[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTKS0W95S8GHX7VDJN2MPM":3,"skill-same:01M6NTKS0W95S8GHX7VDJN2MPM":70},{"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":26,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":14,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6NTKS0W95S8GHX7VDJN2MPM","diff-review-strategy",null,"PR size-based review depth, performance review checklist, architecture conformance checks, and framework-specific review patterns.","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-review-strategy\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"review","strategy","diff","diff review","diff review strategy","performance","architecture","pr","review checklist","performance review","framework","checklist","patterns","size","conformance","framework-specific","2026-11-10 10:12:30",false,"---\nname: diff-review-strategy\ndescription: PR size-based review depth, performance review checklist, architecture conformance checks, and framework-specific review patterns.\n---\n\n# Diff Review Strategy\n\n## PR Size Categories and Review Depth\n\n| Category | Lines Changed | Review Depth | Action |\n|----------|--------------|--------------|--------|\n| XS | 1–10 | Quick scan | Auto-approve if tests pass, typo\u002Fdoc fixes |\n| S | 11–50 | Focused | Check edge cases, naming, one logic path |\n| M | 51–200 | Thorough | Full logic review, design check, test coverage |\n| L | 201–500 | Walkthrough | Request author explanation, check design first |\n| XL | 500+ | Split required | Block merge, ask to split into logical units |\n\n### XS\u002FS review checklist\n```\n[ ] Does the change do exactly what the title says?\n[ ] Are edge cases handled (null, empty, out-of-range)?\n[ ] Are variable names clear?\n[ ] Are tests updated or added?\n```\n\n### M review checklist\n```\n[ ] Is the design the simplest solution?\n[ ] Are error paths handled?\n[ ] Is there duplication that should be extracted?\n[ ] Does it follow existing patterns in the codebase?\n[ ] Are there security implications (user input, auth)?\n[ ] Is the test coverage meaningful (not just happy path)?\n```\n\n### L\u002FXL protocol\n```\n1. Read the PR description and linked ticket first\n2. Review architecture\u002Fdesign before line-by-line reading\n3. Request a walkthrough if intent is unclear\n4. If XL: comment \"Please split by [feature \u002F layer \u002F file]\"\n```\n\n## Performance Review Checklist\n\n### Database\n```\n[ ] N+1 query? (loop calling DB inside a loop)\n[ ] Missing index on filtered\u002Fsorted column?\n[ ] SELECT * where only specific columns needed?\n[ ] Missing pagination on list endpoints?\n[ ] Transaction missing on multi-step writes?\n```\n\n### React \u002F Frontend\n```\n[ ] Unnecessary re-renders? (missing memo\u002FuseCallback\u002FuseMemo)\n[ ] Large component re-renders on every keystroke?\n[ ] Images missing width\u002Fheight (layout shift)?\n[ ] Heavy dependency imported at top level (should be lazy)?\n[ ] Bundle size impact? (check with next build or vite --report)\n```\n\n### General backend\n```\n[ ] Synchronous I\u002FO inside async handler?\n[ ] Missing cache for repeated identical queries?\n[ ] Large payload returned when only summary needed?\n[ ] Polling where event\u002Fwebhook would be better?\n```\n\n## Architecture Conformance Checks\n\n### Layer violation detection\n```\nController → Service → Repository → DB     (ALLOWED)\nController → Repository → DB               (VIOLATION: skip service)\nService → Controller                       (VIOLATION: wrong direction)\nRepository → Service                       (VIOLATION: wrong direction)\n```\n\nRed flags in the diff:\n- `import { db } from '..\u002Fdb'` inside a route handler file\n- `import { Router } from 'express'` inside a service file\n- Direct `fetch()` calls inside a React component (should be in a hook or service)\n\n### Dependency direction (clean architecture)\n```\nEntities (innermost) — no imports from outer rings\nUse Cases — import Entities only\nAdapters — import Use Cases and Entities\nFrameworks — import everything, imported by nothing\n```\n\n### Feature coupling detection\n```\n[ ] Does feature A import from feature B's internals?\n[ ] If yes, should this be a shared utility or event instead?\n[ ] Are feature-specific types leaking into shared modules?\n```\n\n## Framework-Specific Review Patterns\n\n### React\n```\n[ ] Hooks called conditionally? (rules of hooks violation)\n[ ] Missing key prop in lists? Or key is array index?\n[ ] useEffect missing cleanup return for subscriptions\u002Ftimers?\n[ ] State mutation instead of new object? ({ ...prev, field: val })\n[ ] Prop drilling 3+ levels deep? (consider context or composition)\n```\n\n### Next.js\n```\n[ ] Data fetching happening client-side when it could be server-side?