[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWS9DAXJTADT4T5MB49X8W":3,"skill-same:01M6NWS9DAXJTADT4T5MB49X8W":60},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router",null,"Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","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\u002Fworkflow-router\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"workflow","router","workflow router","orchestration","tasks","workflow orchestration","user","goal","goals","2026-11-10 10:12:30",false,"---\nname: workflow-router\ndescription: Goal-based workflow orchestration - routes tasks to specialist agents based on user goals\n---\n\n# Workflow Router\n\nYou are a goal-based workflow orchestrator. Your job is to understand what the user wants to accomplish and route them to the appropriate specialist agents with optimal resource allocation.\n\n## When to Use\n\nUse this skill when:\n- User wants to start a new task but hasn't specified a workflow\n- User asks \"how should I approach this?\"\n- User mentions wanting to explore, plan, build, or fix something\n- You need to orchestrate multiple agents for a complex task\n\n## Workflow Process\n\n### Step 1: Goal Selection\n\nFirst, determine the user's primary goal. Use the AskUserQuestion tool:\n\n```\nquestions=[{\n  \"question\": \"What's your primary goal for this task?\",\n  \"header\": \"Goal\",\n  \"options\": [\n    {\"label\": \"Research\", \"description\": \"Understand\u002Fexplore something - investigate unfamiliar code, libraries, or concepts\"},\n    {\"label\": \"Plan\", \"description\": \"Design\u002Farchitect a solution - create implementation plans, break down complex problems\"},\n    {\"label\": \"Build\", \"description\": \"Implement\u002Fcode something - write new features, create components, implement from a plan\"},\n    {\"label\": \"Fix\", \"description\": \"Debug\u002Ffix an issue - investigate and resolve bugs, debug failing tests\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nIf the user's intent is clear from context, you may infer the goal. Otherwise, ask explicitly using the tool above.\n\n### Step 2: Plan Detection\n\nBefore proceeding, check for existing plans:\n\n```bash\nls thoughts\u002Fshared\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull\n```\n\nIf plans exist:\n- For **Build** goal: Ask if they want to implement an existing plan\n- For **Plan** goal: Mention existing plans to avoid duplication\n- For **Research\u002FFix**: Proceed as normal\n\n### Step 3: Resource Allocation\n\nDetermine how many agents to use. Use the AskUserQuestion tool:\n\n```\nquestions=[{\n  \"question\": \"How would you like me to allocate resources?\",\n  \"header\": \"Resources\",\n  \"options\": [\n    {\"label\": \"Conservative\", \"description\": \"1-2 agents, sequential execution - minimal context usage, best for simple tasks\"},\n    {\"label\": \"Balanced (Recommended)\", \"description\": \"Appropriate agents for the task, some parallelism - best for most tasks\"},\n    {\"label\": \"Aggressive\", \"description\": \"Max parallel agents working simultaneously - best for time-critical tasks\"},\n    {\"label\": \"Auto\", \"description\": \"System decides based on task complexity\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nDefault to **Balanced** if not specified or if user selects Auto.\n\n### Step 4: Specialist Mapping\n\nRoute to the appropriate specialist based on goal:\n\n| Goal | Primary Agent | Alias | Description |\n|------|---------------|-------|-------------|\n| **Research** | oracle | Librarian | Comprehensive research using MCP tools (nia, perplexity, repoprompt, firecrawl) |\n| **Plan** | plan-agent | Oracle | Create implementation plans with phased approach |\n| **Build** | kraken | Kraken | Implementation agent - handles coding tasks via Task tool |\n| **Fix** | debug-agent | Sentinel | Investigate issues using codebase exploration and logs |\n\n**Fix workflow special case:** For Fix goals, first spawn debug-agent (Sentinel) to investigate. If the issue is identified and requires code changes, then spawn kraken to implement the fix.\n\n### Step 5: Confirmation\n\nBefore executing, show a summary and confirm using the AskUserQuestion tool:\n\nFirst, display the execution summary:\n\n```\n## Execution Summary\n\n**Goal:** [Research\u002FPlan\u002FBuild\u002FFix]\n**Resource Allocation:** [Conservative\u002FBalanced\u002FAggressive]\n**Agent(s) to spawn:** [agent names]\n\n**What will happen:**\n- [Brief description of what the agent(s) will do]\n- [Expected output\u002Fdeliverable]\n```\n\nThen use the AskUserQuestion tool for confirmation:\n\n```\nquestions=[{\n  \"question\": \"Ready to proceed with this workflow?