary\nCheck for:\n- Empty catch blocks: try { } catch (e) { } \u002F\u002F swallows error\n- Silent fallbacks: return data || DEFAULT \u002F\u002F hides missing data\n- Unchecked null\u002Fundefined: user.name without validation\n- Ignored promise rejections: async fn without .catch()\n\nLLM Output Trust Boundary (especially relevant in AI-assisted codebases):\n- LLM-generated values (emails, URLs, names, IDs) written to DB or passed to\n  downstream functions without format validation; add lightweight guards\n  (email regex, URL parsing, .trim()) before persisting\n- Structured tool output (arrays, objects from AI tools) accepted without\n  type\u002Fshape checks before database writes or rendering\n- AI-generated SQL or code strings executed without sanitization\n```\n\n### Anti-hallucination rules\n\n**Verify before asserting**:\n- Use `Grep` or `Glob` to verify patterns before recommending them\n- If suggesting \"use existing UserService pattern\", confirm UserService exists first\n- Never claim \"project uses X\" without checking actual codebase\n\n**Occurrence rule**:\n- Pattern with >10 occurrences = established (Suggestion level)\n- Pattern with \u003C3 occurrences = not established (Can Skip or ask maintainer)\n- Read full file context, not just diff lines\n\n**Uncertainty markers**:\n- Use \"❓ To verify:\" when unsure about project conventions\n- Use \"💡 Consider:\" for optional improvements\n- Use \"🔴 Must fix:\" only for critical bugs\u002Fsecurity\n\n### Reconciliation\n\nAfter agents report findings:\n\n1. **Deduplicate**: Remove overlapping suggestions across agents\n2. **Prioritize existing patterns**: If codebase uses pattern X, recommend X (not ideal pattern Y)\n3. **Mark skipped suggestions**: \"Skipping [suggestion] because project uses [alternative pattern]\"\n4. **Track reasoning**: Document why suggestion was kept or skipped\n\n### Severity classification\n\n```\n🔴 Must Fix (Blockers)\n- Security vulnerabilities\n- Data loss risks\n- Breaking changes without migration\n- Silent failures masking bugs\n\n🟡 Should Fix (Improvements)\n- SOLID violations causing maintenance issues\n- DRY violations (>3 duplicates)\n- Performance bottlenecks (N+1 queries)\n- Missing error handling for critical paths\n\n🟢 Can Skip (Nice-to-haves)\n- Style inconsistencies (if no linter)\n- Minor naming improvements\n- Overly nested code (if \u003C3 levels)\n- Documentation gaps (if code self-documenting)\n```\n\n### Fix-first heuristic\n\nDetermine whether to auto-fix each finding or surface it for user decision.\n\n```\nAUTO-FIX (apply without asking):          ASK (needs human judgment):\n├─ Dead code \u002F unused variables            ├─ Security changes (auth, XSS, injection)\n├─ N+1 queries (missing eager loading)     ├─ Race conditions\n├─ Stale comments contradicting code       ├─ Design decisions\n├─ Magic numbers → named constants         ├─ Large fixes (>20 lines changed)\n├─ Missing import \u002F path mismatches        ├─ Enum completeness\n├─ Variables assigned but never read       ├─ Anything removing functionality\n└─ Obvious version\u002Fdoc mismatches          └─ User-visible behavior changes\n```\n\n**Rule**: If a senior engineer would apply the fix in 30 seconds without discussion, it's AUTO-FIX. If reasonable engineers could disagree, it's ASK.\n\nAfter agents report findings:\n1. Apply all AUTO-FIX items immediately with minimal targeted edits\n2. Batch all ASK items into a single user decision (not one question per item)\n\n### Auto-Fix loop (optional)\n\nFor automated convergence:\n\n```\nReview → Identify issues → Fix → Re-review → Repeat until minimal changes\n\nSafeguards:\n- Max 3 iterations to prevent infinite loops\n- Run tsc\u002Flint check before each iteration\n- Skip auto-fix for protected files (package.json, migrations, etc.)