[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTKY7VHPVTSWSME0H6CDX7":3,"skill-same:01M6NTKY7VHPVTSWSME0H6CDX7":71},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6NTKY7VHPVTSWSME0H6CDX7","differential-review",null,"Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP\u002FFOCUSED\u002FSURGICAL), git history correlation, and structured finding format. Adapted from Trail of Bits. Use when reviewing PRs, commits, or code changes for security implications.","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\u002Fdifferential-review\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"review","differential review","prs","code review","adaptive","changes","for","with","deep","use","history","format","commits","analysis","risk","correlation","blast radius","git","code","security","2026-11-10 10:12:30",false,"---\nname: differential-review\ndescription: Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP\u002FFOCUSED\u002FSURGICAL), git history correlation, and structured finding format. Adapted from Trail of Bits. Use when reviewing PRs, commits, or code changes for security implications.\n---\n\n# Differential Review\n\nSecurity-focused code review that adapts depth to codebase size and change risk. Goes beyond style -- finds vulnerabilities, logic errors, and blast radius.\n\n## Review Depth Modes\n\n### DEEP (Small codebase, \u003C 5K lines changed)\n- Line-by-line analysis of every changed file\n- Full control flow tracing through changed paths\n- Cross-reference every function call to its definition\n- Check all error paths and edge cases\n\n### FOCUSED (Medium codebase, 5K-50K lines)\n- Prioritize files touching auth, crypto, input parsing, state mutation\n- Trace data flow from inputs to outputs through changed code\n- Skip cosmetic changes (formatting, comments, renames)\n- Deep-dive only on security-sensitive paths\n\n### SURGICAL (Large codebase, > 50K lines)\n- Review only the diff, not surrounding code\n- Focus exclusively on: new attack surface, removed security controls, changed trust boundaries\n- Flag anything that needs a separate deep review\n\n## Review Process\n\n### Phase 1: Blast Radius Assessment\nBefore reading any code:\n\n```bash\n# What changed?\ngit diff --stat \u003Cbase>...\u003Chead>\n\n# How much changed?\ngit diff --shortstat \u003Cbase>...\u003Chead>\n\n# Which files are security-sensitive?\ngit diff --name-only \u003Cbase>...\u003Chead> | grep -iE '(auth|crypto|token|secret|permission|middleware|validator|sanitiz)'\n```\n\nClassify the change:\n- **Surface area**: How many files, functions, modules touched?\n- **Trust boundary crossing**: Does data flow between trust levels?\n- **Security control modification**: Are auth\u002Fauthz\u002Fvalidation\u002Fcrypto paths changed?\n- **Data model change**: Are schemas, types, or storage formats modified?\n\n### Phase 2: Git History Correlation\nCheck if the changed code has a history of bugs:\n\n```bash\n# How often has this file been changed? (churn = risk)\ngit log --oneline --follow \u003Cfile> | wc -l\n\n# Were there recent security fixes in this area?\ngit log --oneline --grep=\"fix\\|vuln\\|security\\|CVE\" -- \u003Cfile>\n\n# Who else has touched this code?\ngit log --format='%an' -- \u003Cfile> | sort | uniq -c | sort -rn\n```\n\nHigh churn + security fix history = increase review depth.\n\n### Phase 3: Structured Review\n\nFor each changed file, analyze in this order:\n\n1. **Input validation**: Are new inputs validated? Are existing validations preserved?\n2. **Authentication\u002FAuthorization**: Do access controls apply to new code paths?\n3. **Data flow**: Can untrusted data reach sensitive operations?\n4. **Error handling**: Do error paths leak information or skip cleanup?\n5. **State mutation**: Are state changes atomic? Race conditions possible?\n6. **Crypto usage**: Correct algorithms, key sizes, modes, IVs?\n7. **Logging**: Are sensitive values logged? Are security events NOT logged?\n\n## Finding Format\n\n```\n## [SEVERITY] Finding Title\n\n**Location**: file.ts:42-58\n**Category**: [Input Validation | Auth | Crypto | Data Flow | State | Logic]\n**Confidence**: [HIGH | MEDIUM | LOW]\n\n**Description**:\nWhat the vulnerability is, in one paragraph.\n\n**Impact**:\nWhat an attacker can achieve by exploiting this.\n\n**Proof**:\nThe specific code path or data flow that demonstrates the issue.\n\n**Recommendation**:\nConcrete fix with code example if possible.\n```\n\n## Severity Classification\n\n| Severity | Criteria | Examples |\n|----------|----------|---------|\n| CRITICAL | Remote exploitation, no auth required, data breach | SQL injection, auth bypass, RCE |\n| HIGH | Requires some access, significant impact | Privilege escalation, IDOR, stored XSS |\n| MEDIUM | Limited impact or complex exploitation | Reflected XSS, info disclosure, CSRF |\n| LOW | Minimal impact, defense-in-depth | Missing headers, verbose errors, weak config |\n| INFO | Best practice, no direct vulnerability | Code quality, missing rate limit, logging gap |\n\n## Rationalizations to Reject\n\nCommon excuses that lead to missed findings. Do NOT accept these:\n\n| Rationalization | Why It's Wrong | Required Action |\n|----------------|---------------|-----------------|\n| \"It's behind auth\" | Auth can be bypassed | Verify auth is enforced AND correct |\n| \"We trust this input\" | Trust boundaries change | Validate at every boundary |\n| \"It's just internal\" | Internal networks get compromised | Apply defense in depth |\n| \"Nobody would do that\" | Attackers do unexpected things | Test the unexpected case |\n| \"We'll fix it later\" | Later never comes in security | Flag it NOW with severity |\n| \"The framework handles it\" | Frameworks have bypasses | Verify the framework actually applies |\n| \"It's the same as before\" | Before might have been wrong too | Review the original if suspicious |\n\n## Anti-Hallucination Rules\n\n- **Never say \"It probably...