\n[ ] 'use client' added unnecessarily to a component with no interactivity?\n[ ] Large third-party lib imported in a Server Component?\n[ ] Dynamic route missing generateStaticParams for static generation?\n[ ] API route missing input validation?\n```\n\n### Express\n```\n[ ] Middleware added in wrong order? (auth before body-parser?)\n[ ] Error handler missing 4-argument signature (err, req, res, next)?\n[ ] Async handler missing try\u002Fcatch or asyncHandler wrapper?\n[ ] User input used directly in SQL\u002Ffile path\u002Fshell command?\n[ ] Missing rate limiter on public endpoints?\n```\n\n## Review Comment Templates\n\n### Nitpick (non-blocking)\n```\nnit: Consider renaming `data` to `userProfile` for clarity — easy to\nconfuse with the raw API response above.\n```\n\n### Suggestion (non-blocking, better approach available)\n```\nsuggestion: This could use `Promise.all` to run both requests in\nparallel instead of sequentially. Would save ~300ms per call.\n\n  \u002F\u002F instead of:\n  const a = await fetchA()\n  const b = await fetchB()\n\n  \u002F\u002F consider:\n  const [a, b] = await Promise.all([fetchA(), fetchB()])\n```\n\n### Blocker (must fix before merge)\n```\nblocker: This passes `req.params.id` directly into the SQL query\nstring — SQL injection risk. Use a parameterized query:\n\n  db.query('SELECT * FROM users WHERE id = $1', [req.params.id])\n```\n\n### Praise (leave these too — morale matters)\n```\nnice: Clean separation of concerns here. The service layer staying\nunaware of the HTTP layer makes this easy to test.\n```\n\n## Review Anti-Patterns to Avoid\n\n- Bike-shedding on style that the linter already enforces\n- Asking \"why not X?\" without explaining why X would be better\n- Leaving blockers with no suggested fix\n- Reviewing XL PRs line by line without first understanding the design\n- Approving without reading tests\n","# Diff Review Strategy\n\n## PR Size Categories and Review Depth\n\n| Category | Lines Changed | Review Depth | Action |\n|----------|--------------|--------------|--------|\n| XS | 1–10 | Quick scan | Auto-approve if tests pass, typo\u002Fdoc fixes |\n| S | 11–50 | Focused | Check edge cases, naming, one logic path |\n| M | 51–200 | Thorough | Full logic review, design check, test coverage |\n| L | 201–500 | Walkthrough | Request author explanation, check design first |\n| XL | 500+ | Split required | Block merge, ask to split into logical units |\n\n### XS\u002FS review checklist\n```\n[ ] Does the change do exactly what the title says?\n[ ] Are edge cases handled (null, empty, out-of-range)?\n[ ] Are variable names clear?\n[ ] Are tests updated or added?\n```\n\n### M review checklist\n```\n[ ] Is the design the simplest solution?\n[ ] Are error paths handled?\n[ ] Is there duplication that should be extracted?\n[ ] Does it follow existing patterns in the codebase?\n[ ] Are there security implications (user input, auth)?\n[ ] Is the test coverage meaningful (not just happy path)?\n```\n\n### L\u002FXL protocol\n```\n1. Read the PR description and linked ticket first\n2. Review architecture\u002Fdesign before line-by-line reading\n3. Request a walkthrough if intent is unclear\n4. If XL: comment \"Please split by [feature \u002F layer \u002F file]\"\n```\n\n## Performance Review Checklist\n\n### Database\n```\n[ ] N+1 query? (loop calling DB inside a loop)\n[ ] Missing index on filtered\u002Fsorted column?\n[ ] SELECT * where only specific columns needed?\n[ ] Missing pagination on list endpoints?\n[ ] Transaction missing on multi-step writes?\n```\n\n### React \u002F Frontend\n```\n[ ] Unnecessary re-renders? (missing memo\u002FuseCallback\u002FuseMemo)\n[ ] Large component re-renders on every keystroke?\n[ ] Images missing width\u002Fheight (layout shift)?\n[ ] Heavy dependency imported at top level (should be lazy)?\n[ ] Bundle size impact? (check with next build or vite --report)\n```\n\n### General backend\n```\n[ ] Synchronous I\u002FO inside async handler?\n[ ] Missing cache for repeated identical queries?\n[ ] Large payload returned when only summary needed?\n[ ] Polling where event\u002Fwebhook would be better?\n```\n\n## Architecture Conformance Checks\n\n### Layer violation detection\n```\nController → Service → Repository → DB     (ALLOWED)\nController → Repository → DB               (VIOLATION: skip service)\nService → Controller                       (VIOLATION: wrong direction)\nRepository → Service                       (VIOLATION: wrong direction)\n```\n\nRed flags in the diff:\n- `import { db } from '..