[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWS3RETSC0SHP16HP66E14":3,"skill-same:01M6NWS3RETSC0SHP16HP66E14":48},{"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":21,"linkOnly":22,"markdownContent":23,"markdownBody":24,"frontMatter":25,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M6NWS3RETSC0SHP16HP66E14","wiring",null,"Wiring Verification","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\u002Fwiring\u002FSKILL.md",[],[5,19,20],"verification","false","2026-11-10 10:12:30",false,"---\nname: wiring\ndescription: Wiring Verification\nuser-invocable: false\n---\n\n# Wiring Verification\n\nWhen building infrastructure components, ensure they're actually invoked in the execution path.\n\n## Pattern\n\nEvery module needs a clear entry point. Dead code is worse than no code - it creates maintenance burden and false confidence.\n\n## The Four-Step Wiring Check\n\nBefore marking infrastructure \"done\", verify:\n\n1. **Entry Point Exists**: How does user action trigger this code?\n2. **Call Graph Traced**: Can you follow the path from entry to execution?\n3. **Integration Tested**: Does an end-to-end test exercise this path?\n4. **No Dead Code**: Is every built component actually reachable?\n\n## DO\n\n### Verify Entry Points\n\n```bash\n# Hook registered?\ngrep -r \"orchestration\" .claude\u002Fsettings.json\n\n# Skill activated?\ngrep -r \"skill-name\" .claude\u002Fskill-rules.json\n\n# Script executable?\nls -la scripts\u002Forchestrate.py\n\n# Module imported?\ngrep -r \"from orchestration_layer import\" .\n```\n\n### Trace Call Graphs\n\n```python\n# Entry point (hook)\n.claude\u002Fhooks\u002Fpre-tool-use.sh\n  ↓\n# Shell wrapper calls TypeScript\nnpx tsx pre-tool-use.ts\n  ↓\n# TypeScript calls Python script\nspawn('scripts\u002Forchestrate.py')\n  ↓\n# Script imports module\nfrom orchestration_layer import dispatch\n  ↓\n# Module executes\ndispatch(agent_type, task)\n```\n\n### Test End-to-End\n\n```bash\n# Don't just unit test the module\npytest tests\u002Funit\u002Forchestration_layer_test.py  # NOT ENOUGH\n\n# Test the full invocation path\necho '{\"tool\": \"Task\"}' | .claude\u002Fhooks\u002Fpre-tool-use.sh  # VERIFY THIS WORKS\n```\n\n### Document Wiring\n\n```markdown\n## Wiring\n\n- **Entry Point**: PreToolUse hook on Task tool\n- **Registration**: `.claude\u002Fsettings.json` line 45\n- **Call Path**: hook → pre-tool-use.ts → scripts\u002Forchestrate.py → orchestration_layer.py\n- **Test**: `tests\u002Fintegration\u002Ftask_orchestration_test.py`\n```\n\n## DON'T\n\n### Build Without Wiring\n\n```python\n# BAD: Created orchestration_layer.py with 500 lines\n# But nothing imports it or calls it\n# Result: Dead code, wasted effort\n\n# GOOD: Start with minimal wiring, then expand\n# 1. Create hook (10 lines)\n# 2. Test hook fires\n# 3. Add script (20 lines)\n# 4. Test script executes\n# 5. Add module logic (iterate)\n```\n\n### Create Parallel Routing\n\n```python\n# BAD: Agent router has dispatch logic\n# AND skill-rules.json has agent selection logic\n# AND hooks have agent filtering logic\n# Result: Three places to update, routing conflicts\n\n# GOOD: Single source of truth for routing\n# skill-rules.json activates skill → skill calls router → router dispatches\n```\n\n### Assume Imports Work\n\n```python\n# BAD: Assume because you wrote the code, it's imported\nfrom orchestration_layer import dispatch  # Does this path exist?