\"** -- say \"Unclear; need to inspect X\"\n- **Never assume a function is safe** without reading its implementation\n- **Never skip a finding** because it seems minor -- document everything\n- **Every claim must reference a specific file and line number**\n- **If you haven't read the code, say so** -- don't infer behavior from names\n\n## Diff Review Checklist\n\n```\n[ ] Blast radius assessed (files, trust boundaries, security controls)\n[ ] Git history checked for churn and past security fixes\n[ ] All new inputs validated\n[ ] Auth\u002Fauthz applied to new endpoints\u002Fpaths\n[ ] Error handling doesn't leak sensitive info\n[ ] No hardcoded secrets or credentials\n[ ] State mutations are atomic\n[ ] Crypto usage follows current best practices\n[ ] Logging doesn't include sensitive data\n[ ] Removed code didn't contain security controls that are now missing\n[ ] Dependencies added\u002Fupdated are from trusted sources\n[ ] Test coverage exists for security-critical paths\n```\n\n## Integration with vibecosystem\n\n- **code-reviewer agent**: Use this skill for security-focused review depth\n- **security-reviewer agent**: Primary consumer of this skill\n- **coroner agent**: Use blast radius analysis for post-mortem propagation\n- **\u002Freview skill**: Automatically applies differential review to PRs\n\nInspired by [Trail of Bits](https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills) differential-review plugin.\n","# Differential Review\n\nSecurity-focused code review that adapts depth to codebase size and change risk. Goes beyond style -- finds vulnerabilities, logic errors, and blast radius.\n\n## Review Depth Modes\n\n### DEEP (Small codebase, \u003C 5K lines changed)\n- Line-by-line analysis of every changed file\n- Full control flow tracing through changed paths\n- Cross-reference every function call to its definition\n- Check all error paths and edge cases\n\n### FOCUSED (Medium codebase, 5K-50K lines)\n- Prioritize files touching auth, crypto, input parsing, state mutation\n- Trace data flow from inputs to outputs through changed code\n- Skip cosmetic changes (formatting, comments, renames)\n- Deep-dive only on security-sensitive paths\n\n### SURGICAL (Large codebase, > 50K lines)\n- Review only the diff, not surrounding code\n- Focus exclusively on: new attack surface, removed security controls, changed trust boundaries\n- Flag anything that needs a separate deep review\n\n## Review Process\n\n### Phase 1: Blast Radius Assessment\nBefore reading any code:\n\n```bash\n# What changed?\ngit diff --stat \u003Cbase>...\u003Chead>\n\n# How much changed?\ngit diff --shortstat \u003Cbase>...\u003Chead>\n\n# Which files are security-sensitive?\ngit diff --name-only \u003Cbase>...\u003Chead> | grep -iE '(auth|crypto|token|secret|permission|middleware|validator|sanitiz)'\n```\n\nClassify the change:\n- **Surface area**: How many files, functions, modules touched?\n- **Trust boundary crossing**: Does data flow between trust levels?\n- **Security control modification**: Are auth\u002Fauthz\u002Fvalidation\u002Fcrypto paths changed?\n- **Data model change**: Are schemas, types, or storage formats modified?\n\n### Phase 2: Git History Correlation\nCheck if the changed code has a history of bugs:\n\n```bash\n# How often has this file been changed? (churn = risk)\ngit log --oneline --follow \u003Cfile> | wc -l\n\n# Were there recent security fixes in this area?\ngit log --oneline --grep=\"fix\\|vuln\\|security\\|CVE\" -- \u003Cfile>\n\n# Who else has touched this code?\ngit log --format='%an' -- \u003Cfile> | sort | uniq -c | sort -rn\n```\n\nHigh churn + security fix history = increase review depth.\n\n### Phase 3: Structured Review\n\nFor each changed file, analyze in this order:\n\n1. **Input validation**: Are new inputs validated? Are existing validations preserved?\n2. **Authentication\u002FAuthorization**: Do access controls apply to new code paths?\n3. **Data flow**: Can untrusted data reach sensitive operations?\n4. **Error handling**: Do error paths leak information or skip cleanup?\n5. **State mutation**: Are state changes atomic? Race conditions possible?\n6. **Crypto usage**: Correct algorithms, key sizes, modes, IVs?\n7. **Logging**: Are sensitive values logged? Are security events NOT logged?\n\n## Finding Format\n\n```\n## [SEVERITY] Finding Title\n\n**Location**: file.ts:42-58\n**Category**: [Input Validation | Auth | Crypto | Data Flow | State | Logic]\n**Confidence**: [HIGH | MEDIUM | LOW]\n\n**Description**:\nWhat the vulnerability is, in one paragraph.