\",\n  \"header\": \"Confirm\",\n  \"options\": [\n    {\"label\": \"Yes, proceed\", \"description\": \"Run the workflow with the settings above\"},\n    {\"label\": \"Adjust settings\", \"description\": \"Go back and modify goal or resource allocation\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nWait for user confirmation before spawning agents. If user selects \"Adjust settings\", return to the relevant step.\n\n## Agent Spawn Examples\n\n### Research (Librarian)\n```\nTask(\n  subagent_type=\"oracle\",\n  prompt=\"\"\"\n  Research: [topic]\n\n  Scope: [what to investigate]\n  Output: Create a handoff with findings at thoughts\u002Fhandoffs\u002F\u003Csession>\u002F\n  \"\"\"\n)\n```\n\n### Plan (Oracle)\n```\nTask(\n  subagent_type=\"plan-agent\",\n  prompt=\"\"\"\n  Create implementation plan for: [feature\u002Ftask]\n\n  Context: [relevant context]\n  Output: Save plan to thoughts\u002Fshared\u002Fplans\u002F\n  \"\"\"\n)\n```\n\n### Build (Kraken)\n\n**If plan exists:** Run pre-mortem before implementation:\n```\n\u002Fpremortem deep \u003Cplan-path>\n```\n\nThis identifies risks and blocks if HIGH severity issues found. User can accept, mitigate, or research solutions.\n\n**After premortem passes:**\n```\nTask(\n  subagent_type=\"kraken\",\n  prompt=\"\"\"\n  Implement: [task]\n\n  Plan location: [if applicable]\n  Tests: Run tests after implementation\n  \"\"\"\n)\n```\n\n### Fix (Sentinel then Kraken)\n```\n# Step 1: Investigate\nTask(\n  subagent_type=\"debug-agent\",\n  prompt=\"\"\"\n  Investigate: [issue description]\n\n  Symptoms: [what's failing]\n  Output: Diagnosis and recommended fix\n  \"\"\"\n)\n\n# Step 2: If fix identified, spawn kraken\nTask(\n  subagent_type=\"kraken\",\n  prompt=\"\"\"\n  Fix: [issue based on Sentinel's diagnosis]\n  \"\"\"\n)\n```\n\n## Invisible Routing Principle\n\nThe user should never see the orchestration machinery. They say what they want; the system routes silently.\n\n```\nGOOD: User says \"add dark mode\" → you silently pick Plan → spawn architect\nBAD:  User says \"add dark mode\" → you explain routing tables and agent selection\n```\n\nRoute invisibly. Act decisively. Only surface choices when genuinely ambiguous.\n\n## Decision Flowchart\n\n```\nUser input arrives\n    │\n    ├─ CLEAR intent? ──────→ Route directly (no questions)\n    │   \"fix the login bug\"     → Fix workflow\n    │   \"add a REST endpoint\"   → Build workflow\n    │\n    ├─ AMBIGUOUS intent? ──→ Ask MAX 1 clarifying question\n    │   \"improve the app\"       → \"What aspect? Performance \u002F UX \u002F Security?\"\n    │   \"work on auth\"          → \"Fix existing auth or build new?\"\n    │\n    └─ CONVERSATIONAL? ────→ Don't route. Just respond naturally.\n        \"how does X work?\"      → Explain directly\n        \"what do you think?\"    → Give opinion\n```\n\n## Fallback Strategy\n\nWhen no internal skill or agent fully covers the need:\n\n```\nStep 1: WORKAROUND  → Can an existing skill partially handle it?\nStep 2: COMBO       → Can 2+ skills combine to solve it?\nStep 3: CREATE      → Worth building a new skill? Use \u002Fskill-create\nStep 4: EXTERNAL    → Check external-skills-catalog for community options\n```\n\nReference the `external-skills-catalog` skill when reaching Step 4.\n\n## Tips\n\n- **Infer when possible:** If the user says \"this test is failing\", that's clearly a Fix goal\n- **Be adaptive:** Start with Balanced allocation; scale up if task proves complex\n- **Chain agents:** For complex tasks, Research -> Plan -> Premortem -> Build is the recommended flow\n- **Run premortem:** Before Build, always run `\u002Fpremortem deep` on the plan to catch risks early\n- **Preserve context:** Use handoffs between agents to maintain continuity\n- **Invisible routing:** Never explain the routing decision unless asked\n- **One question max:** If ambiguous, ask at most 1 question before routing\n","# Workflow Router\n\nYou are a goal-based workflow orchestrator. Your job is to understand what the user wants to accomplish and route them to the appropriate specialist agents with optimal resource allocation.\n\n## When to Use\n\nUse this skill when:\n- User wants to start a new task but hasn't specified a workflow\n- User asks \"how should I approach this?\"\n- User mentions wanting to explore, plan, build, or fix something\n- You need to orchestrate multiple agents for a complex task\n\n## Workflow Process\n\n### Step 1: Goal Selection\n\nFirst, determine the user's primary goal. Use the AskUserQuestion tool:\n\n```\nquestions=[{\n  \"question\": \"What's your primary goal for this task?