\n```\n\n**Example prompt**:\n```\nReview this PR with auto-fix enabled:\n1. Review using 3 agents above\n2. Fix all 🔴 Must Fix issues\n3. Re-review to verify fixes\n4. Repeat for 🟡 Should Fix (max 2 more iterations)\n5. Stop when only 🟢 Can Skip remain\n```\n\n### Conditional context loading\n\nLoad additional context based on diff content (stack-agnostic):\n\n| If diff contains... | Then check... |\n|---------------------|---------------|\n| Database queries | Indexes, N+1 patterns, query optimization |\n| API endpoints | Auth middleware, input validation, rate limiting |\n| Authentication logic | Password hashing, session management, CSRF tokens |\n| File uploads | Size limits, MIME validation, storage security |\n| Date\u002Ftime operations | Timezone handling, DST edge cases |\n| External API calls | Timeout configs, retry logic, error handling |\n| Environment variables | Presence in .env.example, validation at startup |\n\n### Integration with existing tools\n\n**SE-CoVe Plugin**: Use for general fact-checking of review claims (complementary to anti-hallucination rules above)\n\n**Worktrunk**: For codebase-wide pattern analysis before suggesting changes\n\n**AST-grep**: For structural pattern matching (e.g., find all similar try\u002Fcatch blocks)\n\n---\n\n## Sources\n\n- Base template: Claude Code Ultimate Guide\n- Multi-agent review: [Pat Cullen](https:\u002F\u002Fgist.github.com\u002Fpatyearone\u002Fc9a091b97e756f5ed361f7514d88ef0b) (Jan 2026)\n- Anti-hallucination patterns: [Méthode Aristote](https:\u002F\u002Fgithub.com\u002FFlorianBruniaux) code review system\n\n$ARGUMENTS\n","# Review pull request\n\nPerform a comprehensive code review of a pull request.\n\n## Instructions\n\n1. Get PR information: `gh pr view $ARGUMENTS --json title,body,files,additions,deletions`\n2. Review each changed file\n3. Provide structured feedback\n\n## Review checklist\n\n### Code quality\n- [ ] Code is readable and well-organized\n- [ ] Functions are appropriately sized\n- [ ] No code duplication\n- [ ] Meaningful variable\u002Ffunction names\n\n### Functionality\n- [ ] Logic is correct\n- [ ] Edge cases handled\n- [ ] Error handling is comprehensive\n- [ ] No obvious bugs\n\n### Security\n- [ ] No hardcoded secrets\n- [ ] Input validation present\n- [ ] No injection vulnerabilities\n- [ ] Authorization checks in place\n\n### Testing\n- [ ] Tests added for new code\n- [ ] Existing tests still pass\n- [ ] Edge cases tested\n\n### Documentation\n- [ ] Code is self-documenting or commented\n- [ ] README updated if needed\n- [ ] API changes documented\n\n## Output format\n\n```markdown\n## PR Review: #[number] - [title]\n\n### Summary\n[1-2 sentence overview]\n\n### Approval Status\n[ ] Approved\n[ ] Approved with suggestions\n[ ] Changes requested\n\n### Findings\n\n#### Critical (Must Fix)\n- [ ] [Issue description] - `file:line`\n\n#### Suggestions (Should Consider)\n- [ ] [Improvement] - `file:line`\n\n#### Nitpicks (Optional)\n- [ ] [Minor suggestion] - `file:line`\n\n### Positive Highlights\n- [What's done well]\n\n### Questions\n- [Clarifications needed]\n```\n\n## Usage\n\n```\n\u002Freview-pr 123\n\u002Freview-pr https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\u002Fpull\u002F123\n```\n\n---\n\n## Advanced: Multi-Agent review\n\nFor production-grade reviews requiring specialized perspectives and anti-hallucination safeguards.\n\n### Pre-flight Check\n\nBefore reviewing, check if this is a follow-up pass to avoid repeating suggestions:\n\n```bash\n# Detect if Claude already reviewed this PR\ngit log --oneline -10 | grep \"Co-Authored-By: Claude\"\n```\n\nIf detected, note: \"This appears to be a follow-up pass. I'll focus on new issues and avoid repeating previous suggestions.\"\n\n### Scope drift detection\n\nCross-reference the PR diff against the original plan to catch unintended changes.