\n\n**Impact**:\nWhat an attacker can achieve by exploiting this.\n\n**Proof**:\nThe specific code path or data flow that demonstrates the issue.\n\n**Recommendation**:\nConcrete fix with code example if possible.\n```\n\n## Severity Classification\n\n| Severity | Criteria | Examples |\n|----------|----------|---------|\n| CRITICAL | Remote exploitation, no auth required, data breach | SQL injection, auth bypass, RCE |\n| HIGH | Requires some access, significant impact | Privilege escalation, IDOR, stored XSS |\n| MEDIUM | Limited impact or complex exploitation | Reflected XSS, info disclosure, CSRF |\n| LOW | Minimal impact, defense-in-depth | Missing headers, verbose errors, weak config |\n| INFO | Best practice, no direct vulnerability | Code quality, missing rate limit, logging gap |\n\n## Rationalizations to Reject\n\nCommon excuses that lead to missed findings. Do NOT accept these:\n\n| Rationalization | Why It's Wrong | Required Action |\n|----------------|---------------|-----------------|\n| \"It's behind auth\" | Auth can be bypassed | Verify auth is enforced AND correct |\n| \"We trust this input\" | Trust boundaries change | Validate at every boundary |\n| \"It's just internal\" | Internal networks get compromised | Apply defense in depth |\n| \"Nobody would do that\" | Attackers do unexpected things | Test the unexpected case |\n| \"We'll fix it later\" | Later never comes in security | Flag it NOW with severity |\n| \"The framework handles it\" | Frameworks have bypasses | Verify the framework actually applies |\n| \"It's the same as before\" | Before might have been wrong too | Review the original if suspicious |\n\n## Anti-Hallucination Rules\n\n- **Never say \"It probably...\"** -- say \"Unclear; need to inspect X\"\n- **Never assume a function is safe** without reading its implementation\n- **Never skip a finding** because it seems minor -- document everything\n- **Every claim must reference a specific file and line number**\n- **If you haven't read the code, say so** -- don't infer behavior from names\n\n## Diff Review Checklist\n\n```\n[ ] Blast radius assessed (files, trust boundaries, security controls)\n[ ] Git history checked for churn and past security fixes\n[ ] All new inputs validated\n[ ] Auth\u002Fauthz applied to new endpoints\u002Fpaths\n[ ] Error handling doesn't leak sensitive info\n[ ] No hardcoded secrets or credentials\n[ ] State mutations are atomic\n[ ] Crypto usage follows current best practices\n[ ] Logging doesn't include sensitive data\n[ ] Removed code didn't contain security controls that are now missing\n[ ] Dependencies added\u002Fupdated are from trusted sources\n[ ] Test coverage exists for security-critical paths\n```\n\n## Integration with vibecosystem\n\n- **code-reviewer agent**: Use this skill for security-focused review depth\n- **security-reviewer agent**: Primary consumer of this skill\n- **coroner agent**: Use blast radius analysis for post-mortem propagation\n- **\u002Freview skill**: Automatically applies differential review to PRs\n\nInspired by [Trail of Bits](https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills) differential-review plugin.\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fdifferential-review","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":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add rubicanjr\u002FFinCognis --skill differential-review",{"tool":63,"command":64},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill differential-review",{"tool":66,"command":67},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill differential-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fdifferential-review\u002FSKILL.md",true,[],[72,91,100,120,148,165],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":81,"publishedAt":44},"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",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[82,83,84,85,86,87,88,89,90],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":44},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[93,98,99],"verification","false",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":109,"publishedAt":44},"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",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[110,111,112,113,114,115,116,117,118,119],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":130,"publishedAt":44},"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",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},[131,132,133,134,135,136,137,138,139,30,140,141,142,113,143,144,145,146,33,147],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","fixes","dimensions","frontend","development","qa","screenshot","returns","frontend development",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":44},"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",[],[155,156,98,157,24,43,158,159,160,161,162,163,164],"verification loop","loop","lint","pr","system","diff","build","tests","diff review","types",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":44},"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",[],[172,173,174,175,111,176,177,178,179,117,180,181,182,183,184,30,185,186],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]