[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NV43KDCJ583HHDG98CTDRW":3,"skill-same:01M6NV43KDCJ583HHDG98CTDRW":63},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6NV43KDCJ583HHDG98CTDRW","insecure-defaults",null,"Detect fail-open configurations, hardcoded secrets, weak authentication defaults, permissive CORS, disabled security features, and other insecure-by-default patterns. Adapted from Trail of Bits. Use during security review or when auditing configuration and initialization code.","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\u002Finsecure-defaults\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"insecure defaults","use","features","initialization","trail","detect","patterns","configuration","default","review","open","cors","secrets","authentication","code","security review","security","2026-11-10 10:12:30",false,"---\nname: insecure-defaults\ndescription: Detect fail-open configurations, hardcoded secrets, weak authentication defaults, permissive CORS, disabled security features, and other insecure-by-default patterns. Adapted from Trail of Bits. Use during security review or when auditing configuration and initialization code.\n---\n\n# Insecure Defaults Detection\n\nSystematic detection of security misconfigurations where the default behavior is insecure. These are the bugs that ship because \"it worked in development.\"\n\n## Detection Categories\n\n### 1. Fail-Open Configurations\n\nCode that defaults to allowing access when a security check fails.\n\n```typescript\n\u002F\u002F BAD: Fail-open -- if auth service is down, everyone gets in\nasync function checkAuth(token: string): Promise\u003Cboolean> {\n  try {\n    return await authService.verify(token)\n  } catch {\n    return true  \u002F\u002F INSECURE: fails open\n  }\n}\n\n\u002F\u002F GOOD: Fail-closed -- if auth service is down, deny access\nasync function checkAuth(token: string): Promise\u003Cboolean> {\n  try {\n    return await authService.verify(token)\n  } catch {\n    return false  \u002F\u002F SECURE: fails closed\n  }\n}\n```\n\n**Detection pattern**: Look for `catch` blocks that return truthy\u002Fpermissive values in auth\u002Fauthz code.\n\n### 2. Hardcoded Secrets\n\n```typescript\n\u002F\u002F BAD patterns -- detect ALL of these\nconst API_KEY = \"sk-proj-abc123\"\nconst DB_PASSWORD = \"admin123\"\nconst JWT_SECRET = \"super-secret-key\"\nconst ENCRYPTION_KEY = Buffer.from(\"0123456789abcdef\")\n\n\u002F\u002F GOOD\nconst API_KEY = process.env.API_KEY\nif (!API_KEY) throw new Error('API_KEY environment variable required')\n```\n\n**Detection patterns**:\n- String literals assigned to variables named `*key*`, `*secret*`, `*password*`, `*token*`, `*credential*`\n- Base64-encoded strings in source (potential embedded keys)\n- `Bearer ` followed by a string literal\n- AWS access keys (`AKIA...`), GitHub tokens (`ghp_...`), Stripe keys (`sk_live_...`)\n\n### 3. Weak Authentication Defaults\n\n```typescript\n\u002F\u002F BAD: Session without secure flags\napp.use(session({\n  secret: 'keyboard cat',      \u002F\u002F Hardcoded secret\n  cookie: {}                    \u002F\u002F Missing secure, httpOnly, sameSite\n}))\n\n\u002F\u002F GOOD\napp.use(session({\n  secret: process.env.SESSION_SECRET,\n  cookie: {\n    secure: true,               \u002F\u002F HTTPS only\n    httpOnly: true,             \u002F\u002F No JS access\n    sameSite: 'strict',         \u002F\u002F CSRF protection\n    maxAge: 3600000             \u002F\u002F 1 hour expiry\n  },\n  resave: false,\n  saveUninitialized: false\n}))\n```\n\n### 4. Permissive CORS\n\n```typescript\n\u002F\u002F BAD: Allow everything\napp.use(cors())                          \u002F\u002F Defaults to origin: '*'\napp.use(cors({ origin: '*' }))          \u002F\u002F Explicit wildcard\napp.use(cors({ origin: true }))         \u002F\u002F Reflect any origin\n\n\u002F\u002F GOOD: Explicit allowlist\napp.use(cors({\n  origin: ['https:\u002F\u002Fapp.example.com', 'https:\u002F\u002Fadmin.example.com'],\n  credentials: true,\n  methods: ['GET', 'POST', 'PUT', 'DELETE'],\n  allowedHeaders: ['Content-Type', 'Authorization']\n}))\n```\n\n### 5. Disabled Security Features\n\n```typescript\n\u002F\u002F BAD: Disabling security in code (not just config)\napp.disable('x-powered-by')  \u002F\u002F This one is actually GOOD\n\u002F\u002F But these are BAD:\nprocess.env.NODE_TLS_REJECT_UNAUTHORIZED = '0'  \u002F\u002F Disable TLS verification\nhelmet({ contentSecurityPolicy: false })          \u002F\u002F Disable CSP\napp.use(csrf({ ignoreMethods: ['POST'] }))       \u002F\u002F Disable CSRF for POST\n```\n\n**Detection pattern**: Look for `false`, `'0'`, `disable`, `skip`, `ignore` near security-related configs.\n\n### 6. Debug Mode in Production\n\n```typescript\n\u002F\u002F BAD: Debug flags that leak info\napp.use(errorHandler({ dumpExceptions: true, showStack: true }))\nmongoose.set('debug', true)\napp.set('env', 'development')  \u002F\u002F Hardcoded to dev\n\n\u002F\u002F GOOD: Environment-aware\nif (process.env.NODE_ENV !== 'production') {\n  mongoose.set('debug', true)\n}\n```\n\n### 7. Overly Permissive File\u002FDirectory Permissions\n\n```bash\n# BAD\nchmod 777 \u002Fapp\u002Fconfig\nchmod 666 \u002Fapp\u002F.env\n\n# GOOD\nchmod 600 \u002Fapp\u002F.env\nchmod 700 \u002Fapp\u002Fconfig\n```\n\n### 8. Missing Rate Limiting\n\n```typescript\n\u002F\u002F BAD: No rate limit on auth endpoints\napp.post('\u002Fapi\u002Flogin', loginHandler)\napp.post('\u002Fapi\u002Fregister', registerHandler)\napp.post('\u002Fapi\u002Fforgot-password', forgotPasswordHandler)\n\n\u002F\u002F GOOD: Rate limited\nconst authLimiter = rateLimit({\n  windowMs: 15 * 60 * 1000,  \u002F\u002F 15 minutes\n  max: 5,                     \u002F\u002F 5 attempts\n  message: 'Too many attempts, try again later'\n})\napp.post('\u002Fapi\u002Flogin', authLimiter, loginHandler)\n```\n\n### 9. Insecure Deserialization\n\n```typescript\n\u002F\u002F BAD: Deserializing untrusted input\nconst data = JSON.parse(userInput)        \u002F\u002F JSON is generally safe\nconst obj = yaml.load(userInput)           \u002F\u002F YAML can execute code!\nconst result = eval(userInput)             \u002F\u002F Never ever\n\n\u002F\u002F GOOD\nconst obj = yaml.load(userInput, { schema: yaml.FAILSAFE_SCHEMA })\n```\n\n### 10. Missing Security Headers\n\nRequired headers for web applications:\n\n```typescript\n\u002F\u002F Minimum security headers\napp.use(helmet())  \u002F\u002F Sets many headers, but verify:\n\n\u002F\u002F Or manually:\napp.use((req, res, next) => {\n  res.setHeader('X-Content-Type-Options', 'nosniff')\n  res.setHeader('X-Frame-Options', 'DENY')\n  res.setHeader('X-XSS-Protection', '0')  \u002F\u002F Disabled intentionally, CSP replaces it\n  res.setHeader('Strict-Transport-Security', 'max-age=31536000; includeSubDomains')\n  res.setHeader('Content-Security-Policy', \"default-src 'self'\")\n  res.setHeader('Referrer-Policy', 'strict-origin-when-cross-origin')\n  res.setHeader('Permissions-Policy', 'camera=(), microphone=(), geolocation=()')\n  next()\n})\n```\n\n## Audit Checklist\n\n```\nAuthentication:\n[ ] No hardcoded secrets in source code\n[ ] Session cookies have secure, httpOnly, sameSite flags\n[ ] JWT secrets are env vars, not constants\n[ ] Password hashing uses bcrypt\u002Fargon2 (not MD5\u002FSHA1)\n[ ] Default admin passwords don't exist\n\nAuthorization:\n[ ] Fail-closed on error (deny by default)\n[ ] No wildcard permissions in defaults\n[ ] Role checks can't be bypassed by omitting headers\n\nNetwork:\n[ ] CORS is not wildcard in production\n[ ] TLS verification is not disabled\n[ ] Rate limiting on auth