[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NRMCK2G1CT82MZAYP90Q57":3,"skill-same:01M6NRMCK2G1CT82MZAYP90Q57":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6NRMCK2G1CT82MZAYP90Q57","code-review",null,"Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion\u002Fsuccess claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.","vntopicai\u002Fai-planner","vntopicai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F201040886?v=4","01M6NRHDP3KC0J2F22TSFZH796","01M6NRHDT0JGWD7J4Z10Y0NHHS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fcode-review\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"review","code review","code","features","claims","reviews","false","essential","three","evidence","verification gates","code review feedback","reviewer","feedback","subagent","pull","verification","tasks","status","pull requests","2026-11-10 10:12:30",false,"---\nname: code-review\ndescription: Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion\u002Fsuccess claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.\n---\n\n# Code Review\n\nGuide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.\n\n## Overview\n\nCode review requires three distinct practices:\n\n1. **Receiving feedback** - Technical evaluation over performative agreement\n2. **Requesting reviews** - Systematic review via code-reviewer subagent\n3. **Verification gates** - Evidence before any completion claims\n\nEach practice has specific triggers and protocols detailed in reference files.\n\n## Core Principle\n\nAlways honoring **YAGNI**, **KISS**, and **DRY** principles.\n**Be honest, be brutal, straight to the point, and be concise.**\n\n**Technical correctness over social comfort.** Verify before implementing. Ask before assuming. Evidence before claims.\n\n## When to Use This Skill\n\n### Receiving Feedback\nTrigger when:\n- Receiving code review comments from any source\n- Feedback seems unclear or technically questionable\n- Multiple review items need prioritization\n- External reviewer lacks full context\n- Suggestion conflicts with existing decisions\n\n**Reference:** `references\u002Fcode-review-reception.md`\n\n### Requesting Review\nTrigger when:\n- Completing tasks in subagent-driven development (after EACH task)\n- Finishing major features or refactors\n- Before merging to main branch\n- Stuck and need fresh perspective\n- After fixing complex bugs\n\n**Reference:** `references\u002Frequesting-code-review.md`\n\n### Verification Gates\nTrigger when:\n- About to claim tests pass, build succeeds, or work is complete\n- Before committing, pushing, or creating PRs\n- Moving to next task\n- Any statement suggesting success\u002Fcompletion\n- Expressing satisfaction with work\n\n**Reference:** `references\u002Fverification-before-completion.md`\n\n## Quick Decision Tree\n\n```\nSITUATION?\n│\n├─ Received feedback\n│  ├─ Unclear items? → STOP, ask for clarification first\n│  ├─ From human partner? → Understand, then implement\n│  └─ From external reviewer? → Verify technically before implementing\n│\n├─ Completed work\n│  ├─ Major feature\u002Ftask? → Request code-reviewer subagent review\n│  └─ Before merge? → Request code-reviewer subagent review\n│\n└─ About to claim status\n   ├─ Have fresh verification? → State claim WITH evidence\n   └─ No fresh verification? → RUN verification command first\n```\n\n## Receiving Feedback Protocol\n\n### Response Pattern\nREAD → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT\n\n### Key Rules\n- ❌ No performative agreement: \"You're absolutely right!\", \"Great point!\", \"Thanks for [anything]\"\n- ❌ No implementation before verification\n- ✅ Restate requirement, ask questions, push back with technical reasoning, or just start working\n- ✅ If unclear: STOP and ask for clarification on ALL unclear items first\n- ✅ YAGNI check: grep for usage before implementing suggested \"proper\" features\n\n### Source Handling\n- **Human partner:** Trusted - implement after understanding, no performative agreement\n- **External reviewers:** Verify technically correct, check for breakage, push back if wrong\n\n**Full protocol:** `references\u002Fcode-review-reception.md`\n\n## Requesting Review Protocol\n\n### When to Request\n- After each task in subagent-driven development\n- After major feature completion\n- Before merge to main\n\n### Process\n1. Get git SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`\n2. Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION\n3. Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later\n\n**Full protocol:** `references\u002Frequesting-code-review.md`\n\n## Verification Gates Protocol\n\n### The Iron Law\n**NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE**\n\n### Gate Function\nIDENTIFY command → RUN full command → READ output → VERIFY confirms claim → THEN claim\n\nSkip any step = lying, not verifying\n\n### Requirements\n- Tests pass: Test output shows 0 failures\n- Build succeeds: Build command exit 0\n- Bug fixed: Test original symptom passes\n- Requirements met: Line-by-line checklist verified\n\n### Red Flags - STOP\nUsing \"should\"\u002F\"probably\"\u002F\"seems to\", expressing satisfaction before verification, committing without verification, trusting agent reports, ANY wording implying success without running verification\n\n**Full protocol:** `references\u002Fverification-before-completion.md`\n\n## Integration with Workflows\n\n- **Subagent-Driven:** Review after EACH task, verify before moving to next\n- **Pull Requests:** Verify tests pass, request code-reviewer review before merge\n- **General:** Apply verification gates before any status claims, push back on invalid feedback\n\n## Bottom Line\n\n1. Technical rigor over social performance - No performative agreement\n2. Systematic review processes - Use code-reviewer subagent\n3. Evidence before claims - Verification gates always\n\nVerify. Question. Then implement. Evidence. Then claim.