\",\n  \"header\": \"Goal\",\n  \"options\": [\n    {\"label\": \"Research\", \"description\": \"Understand\u002Fexplore something - investigate unfamiliar code, libraries, or concepts\"},\n    {\"label\": \"Plan\", \"description\": \"Design\u002Farchitect a solution - create implementation plans, break down complex problems\"},\n    {\"label\": \"Build\", \"description\": \"Implement\u002Fcode something - write new features, create components, implement from a plan\"},\n    {\"label\": \"Fix\", \"description\": \"Debug\u002Ffix an issue - investigate and resolve bugs, debug failing tests\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nIf the user's intent is clear from context, you may infer the goal. Otherwise, ask explicitly using the tool above.\n\n### Step 2: Plan Detection\n\nBefore proceeding, check for existing plans:\n\n```bash\nls thoughts\u002Fshared\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull\n```\n\nIf plans exist:\n- For **Build** goal: Ask if they want to implement an existing plan\n- For **Plan** goal: Mention existing plans to avoid duplication\n- For **Research\u002FFix**: Proceed as normal\n\n### Step 3: Resource Allocation\n\nDetermine how many agents to use. Use the AskUserQuestion tool:\n\n```\nquestions=[{\n  \"question\": \"How would you like me to allocate resources?\",\n  \"header\": \"Resources\",\n  \"options\": [\n    {\"label\": \"Conservative\", \"description\": \"1-2 agents, sequential execution - minimal context usage, best for simple tasks\"},\n    {\"label\": \"Balanced (Recommended)\", \"description\": \"Appropriate agents for the task, some parallelism - best for most tasks\"},\n    {\"label\": \"Aggressive\", \"description\": \"Max parallel agents working simultaneously - best for time-critical tasks\"},\n    {\"label\": \"Auto\", \"description\": \"System decides based on task complexity\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nDefault to **Balanced** if not specified or if user selects Auto.\n\n### Step 4: Specialist Mapping\n\nRoute to the appropriate specialist based on goal:\n\n| Goal | Primary Agent | Alias | Description |\n|------|---------------|-------|-------------|\n| **Research** | oracle | Librarian | Comprehensive research using MCP tools (nia, perplexity, repoprompt, firecrawl) |\n| **Plan** | plan-agent | Oracle | Create implementation plans with phased approach |\n| **Build** | kraken | Kraken | Implementation agent - handles coding tasks via Task tool |\n| **Fix** | debug-agent | Sentinel | Investigate issues using codebase exploration and logs |\n\n**Fix workflow special case:** For Fix goals, first spawn debug-agent (Sentinel) to investigate. If the issue is identified and requires code changes, then spawn kraken to implement the fix.\n\n### Step 5: Confirmation\n\nBefore executing, show a summary and confirm using the AskUserQuestion tool:\n\nFirst, display the execution summary:\n\n```\n## Execution Summary\n\n**Goal:** [Research\u002FPlan\u002FBuild\u002FFix]\n**Resource Allocation:** [Conservative\u002FBalanced\u002FAggressive]\n**Agent(s) to spawn:** [agent names]\n\n**What will happen:**\n- [Brief description of what the agent(s) will do]\n- [Expected output\u002Fdeliverable]\n```\n\nThen use the AskUserQuestion tool for confirmation:\n\n```\nquestions=[{\n  \"question\": \"Ready to proceed with this workflow?\",\n  \"header\": \"Confirm\",\n  \"options\": [\n    {\"label\": \"Yes, proceed\", \"description\": \"Run the workflow with the settings above\"},\n    {\"label\": \"Adjust settings\", \"description\": \"Go back and modify goal or resource allocation\"}\n  ],\n  \"multiSelect\": false\n}]\n```\n\nWait for user confirmation before spawning agents. If user selects \"Adjust settings\", return to the relevant step.\n\n## Agent Spawn Examples\n\n### Research (Librarian)\n```\nTask(\n  subagent_type=\"oracle\",\n  prompt=\"\"\"\n  Research: [topic]\n\n  Scope: [what to investigate]\n  Output: Create a handoff with findings at thoughts\u002Fhandoffs\u002F\u003Csession>\u002F\n  \"\"\"\n)\n```\n\n### Plan (Oracle)\n```\nTask(\n  subagent_type=\"plan-agent\",\n  prompt=\"\"\"\n  Create implementation plan for: [feature\u002Ftask]\n\n  Context: [relevant context]\n  Output: Save plan to thoughts\u002Fshared\u002Fplans\u002F\n  \"\"\"\n)\n```\n\n### Build (Kraken)\n\n**If plan exists:** Run pre-mortem before implementation:\n```\n\u002Fpremortem deep \u003Cplan-path>\n```\n\nThis identifies risks and blocks if HIGH severity issues found. User can accept, mitigate, or research solutions.\n\n**After premortem passes:**\n```\nTask(\n  subagent_type=\"kraken\",\n  prompt=\"\"\"\n  Implement: [task]\n\n  Plan location: [if applicable]\n  Tests: Run tests after implementation\n  \"\"\"\n)\n```\n\n### Fix (Sentinel then Kraken)\n```\n# Step 1: Investigate\nTask(\n  subagent_type=\"debug-agent\",\n  prompt=\"\"\"\n  Investigate: [issue description]\n\n  Symptoms: [what's failing]\n  Output: Diagnosis and recommended fix\n  \"\"\"\n)\n\n# Step 2: If fix identified, spawn kraken\nTask(\n  subagent_type=\"kraken\",\n  prompt=\"\"\"\n  Fix: [issue based on Sentinel's diagnosis]\n  \"\"\"\n)\n```\n\n## Invisible Routing Principle\n\nThe user should never see the orchestration machinery. They say what they want; the system routes silently.