\n\n# GOOD: Verify imports at integration test time\nuv run python -c \"from orchestration_layer import dispatch; print('OK')\"\n```\n\n### Skip Integration Tests\n\n```bash\n# BAD: Only unit test\npytest tests\u002Funit\u002F  # All pass, but nothing works end-to-end\n\n# GOOD: Integration test the wiring\npytest tests\u002Fintegration\u002F  # Verify full call path\n```\n\n## Common Wiring Gaps\n\n### Hook Not Registered\n\n```json\n\u002F\u002F .claude\u002Fsettings.json - hook definition exists but not in hooks section\n{\n  \"hooks\": {\n    \"PreToolUse\": []  \u002F\u002F Empty! Your hook never fires\n  }\n}\n```\n\n**Fix**: Add hook registration:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [{\n      \"matcher\": [\"Task\"],\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhooks\u002Forchestration.sh\"\n      }]\n    }]\n  }\n}\n```\n\n### Script Not Executable\n\n```bash\n# Script exists but can't execute\n-rw-r--r-- scripts\u002Forchestrate.py\n\n# Fix: Make executable\nchmod +x scripts\u002Forchestrate.py\n```\n\n### Module Not Importable\n\n```python\n# Script tries to import but path is wrong\nfrom orchestration_layer import dispatch\n# ModuleNotFoundError\n\n# Fix: Add to Python path or use proper package structure\nsys.path.insert(0, str(Path(__file__).parent.parent))\n```\n\n### Router Has No Dispatch Path\n\n```python\n# BAD: Router has beautiful mapping\nAGENT_MAP = {\n    \"implement\": ImplementAgent,\n    \"research\": ResearchAgent,\n    # ... 18 agent types\n}\n\n# But no dispatch function uses the map\ndef route(task):\n    return \"general-purpose\"  # Hardcoded! Map is dead code\n\n# GOOD: Dispatch actually uses the map\ndef route(task):\n    agent_type = classify(task)\n    return AGENT_MAP[agent_type]\n```\n\n## Wiring Checklist\n\nBefore marking infrastructure \"complete\":\n\n- [ ] Entry point identified and tested (hook\u002Fskill\u002FCLI)\n- [ ] Call graph documented (entry → module execution)\n- [ ] Integration test exercises full path\n- [ ] No orphaned modules (everything imported\u002Fcalled)\n- [ ] Registration complete (settings.json\u002Fskill-rules.json)\n- [ ] Permissions correct (scripts executable)\n- [ ] Import paths verified (manual import test passes)\n\n## Real-World Examples\n\n### Example 1: DAG Orchestration (This Session)\n\n**What was built:**\n- `opc\u002Forchestration\u002Forchestration_layer.py` (500+ lines)\n- `opc\u002Forchestration\u002Fdag\u002F` (DAG builder, validator, executor)\n- 18 agent type definitions\n- Sophisticated routing logic\n\n**Wiring gap:**\n- No hook calls orchestration_layer.py\n- No script imports the DAG modules\n- Agent routing returns hardcoded \"general-purpose\"\n- Result: 100% dead code\n\n**Fix:**\n1. Create PreToolUse hook for Task tool\n2. Hook calls `scripts\u002Forchestrate.py`\n3. Script imports and calls `orchestration_layer.dispatch()`\n4. Dispatch uses AGENT_MAP to route to actual agents\n5. Integration test: Submit Task → verify correct agent type used\n\n### Example 2: Artifact Index (Previous Session)\n\n**What was built:**\n- SQLite database schema\n- Indexing logic\n- Query functions\n\n**Wiring gap:**\n- No hook triggered indexing\n- Files created but never indexed\n\n**Fix:**\n1. PostToolUse hook on Write tool\n2. Hook calls indexing script immediately\n3. Integration test: Write file → verify indexed\n\n## Detection Strategy\n\n### Grep for Orphans\n\n```bash\n# Find Python modules\nfind . -name \"*.py\" -type f\n\n# Check if each is imported\nfor file in $(find . -name \"*.py\"); do\n  module=$(basename $file .py)\n  grep -r \"from.*$module import\\|import.