\n\n```bash\n# Detect current branch\nBRANCH=$(git branch --show-current)\n\n# Search for a plan file associated with this branch\nls ~\u002F.claude\u002Fplans\u002F 2>\u002Fdev\u002Fnull | grep -i \"$BRANCH\" | head -3\n\n# Files actually changed in this PR\ngit diff --stat origin\u002Fmain...HEAD | head -30\n```\n\nIf a plan file exists for this branch:\n1. Read the plan file: what was the stated scope?\n2. Compare stated scope vs actual `git diff --stat`\n3. Flag files changed that were NOT mentioned in the plan\n\nOutput format:\n```\nSCOPE DRIFT CHECK\n─────────────────────────────────────────\nPlan scope:    [what the plan said would change]\nActual diff:   [files actually changed]\nDrift:         [files changed outside plan scope, if any]\nVerdict:       IN SCOPE \u002F DRIFT DETECTED\n```\n\nIf no plan file exists: note \"No plan file found for this branch, skipping scope drift check.\"\n\n### Multi-agent specialization\n\nLaunch 3 parallel specialized agents (see [Split Role Sub-Agents](..\u002F..\u002F..\u002Fguide\u002Fultimate-guide.md#split-role-sub-agents)):\n\n**Agent 1: Consistency Auditor**\n```\nFocus: DRY violations, duplicate logic, pattern inconsistencies\nCheck for:\n- Duplicated code blocks (>5 lines similar)\n- Inconsistent naming conventions\n- Pattern violations (if project uses X pattern, enforce it)\n```\n\n**Agent 2: SOLID Principles Analyst**\n```\nFocus: Single Responsibility Principle violations, complexity\nCheck for:\n- Functions >50 lines (likely doing too much)\n- Nested conditionals >3 levels deep\n- Cyclomatic complexity >10\n- Mixed concerns in single component\n```\n\n**Agent 3: Defensive Code Auditor**\n```\nFocus: Silent failures, masked bugs, hidden fallbacks, LLM output trust boundary\nCheck for:\n- Empty catch blocks: try { } catch (e) { } \u002F\u002F swallows error\n- Silent fallbacks: return data || DEFAULT \u002F\u002F hides missing data\n- Unchecked null\u002Fundefined: user.name without validation\n- Ignored promise rejections: async fn without .catch()\n\nLLM Output Trust Boundary (especially relevant in AI-assisted codebases):\n- LLM-generated values (emails, URLs, names, IDs) written to DB or passed to\n  downstream functions without format validation; add lightweight guards\n  (email regex, URL parsing, .trim()) before persisting\n- Structured tool output (arrays, objects from AI tools) accepted without\n  type\u002Fshape checks before database writes or rendering\n- AI-generated SQL or code strings executed without sanitization\n```\n\n### Anti-hallucination rules\n\n**Verify before asserting**:\n- Use `Grep` or `Glob` to verify patterns before recommending them\n- If suggesting \"use existing UserService pattern\", confirm UserService exists first\n- Never claim \"project uses X\" without checking actual codebase\n\n**Occurrence rule**:\n- Pattern with >10 occurrences = established (Suggestion level)\n- Pattern with \u003C3 occurrences = not established (Can Skip or ask maintainer)\n- Read full file context, not just diff lines\n\n**Uncertainty markers**:\n- Use \"❓ To verify:\" when unsure about project conventions\n- Use \"💡 Consider:\" for optional improvements\n- Use \"🔴 Must fix:\" only for critical bugs\u002Fsecurity\n\n### Reconciliation\n\nAfter agents report findings:\n\n1. **Deduplicate**: Remove overlapping suggestions across agents\n2. **Prioritize existing patterns**: If codebase uses pattern X, recommend X (not ideal pattern Y)\n3. **Mark skipped suggestions**: \"Skipping [suggestion] because project uses [alternative pattern]\"\n4. **Track reasoning**: Document why suggestion was kept or skipped\n\n### Severity classification\n\n```\n🔴 Must Fix (Blockers)\n- Security vulnerabilities\n- Data loss risks\n- Breaking changes without migration\n- Silent failures masking bugs\n\n🟡 Should Fix (Improvements)\n- SOLID violations causing maintenance issues\n- DRY violations (>3 duplicates)\n- Performance bottlenecks (N+1 queries)\n- Missing error handling for critical paths\n\n🟢 Can Skip (Nice-to-haves)\n- Style inconsistencies (if no linter)\n- Minor naming improvements\n- Overly nested code (if \u003C3 levels)\n- Documentation gaps (if code self-documenting)\n```\n\n### Fix-first heuristic\n\nDetermine whether to auto-fix each finding or surface it for user decision.