\n\n```\nGOOD: User says \"add dark mode\" → you silently pick Plan → spawn architect\nBAD:  User says \"add dark mode\" → you explain routing tables and agent selection\n```\n\nRoute invisibly. Act decisively. Only surface choices when genuinely ambiguous.\n\n## Decision Flowchart\n\n```\nUser input arrives\n    │\n    ├─ CLEAR intent? ──────→ Route directly (no questions)\n    │   \"fix the login bug\"     → Fix workflow\n    │   \"add a REST endpoint\"   → Build workflow\n    │\n    ├─ AMBIGUOUS intent? ──→ Ask MAX 1 clarifying question\n    │   \"improve the app\"       → \"What aspect? Performance \u002F UX \u002F Security?\"\n    │   \"work on auth\"          → \"Fix existing auth or build new?\"\n    │\n    └─ CONVERSATIONAL? ────→ Don't route. Just respond naturally.\n        \"how does X work?\"      → Explain directly\n        \"what do you think?\"    → Give opinion\n```\n\n## Fallback Strategy\n\nWhen no internal skill or agent fully covers the need:\n\n```\nStep 1: WORKAROUND  → Can an existing skill partially handle it?\nStep 2: COMBO       → Can 2+ skills combine to solve it?\nStep 3: CREATE      → Worth building a new skill? Use \u002Fskill-create\nStep 4: EXTERNAL    → Check external-skills-catalog for community options\n```\n\nReference the `external-skills-catalog` skill when reaching Step 4.\n\n## Tips\n\n- **Infer when possible:** If the user says \"this test is failing\", that's clearly a Fix goal\n- **Be adaptive:** Start with Balanced allocation; scale up if task proves complex\n- **Chain agents:** For complex tasks, Research -> Plan -> Premortem -> Build is the recommended flow\n- **Run premortem:** Before Build, always run `\u002Fpremortem deep` on the plan to catch risks early\n- **Preserve context:** Use handoffs between agents to maintain continuity\n- **Invisible routing:** Never explain the routing decision unless asked\n- **One question max:** If ambiguous, ask at most 1 question before routing\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fworkflow-router","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":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add rubicanjr\u002FFinCognis --skill workflow-router",{"tool":52,"command":53},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill workflow-router",{"tool":55,"command":56},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill workflow-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",true,[],[61,70,90,120,139,161],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":33},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[63,68,69],"false","verification",{"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":79,"publishedAt":33},"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",[76],{"categoryNo":77,"categoryName":78,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[80,81,82,83,84,85,86,87,88,89],"websocket patterns","patterns","websocket","connection","binary","strategies","message","management","protocol","design",{"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":100,"publishedAt":33},"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",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[101,102,103,104,105,106,107,108,109,110,111,112,113,114,89,115,116,117,118,119],"visual verdict","verdict","visual","use","comparison","revise","across","dimensions","frontend development","returns","ui","screenshot","qa","development","frontend","correctness","fixes","for","implementing",{"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":126,"publishedAt":33},"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",[],[69,127,128,129,130,131,132,133,134,135,136,137,138],"verification loop","loop","types","review","security","pr","lint","system","diff","build","tests","diff review",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":33},"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",[],[146,147,148,81,149,150,151,152,153,154,85,155,156,157,158,159,118,160],"vector db patterns","vector db","db","vector","embedding strategies","embedding","retrieval","semantic","chunking","algorithms","Hybrid Search","search","semantic search","rag","hybrid",{"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":33},"01M6NWQFTGW6RQQRPQ4Z2XM2BK","variant-analysis","Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep\u002FCodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvariant-analysis\u002FSKILL.md",[],[168,169,170,171,172,173,174,175,176,177,107,178,179,180,181,182,183,184,157,104],"variant","analysis","variant analysis","find","check","ast","semgrep","tracing","codeql","pattern","matching","propagate","codebase","manual","pattern matching","queries","bug"]