*$module\" . || echo \"ORPHAN: $file\"\ndone\n```\n\n### Check Hook Registration\n\n```bash\n# List all hooks in .claude\u002Fhooks\u002F\nls .claude\u002Fhooks\u002F*.sh\n\n# Check each is registered\nfor hook in $(ls .claude\u002Fhooks\u002F*.sh); do\n  basename_hook=$(basename $hook)\n  grep -q \"$basename_hook\" .claude\u002Fsettings.json || echo \"UNREGISTERED: $hook\"\ndone\n```\n\n### Verify Script Execution\n\n```bash\n# Find all Python scripts\nfind scripts\u002F -name \"*.py\"\n\n# Test each can be imported\nfor script in $(find scripts\u002F -name \"*.py\"); do\n  uv run python -c \"import sys; sys.path.insert(0, 'scripts'); import $(basename $script .py)\" 2>\u002Fdev\u002Fnull || echo \"IMPORT FAIL: $script\"\ndone\n```\n\n## Source\n\n- This session: DAG orchestration wiring gap - 500+ lines of dead code discovered\n- Previous sessions: Artifact Index, LMStudio integration - wiring added after initial build\n","# Wiring Verification\n\nWhen building infrastructure components, ensure they're actually invoked in the execution path.\n\n## Pattern\n\nEvery module needs a clear entry point. Dead code is worse than no code - it creates maintenance burden and false confidence.\n\n## The Four-Step Wiring Check\n\nBefore marking infrastructure \"done\", verify:\n\n1. **Entry Point Exists**: How does user action trigger this code?\n2. **Call Graph Traced**: Can you follow the path from entry to execution?\n3. **Integration Tested**: Does an end-to-end test exercise this path?\n4. **No Dead Code**: Is every built component actually reachable?\n\n## DO\n\n### Verify Entry Points\n\n```bash\n# Hook registered?\ngrep -r \"orchestration\" .claude\u002Fsettings.json\n\n# Skill activated?\ngrep -r \"skill-name\" .claude\u002Fskill-rules.json\n\n# Script executable?\nls -la scripts\u002Forchestrate.py\n\n# Module imported?\ngrep -r \"from orchestration_layer import\" .\n```\n\n### Trace Call Graphs\n\n```python\n# Entry point (hook)\n.claude\u002Fhooks\u002Fpre-tool-use.sh\n  ↓\n# Shell wrapper calls TypeScript\nnpx tsx pre-tool-use.ts\n  ↓\n# TypeScript calls Python script\nspawn('scripts\u002Forchestrate.py')\n  ↓\n# Script imports module\nfrom orchestration_layer import dispatch\n  ↓\n# Module executes\ndispatch(agent_type, task)\n```\n\n### Test End-to-End\n\n```bash\n# Don't just unit test the module\npytest tests\u002Funit\u002Forchestration_layer_test.py  # NOT ENOUGH\n\n# Test the full invocation path\necho '{\"tool\": \"Task\"}' | .claude\u002Fhooks\u002Fpre-tool-use.sh  # VERIFY THIS WORKS\n```\n\n### Document Wiring\n\n```markdown\n## Wiring\n\n- **Entry Point**: PreToolUse hook on Task tool\n- **Registration**: `.claude\u002Fsettings.json` line 45\n- **Call Path**: hook → pre-tool-use.ts → scripts\u002Forchestrate.py → orchestration_layer.py\n- **Test**: `tests\u002Fintegration\u002Ftask_orchestration_test.py`\n```\n\n## DON'T\n\n### Build Without Wiring\n\n```python\n# BAD: Created orchestration_layer.py with 500 lines\n# But nothing imports it or calls it\n# Result: Dead code, wasted effort\n\n# GOOD: Start with minimal wiring, then expand\n# 1. Create hook (10 lines)\n# 2. Test hook fires\n# 3. Add script (20 lines)\n# 4. Test script executes\n# 5. Add module logic (iterate)\n```\n\n### Create Parallel Routing\n\n```python\n# BAD: Agent router has dispatch logic\n# AND skill-rules.json has agent selection logic\n# AND hooks have agent filtering logic\n# Result: Three places to update, routing conflicts\n\n# GOOD: Single source of truth for routing\n# skill-rules.json activates skill → skill calls router → router dispatches\n```\n\n### Assume Imports Work\n\n```python\n# BAD: Assume because you wrote the code, it's imported\nfrom orchestration_layer import dispatch  # Does this path exist?