\n\n```\nAUTO-FIX (apply without asking):          ASK (needs human judgment):\n├─ Dead code \u002F unused variables            ├─ Security changes (auth, XSS, injection)\n├─ N+1 queries (missing eager loading)     ├─ Race conditions\n├─ Stale comments contradicting code       ├─ Design decisions\n├─ Magic numbers → named constants         ├─ Large fixes (>20 lines changed)\n├─ Missing import \u002F path mismatches        ├─ Enum completeness\n├─ Variables assigned but never read       ├─ Anything removing functionality\n└─ Obvious version\u002Fdoc mismatches          └─ User-visible behavior changes\n```\n\n**Rule**: If a senior engineer would apply the fix in 30 seconds without discussion, it's AUTO-FIX. If reasonable engineers could disagree, it's ASK.\n\nAfter agents report findings:\n1. Apply all AUTO-FIX items immediately with minimal targeted edits\n2. Batch all ASK items into a single user decision (not one question per item)\n\n### Auto-Fix loop (optional)\n\nFor automated convergence:\n\n```\nReview → Identify issues → Fix → Re-review → Repeat until minimal changes\n\nSafeguards:\n- Max 3 iterations to prevent infinite loops\n- Run tsc\u002Flint check before each iteration\n- Skip auto-fix for protected files (package.json, migrations, etc.)\n```\n\n**Example prompt**:\n```\nReview this PR with auto-fix enabled:\n1. Review using 3 agents above\n2. Fix all 🔴 Must Fix issues\n3. Re-review to verify fixes\n4. Repeat for 🟡 Should Fix (max 2 more iterations)\n5. Stop when only 🟢 Can Skip remain\n```\n\n### Conditional context loading\n\nLoad additional context based on diff content (stack-agnostic):\n\n| If diff contains... | Then check... |\n|---------------------|---------------|\n| Database queries | Indexes, N+1 patterns, query optimization |\n| API endpoints | Auth middleware, input validation, rate limiting |\n| Authentication logic | Password hashing, session management, CSRF tokens |\n| File uploads | Size limits, MIME validation, storage security |\n| Date\u002Ftime operations | Timezone handling, DST edge cases |\n| External API calls | Timeout configs, retry logic, error handling |\n| Environment variables | Presence in .env.example, validation at startup |\n\n### Integration with existing tools\n\n**SE-CoVe Plugin**: Use for general fact-checking of review claims (complementary to anti-hallucination rules above)\n\n**Worktrunk**: For codebase-wide pattern analysis before suggesting changes\n\n**AST-grep**: For structural pattern matching (e.g., find all similar try\u002Fcatch blocks)\n\n---\n\n## Sources\n\n- Base template: Claude Code Ultimate Guide\n- Multi-agent review: [Pat Cullen](https:\u002F\u002Fgist.github.com\u002Fpatyearone\u002Fc9a091b97e756f5ed361f7514d88ef0b) (Jan 2026)\n- Anti-hallucination patterns: [Méthode Aristote](https:\u002F\u002Fgithub.com\u002FFlorianBruniaux) code review system\n\n$ARGUMENTS\n",{"name":5,"effort":24,"description":7,"argument-hint":25,"disable-model-invocation":26},"high","[PR_number|URL]",true,"main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Freview-pr",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill review-pr",{"tool":41,"command":42},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill review-pr",{"tool":44,"command":45},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill review-pr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Freview-pr\u002FSKILL.md",[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes","Evaluate staged changes using LLM-as-a-Judge before committing","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[]]