\n","# Code Review\n\nGuide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.\n\n## Overview\n\nCode review requires three distinct practices:\n\n1. **Receiving feedback** - Technical evaluation over performative agreement\n2. **Requesting reviews** - Systematic review via code-reviewer subagent\n3. **Verification gates** - Evidence before any completion claims\n\nEach practice has specific triggers and protocols detailed in reference files.\n\n## Core Principle\n\nAlways honoring **YAGNI**, **KISS**, and **DRY** principles.\n**Be honest, be brutal, straight to the point, and be concise.**\n\n**Technical correctness over social comfort.** Verify before implementing. Ask before assuming. Evidence before claims.\n\n## When to Use This Skill\n\n### Receiving Feedback\nTrigger when:\n- Receiving code review comments from any source\n- Feedback seems unclear or technically questionable\n- Multiple review items need prioritization\n- External reviewer lacks full context\n- Suggestion conflicts with existing decisions\n\n**Reference:** `references\u002Fcode-review-reception.md`\n\n### Requesting Review\nTrigger when:\n- Completing tasks in subagent-driven development (after EACH task)\n- Finishing major features or refactors\n- Before merging to main branch\n- Stuck and need fresh perspective\n- After fixing complex bugs\n\n**Reference:** `references\u002Frequesting-code-review.md`\n\n### Verification Gates\nTrigger when:\n- About to claim tests pass, build succeeds, or work is complete\n- Before committing, pushing, or creating PRs\n- Moving to next task\n- Any statement suggesting success\u002Fcompletion\n- Expressing satisfaction with work\n\n**Reference:** `references\u002Fverification-before-completion.md`\n\n## Quick Decision Tree\n\n```\nSITUATION?\n│\n├─ Received feedback\n│  ├─ Unclear items? → STOP, ask for clarification first\n│  ├─ From human partner? → Understand, then implement\n│  └─ From external reviewer? → Verify technically before implementing\n│\n├─ Completed work\n│  ├─ Major feature\u002Ftask? → Request code-reviewer subagent review\n│  └─ Before merge? → Request code-reviewer subagent review\n│\n└─ About to claim status\n   ├─ Have fresh verification? → State claim WITH evidence\n   └─ No fresh verification? → RUN verification command first\n```\n\n## Receiving Feedback Protocol\n\n### Response Pattern\nREAD → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT\n\n### Key Rules\n- ❌ No performative agreement: \"You're absolutely right!\", \"Great point!\", \"Thanks for [anything]\"\n- ❌ No implementation before verification\n- ✅ Restate requirement, ask questions, push back with technical reasoning, or just start working\n- ✅ If unclear: STOP and ask for clarification on ALL unclear items first\n- ✅ YAGNI check: grep for usage before implementing suggested \"proper\" features\n\n### Source Handling\n- **Human partner:** Trusted - implement after understanding, no performative agreement\n- **External reviewers:** Verify technically correct, check for breakage, push back if wrong\n\n**Full protocol:** `references\u002Fcode-review-reception.md`\n\n## Requesting Review Protocol\n\n### When to Request\n- After each task in subagent-driven development\n- After major feature completion\n- Before merge to main\n\n### Process\n1. Get git SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`\n2. Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION\n3. Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later\n\n**Full protocol:** `references\u002Frequesting-code-review.md`\n\n## Verification Gates Protocol\n\n### The Iron Law\n**NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE**\n\n### Gate Function\nIDENTIFY command → RUN full command → READ output → VERIFY confirms claim → THEN claim\n\nSkip any step = lying, not verifying\n\n### Requirements\n- Tests pass: Test output shows 0 failures\n- Build succeeds: Build command exit 0\n- Bug fixed: Test original symptom passes\n- Requirements met: Line-by-line checklist verified\n\n### Red Flags - STOP\nUsing \"should\"\u002F\"probably\"\u002F\"seems to\", expressing satisfaction before verification, committing without verification, trusting agent reports, ANY wording implying success without running verification\n\n**Full protocol:** `references\u002Fverification-before-completion.md`\n\n## Integration with Workflows\n\n- **Subagent-Driven:** Review after EACH task, verify before moving to next\n- **Pull Requests:** Verify tests pass, request code-reviewer review before merge\n- **General:** Apply verification gates before any status claims, push back on invalid feedback\n\n## Bottom Line\n\n1. Technical rigor over social performance - No performative agreement\n2. Systematic review processes - Use code-reviewer subagent\n3. Evidence before claims - Verification gates always\n\nVerify. Question. Then implement. Evidence. Then claim.