\n\n# GOOD: Verify imports at integration test time\nuv run python -c \"from orchestration_layer import dispatch; print('OK')\"\n```\n\n### Skip Integration Tests\n\n```bash\n# BAD: Only unit test\npytest tests\u002Funit\u002F  # All pass, but nothing works end-to-end\n\n# GOOD: Integration test the wiring\npytest tests\u002Fintegration\u002F  # Verify full call path\n```\n\n## Common Wiring Gaps\n\n### Hook Not Registered\n\n```json\n\u002F\u002F .claude\u002Fsettings.json - hook definition exists but not in hooks section\n{\n  \"hooks\": {\n    \"PreToolUse\": []  \u002F\u002F Empty! Your hook never fires\n  }\n}\n```\n\n**Fix**: Add hook registration:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [{\n      \"matcher\": [\"Task\"],\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhooks\u002Forchestration.sh\"\n      }]\n    }]\n  }\n}\n```\n\n### Script Not Executable\n\n```bash\n# Script exists but can't execute\n-rw-r--r-- scripts\u002Forchestrate.py\n\n# Fix: Make executable\nchmod +x scripts\u002Forchestrate.py\n```\n\n### Module Not Importable\n\n```python\n# Script tries to import but path is wrong\nfrom orchestration_layer import dispatch\n# ModuleNotFoundError\n\n# Fix: Add to Python path or use proper package structure\nsys.path.insert(0, str(Path(__file__).parent.parent))\n```\n\n### Router Has No Dispatch Path\n\n```python\n# BAD: Router has beautiful mapping\nAGENT_MAP = {\n    \"implement\": ImplementAgent,\n    \"research\": ResearchAgent,\n    # ... 18 agent types\n}\n\n# But no dispatch function uses the map\ndef route(task):\n    return \"general-purpose\"  # Hardcoded! Map is dead code\n\n# GOOD: Dispatch actually uses the map\ndef route(task):\n    agent_type = classify(task)\n    return AGENT_MAP[agent_type]\n```\n\n## Wiring Checklist\n\nBefore marking infrastructure \"complete\":\n\n- [ ] Entry point identified and tested (hook\u002Fskill\u002FCLI)\n- [ ] Call graph documented (entry → module execution)\n- [ ] Integration test exercises full path\n- [ ] No orphaned modules (everything imported\u002Fcalled)\n- [ ] Registration complete (settings.json\u002Fskill-rules.json)\n- [ ] Permissions correct (scripts executable)\n- [ ] Import paths verified (manual import test passes)\n\n## Real-World Examples\n\n### Example 1: DAG Orchestration (This Session)\n\n**What was built:**\n- `opc\u002Forchestration\u002Forchestration_layer.py` (500+ lines)\n- `opc\u002Forchestration\u002Fdag\u002F` (DAG builder, validator, executor)\n- 18 agent type definitions\n- Sophisticated routing logic\n\n**Wiring gap:**\n- No hook calls orchestration_layer.py\n- No script imports the DAG modules\n- Agent routing returns hardcoded \"general-purpose\"\n- Result: 100% dead code\n\n**Fix:**\n1. Create PreToolUse hook for Task tool\n2. Hook calls `scripts\u002Forchestrate.py`\n3. Script imports and calls `orchestration_layer.dispatch()`\n4. Dispatch uses AGENT_MAP to route to actual agents\n5. Integration test: Submit Task → verify correct agent type used\n\n### Example 2: Artifact Index (Previous Session)\n\n**What was built:**\n- SQLite database schema\n- Indexing logic\n- Query functions\n\n**Wiring gap:**\n- No hook triggered indexing\n- Files created but never indexed\n\n**Fix:**\n1. PostToolUse hook on Write tool\n2. Hook calls indexing script immediately\n3. Integration test: Write file → verify indexed\n\n## Detection Strategy\n\n### Grep for Orphans\n\n```bash\n# Find Python modules\nfind . -name \"*.py\" -type f\n\n# Check if each is imported\nfor file in $(find . -name \"*.py\"); do\n  module=$(basename $file .py)\n  grep -r \"from.*$module import\\|import.