\u002Fdb'` inside a route handler file\n- `import { Router } from 'express'` inside a service file\n- Direct `fetch()` calls inside a React component (should be in a hook or service)\n\n### Dependency direction (clean architecture)\n```\nEntities (innermost) — no imports from outer rings\nUse Cases — import Entities only\nAdapters — import Use Cases and Entities\nFrameworks — import everything, imported by nothing\n```\n\n### Feature coupling detection\n```\n[ ] Does feature A import from feature B's internals?\n[ ] If yes, should this be a shared utility or event instead?\n[ ] Are feature-specific types leaking into shared modules?\n```\n\n## Framework-Specific Review Patterns\n\n### React\n```\n[ ] Hooks called conditionally? (rules of hooks violation)\n[ ] Missing key prop in lists? Or key is array index?\n[ ] useEffect missing cleanup return for subscriptions\u002Ftimers?\n[ ] State mutation instead of new object? ({ ...prev, field: val })\n[ ] Prop drilling 3+ levels deep? (consider context or composition)\n```\n\n### Next.js\n```\n[ ] Data fetching happening client-side when it could be server-side?\n[ ] 'use client' added unnecessarily to a component with no interactivity?\n[ ] Large third-party lib imported in a Server Component?\n[ ] Dynamic route missing generateStaticParams for static generation?\n[ ] API route missing input validation?\n```\n\n### Express\n```\n[ ] Middleware added in wrong order? (auth before body-parser?)\n[ ] Error handler missing 4-argument signature (err, req, res, next)?\n[ ] Async handler missing try\u002Fcatch or asyncHandler wrapper?\n[ ] User input used directly in SQL\u002Ffile path\u002Fshell command?\n[ ] Missing rate limiter on public endpoints?\n```\n\n## Review Comment Templates\n\n### Nitpick (non-blocking)\n```\nnit: Consider renaming `data` to `userProfile` for clarity — easy to\nconfuse with the raw API response above.\n```\n\n### Suggestion (non-blocking, better approach available)\n```\nsuggestion: This could use `Promise.all` to run both requests in\nparallel instead of sequentially. Would save ~300ms per call.\n\n  \u002F\u002F instead of:\n  const a = await fetchA()\n  const b = await fetchB()\n\n  \u002F\u002F consider:\n  const [a, b] = await Promise.all([fetchA(), fetchB()])\n```\n\n### Blocker (must fix before merge)\n```\nblocker: This passes `req.params.id` directly into the SQL query\nstring — SQL injection risk. Use a parameterized query:\n\n  db.query('SELECT * FROM users WHERE id = $1', [req.params.id])\n```\n\n### Praise (leave these too — morale matters)\n```\nnice: Clean separation of concerns here. The service layer staying\nunaware of the HTTP layer makes this easy to test.\n```\n\n## Review Anti-Patterns to Avoid\n\n- Bike-shedding on style that the linter already enforces\n- Asking \"why not X?\" without explaining why X would be better\n- Leaving blockers with no suggested fix\n- Reviewing XL PRs line by line without first understanding the design\n- Approving without reading tests\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fdiff-review-strategy","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add rubicanjr\u002FFinCognis --skill diff-review-strategy",{"tool":62,"command":63},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill diff-review-strategy",{"tool":65,"command":66},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill diff-review-strategy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-review-strategy\u002FSKILL.md",true,[],[71,90,99,118,146,161],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":80,"publishedAt":43},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[81,82,83,84,85,86,87,88,89],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":43},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[92,97,98],"verification","false",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":108,"publishedAt":43},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[109,39,110,111,112,113,114,115,116,117],"websocket","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":126,"publishedAt":43},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[124,125],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},[127,128,129,130,131,132,133,134,135,136,137,138,139,111,140,141,142,143,144,145],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":43},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[153,154,97,155,27,156,34,157,29,158,159,30,160],"verification loop","loop","lint","security","system","build","tests","types",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":43},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[168,169,170,171,39,172,173,174,175,115,176,177,178,179,180,136,181,182],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]