\n",{"name":5,"description":7},"main","c6237323cdebe9c0193c97f1a338cb169728d78d","fixtures\u002Flocal-skills\u002Fcode-review",0,"https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner","https:\u002F\u002Fgithub.com\u002Fvntopicai","2026-05-13 18:29:40",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add vntopicai\u002Fai-planner --skill code-review",{"tool":66,"command":67},"bunx","bunx skills add vntopicai\u002Fai-planner --skill code-review",{"tool":69,"command":70},"pnpm","pnpm dlx skills add vntopicai\u002Fai-planner --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fcode-review\u002FSKILL.md",true,[74,80,84],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fcode-review-reception.md","REFERENCE","参考文档",6110,"https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fcode-review\u002Freferences\u002Fcode-review-reception.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Frequesting-code-review.md",2773,"https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fcode-review\u002Freferences\u002Frequesting-code-review.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fverification-before-completion.md",4200,"https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fcode-review\u002Freferences\u002Fverification-before-completion.md",[89,128,141,157,184,211],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":107,"publishedAt":48},"01M6NRX0GTVS1XTC035TQFBD6R","ui-ux-pro-max","Frontend UI\u002FUX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. The primary skill for design decisions before implementation. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check frontend UI\u002FUX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fui-ux-pro-max\u002FSKILL.md",[95,98,101,104],{"categoryNo":96,"categoryName":97,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":102,"categoryName":103,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":105,"categoryName":106,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师",[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"ui ux","ux","ui","ui ux pro max","max","pro","Tailwind","mode","card","chart","app","tsx","fix","projects","improve","Charts","Animation","actions","design","frontend",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":48},"01M6NRWHBP9GJK3QP0SDZ5JKMZ","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Ftemplate-skill\u002FSKILL.md",[134],{"categoryNo":102,"categoryName":103,"taxonomyType":20,"taxonomyTypeDesc":21},[136,137,138,139,140],"template skill","template","with","it","use",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":150,"publishedAt":48},"01M6NRW447KC6JHJETVDTS0D25","research","Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fresearch\u002FSKILL.md",[147],{"categoryNo":148,"categoryName":149,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[143,151,152,153,154,140,155,156],"secure","plan","analyze","technical","Scalable","you",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":48},"01M6NRVG7DA75KBK2XKCHQW8YT","Problem-Solving Techniques","Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fproblem-solving\u002FSKILL.md",[],[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183],"techniques","Problem Solving Techniques","problem","problem solving","uncertainty","simplification","apply","inversion","for","Inversion Exercise","project","problem-solving","thinking","Scale Game","complexity","recurring","game","exercise","Meta","when stuck",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":48},"01M6NRV95P9DA08M92S4BHRG1M","payment-integration","Implement payment integrations with SePay (Vietnamese payment gateway with VietQR, bank transfers, cards) and Polar (global SaaS monetization platform with subscriptions, usage-based billing, automated benefits). Use when integrating payment processing, implementing checkout flows, managing subscriptions, handling webhooks, processing bank transfers, generating QR codes, automating benefit delivery, or building billing systems. Supports authentication (API keys, OAuth2), product management, customer portals, tax compliance (Polar as MoR), and comprehensive SDK integrations (Node.js, PHP, Python, Go, Laravel, Next.js).","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fpayment-integration\u002FSKILL.md",[],[191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210],"payment","payment integration","integration","laravel","api","product","authentication","customer","node","implementing","api keys","bank","transfers","qr","flows","billing","processing","checkout","delivery","next",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":48},"01M6NRV5BXB7JXQXWBHQJZ36AJ","nodejs-best-practices","Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.","https:\u002F\u002Fgithub.com\u002Fvntopicai\u002Fai-planner\u002Fblob\u002Fmain\u002Ffixtures\u002Flocal-skills\u002Fnodejs-best-practices\u002FSKILL.md",[],[218,219,220,221,222,223,224,225,176,226,227,228,199,229,230,231,232,233,234],"best practices","nodejs","nodejs best practices","selection","unknown","principles","decision-making","patterns","community","async","framework selection","decision","js","framework","development","architecture","security"]