*$module\" . || echo \"ORPHAN: $file\"\ndone\n```\n\n### Check Hook Registration\n\n```bash\n# List all hooks in .claude\u002Fhooks\u002F\nls .claude\u002Fhooks\u002F*.sh\n\n# Check each is registered\nfor hook in $(ls .claude\u002Fhooks\u002F*.sh); do\n  basename_hook=$(basename $hook)\n  grep -q \"$basename_hook\" .claude\u002Fsettings.json || echo \"UNREGISTERED: $hook\"\ndone\n```\n\n### Verify Script Execution\n\n```bash\n# Find all Python scripts\nfind scripts\u002F -name \"*.py\"\n\n# Test each can be imported\nfor script in $(find scripts\u002F -name \"*.py\"); do\n  uv run python -c \"import sys; sys.path.insert(0, 'scripts'); import $(basename $script .py)\" 2>\u002Fdev\u002Fnull || echo \"IMPORT FAIL: $script\"\ndone\n```\n\n## Source\n\n- This session: DAG orchestration wiring gap - 500+ lines of dead code discovered\n- Previous sessions: Artifact Index, LMStudio integration - wiring added after initial build\n",{"name":5,"description":7,"user-invocable":22},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fwiring","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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add rubicanjr\u002FFinCognis --skill wiring",{"tool":40,"command":41},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill wiring",{"tool":43,"command":44},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill wiring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",true,[],[49,70,90,120,139,161],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":60,"publishedAt":21},"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",[55],{"categoryNo":56,"categoryName":57,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[61,62,63,64,65,66,67,68,69],"workflow router","router","workflow","goal","goals","user","workflow orchestration","tasks","orchestration",{"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":21},"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":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000015","视觉设计",[80,81,82,83,84,85,86,87,88,89],"websocket","patterns","websocket patterns","strategies","design","protocol","connection","management","binary","message",{"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":21},"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":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":56,"categoryName":57,"taxonomyType":58,"taxonomyTypeDesc":59},[101,102,103,104,105,106,107,108,109,110,111,112,113,84,114,115,116,117,118,119],"visual","verdict","visual verdict","across","revise","dimensions","frontend development","use","returns","ui","screenshot","qa","development","frontend","comparison","correctness","implementing","for","fixes",{"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":21},"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",[],[127,128,19,129,130,131,132,133,134,135,136,137,138],"verification loop","loop","system","diff review","tests","build","diff","lint","pr","security","review","types",{"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":21},"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",[],[146,147,148,81,149,150,151,152,153,154,118,155,156,157,158,159,83,160],"vector db patterns","vector db","db","vector","search","semantic search","rag","embedding strategies","hybrid","Hybrid Search","embedding","retrieval","semantic","chunking","algorithms",{"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":21},"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",[],[168,169,170,171,172,173,174,175,176,104,177,178,108,179,180,181,182,183,184,150],"variant","analysis","variant analysis","pattern","codebase","manual","pattern matching","propagate","matching","queries","bug","check","find","ast","semgrep","codeql","tracing"]