and sensitive endpoints\n[ ] Security headers are set\n\nConfiguration:\n[ ] Debug mode is off in production\n[ ] Stack traces are not exposed to users\n[ ] Error messages don't leak internals\n[ ] File permissions are restrictive (600\u002F700)\n\nData:\n[ ] No sensitive data in logs\n[ ] No PII in URLs\u002Fquery strings\n[ ] Encryption keys are not hardcoded\n[ ] Database connections use TLS\n```\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|----------------|---------------|-----------------|\n| \"It's just for development\" | Dev configs ship to prod constantly | Use env-based config switching |\n| \"We'll secure it before launch\" | Deadline pressure skips security | Secure by default NOW |\n| \"The firewall protects us\" | Firewalls have holes, cloud is complex | Defense in depth required |\n| \"It's an internal API\" | Internal = one hop from external | Treat as semi-trusted |\n| \"Nobody knows this endpoint exists\" | Security through obscurity fails | Authenticate everything |\n\n## Integration with vibecosystem\n\n- **security-reviewer agent**: Primary consumer -- runs this checklist on every review\n- **code-reviewer agent**: Flags obvious insecure defaults during general review\n- **config-validator agent**: Applies these patterns to configuration files\n- **verifier agent**: Includes insecure default check in final quality gate\n\nInspired by [Trail of Bits](https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills) insecure-defaults plugin.\n","# Insecure Defaults Detection\n\nSystematic detection of security misconfigurations where the default behavior is insecure. These are the bugs that ship because \"it worked in development.\"\n\n## Detection Categories\n\n### 1. Fail-Open Configurations\n\nCode that defaults to allowing access when a security check fails.\n\n```typescript\n\u002F\u002F BAD: Fail-open -- if auth service is down, everyone gets in\nasync function checkAuth(token: string): Promise\u003Cboolean> {\n  try {\n    return await authService.verify(token)\n  } catch {\n    return true  \u002F\u002F INSECURE: fails open\n  }\n}\n\n\u002F\u002F GOOD: Fail-closed -- if auth service is down, deny access\nasync function checkAuth(token: string): Promise\u003Cboolean> {\n  try {\n    return await authService.verify(token)\n  } catch {\n    return false  \u002F\u002F SECURE: fails closed\n  }\n}\n```\n\n**Detection pattern**: Look for `catch` blocks that return truthy\u002Fpermissive values in auth\u002Fauthz code.\n\n### 2. Hardcoded Secrets\n\n```typescript\n\u002F\u002F BAD patterns -- detect ALL of these\nconst API_KEY = \"sk-proj-abc123\"\nconst DB_PASSWORD = \"admin123\"\nconst JWT_SECRET = \"super-secret-key\"\nconst ENCRYPTION_KEY = Buffer.from(\"0123456789abcdef\")\n\n\u002F\u002F GOOD\nconst API_KEY = process.env.API_KEY\nif (!API_KEY) throw new Error('API_KEY environment variable required')\n```\n\n**Detection patterns**:\n- String literals assigned to variables named `*key*`, `*secret*`, `*password*`, `*token*`, `*credential*`\n- Base64-encoded strings in source (potential embedded keys)\n- `Bearer ` followed by a string literal\n- AWS access keys (`AKIA...`), GitHub tokens (`ghp_...`), Stripe keys (`sk_live_...`)\n\n### 3. Weak Authentication Defaults\n\n```typescript\n\u002F\u002F BAD: Session without secure flags\napp.use(session({\n  secret: 'keyboard cat',      \u002F\u002F Hardcoded secret\n  cookie: {}                    \u002F\u002F Missing secure, httpOnly, sameSite\n}))\n\n\u002F\u002F GOOD\napp.use(session({\n  secret: process.env.SESSION_SECRET,\n  cookie: {\n    secure: true,               \u002F\u002F HTTPS only\n    httpOnly: true,             \u002F\u002F No JS access\n    sameSite: 'strict',         \u002F\u002F CSRF protection\n    maxAge: 3600000             \u002F\u002F 1 hour expiry\n  },\n  resave: false,\n  saveUninitialized: false\n}))\n```\n\n### 4. Permissive CORS\n\n```typescript\n\u002F\u002F BAD: Allow everything\napp.use(cors())                          \u002F\u002F Defaults to origin: '*'\napp.use(cors({ origin: '*' }))          \u002F\u002F Explicit wildcard\napp.use(cors({ origin: true }))         \u002F\u002F Reflect any origin\n\n\u002F\u002F GOOD: Explicit allowlist\napp.use(cors({\n  origin: ['https:\u002F\u002Fapp.example.com', 'https:\u002F\u002Fadmin.example.com'],\n  credentials: true,\n  methods: ['GET', 'POST', 'PUT', 'DELETE'],\n  allowedHeaders: ['Content-Type', 'Authorization']\n}))\n```\n\n### 5. Disabled Security Features\n\n```typescript\n\u002F\u002F BAD: Disabling security in code (not just config)\napp.disable('x-powered-by')  \u002F\u002F This one is actually GOOD\n\u002F\u002F But these are BAD:\nprocess.env.NODE_TLS_REJECT_UNAUTHORIZED = '0'  \u002F\u002F Disable TLS verification\nhelmet({ contentSecurityPolicy: false })          \u002F\u002F Disable CSP\napp.use(csrf({ ignoreMethods: ['POST'] }))       \u002F\u002F Disable CSRF for POST\n```\n\n**Detection pattern**: Look for `false`, `'0'`, `disable`, `skip`, `ignore` near security-related configs.\n\n### 6. Debug Mode in Production\n\n```typescript\n\u002F\u002F BAD: Debug flags that leak info\napp.use(errorHandler({ dumpExceptions: true, showStack: true }))\nmongoose.set('debug', true)\napp.set('env', 'development')  \u002F\u002F Hardcoded to dev\n\n\u002F\u002F GOOD: Environment-aware\nif (process.env.NODE_ENV !== 'production') {\n  mongoose.set('debug', true)\n}\n```\n\n### 7. Overly Permissive File\u002FDirectory Permissions\n\n```bash\n# BAD\nchmod 777 \u002Fapp\u002Fconfig\nchmod 666 \u002Fapp\u002F.env\n\n# GOOD\nchmod 600 \u002Fapp\u002F.env\nchmod 700 \u002Fapp\u002Fconfig\n```\n\n### 8. Missing Rate Limiting\n\n```typescript\n\u002F\u002F BAD: No rate limit on auth endpoints\napp.post('\u002Fapi\u002Flogin', loginHandler)\napp.post('\u002Fapi\u002Fregister', registerHandler)\napp.post('\u002Fapi\u002Fforgot-password', forgotPasswordHandler)\n\n\u002F\u002F GOOD: Rate limited\nconst authLimiter = rateLimit({\n  windowMs: 15 * 60 * 1000,  \u002F\u002F 15 minutes\n  max: 5,                     \u002F\u002F 5 attempts\n  message: 'Too many attempts, try again later'\n})\napp.post('\u002Fapi\u002Flogin', authLimiter, loginHandler)\n```\n\n### 9. Insecure Deserialization\n\n```typescript\n\u002F\u002F BAD: Deserializing untrusted input\nconst data = JSON.parse(userInput)        \u002F\u002F JSON is generally safe\nconst obj = yaml.load(userInput)           \u002F\u002F YAML can execute code!\nconst result = eval(userInput)             \u002F\u002F Never ever\n\n\u002F\u002F GOOD\nconst obj = yaml.load(userInput, { schema: yaml.FAILSAFE_SCHEMA })\n```\n\n### 10. Missing Security Headers\n\nRequired headers for web applications:\n\n```typescript\n\u002F\u002F Minimum security headers\napp.use(helmet())  \u002F\u002F Sets many headers, but verify:\n\n\u002F\u002F Or manually:\napp.use((req, res, next) => {\n  res.setHeader('X-Content-Type-Options', 'nosniff')\n  res.setHeader('X-Frame-Options', 'DENY')\n  res.setHeader('X-XSS-Protection', '0')  \u002F\u002F Disabled intentionally, CSP replaces it\n  res.setHeader('Strict-Transport-Security', 'max-age=31536000; includeSubDomains')\n  res.setHeader('Content-Security-Policy', \"default-src 'self'\")\n  res.setHeader('Referrer-Policy', 'strict-origin-when-cross-origin')\n  res.setHeader('Permissions-Policy', 'camera=(), microphone=(), geolocation=()')\n  next()\n})\n```\n\n## Audit Checklist\n\n```\nAuthentication:\n[ ] No hardcoded secrets in source code\n[ ] Session cookies have secure, httpOnly, sameSite flags\n[ ] JWT secrets are env vars, not constants\n[ ] Password hashing uses bcrypt\u002Fargon2 (not MD5\u002FSHA1)\n[ ] Default admin passwords don't exist\n\nAuthorization:\n[ ] Fail-closed on error (deny by default)\n[ ] No wildcard permissions in defaults\n[ ] Role checks can't be bypassed by omitting headers\n\nNetwork:\n[ ] CORS is not wildcard in production\n[ ] TLS verification is not disabled\n[ ] Rate limiting on auth and sensitive endpoints\n[ ] Security headers are set\n\nConfiguration:\n[ ] Debug mode is off in production\n[ ] Stack traces are not exposed to users\n[ ] Error messages don't leak internals\n[ ] File permissions are restrictive (600\u002F700)\n\nData:\n[ ] No sensitive data in logs\n[ ] No PII in URLs\u002Fquery strings\n[ ] Encryption keys are not hardcoded\n[ ] Database connections use TLS\n```\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|----------------|---------------|-----------------|\n| \"It's just for development\" | Dev configs ship to prod constantly | Use env-based config switching |\n| \"We'll secure it before launch\" | Deadline pressure skips security | Secure by default NOW |\n| \"The firewall protects us\" | Firewalls have holes, cloud is complex | Defense in depth required |\n| \"It's an internal API\" | Internal = one hop from external | Treat as semi-trusted |\n| \"Nobody knows this endpoint exists\" | Security through obscurity fails | Authenticate everything |\n\n## Integration with vibecosystem\n\n- **security-reviewer agent**: Primary consumer -- runs this checklist on every review\n- **code-reviewer agent**: Flags obvious insecure defaults during general review\n- **config-validator agent**: Applies these patterns to configuration files\n- **verifier agent**: Includes insecure default check in final quality gate\n\nInspired by [Trail of Bits](https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills) insecure-defaults plugin.\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Finsecure-defaults","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":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add rubicanjr\u002FFinCognis --skill insecure-defaults",{"tool":55,"command":56},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill insecure-defaults",{"tool":58,"command":59},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill insecure-defaults","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Finsecure-defaults\u002FSKILL.md",true,[],[64,85,94,113,142,159],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":75,"publishedAt":36},"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",[70],{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[76,77,78,79,80,81,82,83,84],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":36},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[87,92,93],"verification","false",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":103,"publishedAt":36},"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",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000015","视觉设计",[104,25,105,106,107,108,109,110,111,112],"websocket","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":123,"publishedAt":36},"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",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},[124,125,126,127,128,129,130,131,132,133,134,135,136,106,137,138,139,140,20,141],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","frontend development",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":36},"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",[],[149,150,92,151,28,35,152,153,154,155,156,157,158],"verification loop","loop","lint","pr","system","diff","build","tests","diff review","types",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":36},"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",[],[166,167,168,169,25,170,171,172,173,110,174,175,176,177,178,133,179,180],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]