[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTGMVPRXT0C1A7MVFPYHZC":3,"skill-same:01M6NTGMVPRXT0C1A7MVFPYHZC":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":18,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6NTGMVPRXT0C1A7MVFPYHZC","continuous-learning",null,"Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.","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\u002Fcontinuous-learning\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"learning","continuous learning","sessions","code","claude code sessions","save","extract","use","reusable","patterns","as","learned","for","2026-11-10 10:12:30",false,"---\nname: continuous-learning\ndescription: Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.\n---\n\n# Continuous Learning Skill\n\nAutomatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.\n\n## How It Works\n\nThis skill runs as a **Stop hook** at the end of each session:\n\n1. **Session Evaluation**: Checks if session has enough messages (default: 10+)\n2. **Pattern Detection**: Identifies extractable patterns from the session\n3. **Skill Extraction**: Saves useful patterns to `~\u002F.claude\u002Fskills\u002Flearned\u002F`\n\n## Configuration\n\nEdit `config.json` to customize:\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\n  \"patterns_to_detect\": [\n    \"error_resolution\",\n    \"user_corrections\",\n    \"workarounds\",\n    \"debugging_techniques\",\n    \"project_specific\"\n  ],\n  \"ignore_patterns\": [\n    \"simple_typos\",\n    \"one_time_fixes\",\n    \"external_api_issues\"\n  ]\n}\n```\n\n## Pattern Types\n\n| Pattern | Description |\n|---------|-------------|\n| `error_resolution` | How specific errors were resolved |\n| `user_corrections` | Patterns from user corrections |\n| `workarounds` | Solutions to framework\u002Flibrary quirks |\n| `debugging_techniques` | Effective debugging approaches |\n| `project_specific` | Project-specific conventions |\n\n## Hook Setup\n\nAdd to your `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## Why Stop Hook?\n\n- **Lightweight**: Runs once at session end\n- **Non-blocking**: Doesn't add latency to every message\n- **Complete context**: Has access to full session transcript\n\n## Related\n\n- [The Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - Section on continuous learning\n- `\u002Flearn` command - Manual pattern extraction mid-session\n\n---\n\n## Comparison Notes (Research: Jan 2025)\n\n### vs Homunculus (github.com\u002Fhumanplane\u002Fhomunculus)\n\nHomunculus v2 takes a more sophisticated approach:\n\n| Feature | Our Approach | Homunculus v2 |\n|---------|--------------|---------------|\n| Observation | Stop hook (end of session) | PreToolUse\u002FPostToolUse hooks (100% reliable) |\n| Analysis | Main context | Background agent (Haiku) |\n| Granularity | Full skills | Atomic \"instincts\" |\n| Confidence | None | 0.3-0.9 weighted |\n| Evolution | Direct to skill | Instincts → cluster → skill\u002Fcommand\u002Fagent |\n| Sharing | None | Export\u002Fimport instincts |\n\n**Key insight from homunculus:**\n> \"v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time. v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior.\"\n\n### Potential v2 Enhancements\n\n1. **Instinct-based learning** - Smaller, atomic behaviors with confidence scoring\n2. **Background observer** - Haiku agent analyzing in parallel\n3. **Confidence decay** - Instincts lose confidence if contradicted\n4. **Domain tagging** - code-style, testing, git, debugging, etc.\n5. **Evolution path** - Cluster related instincts into skills\u002Fcommands\n\nSee the continuous-learning-v2 spec for full details.\n","# Continuous Learning Skill\n\nAutomatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.\n\n## How It Works\n\nThis skill runs as a **Stop hook** at the end of each session:\n\n1. **Session Evaluation**: Checks if session has enough messages (default: 10+)\n2. **Pattern Detection**: Identifies extractable patterns from the session\n3. **Skill Extraction**: Saves useful patterns to `~\u002F.claude\u002Fskills\u002Flearned\u002F`\n\n## Configuration\n\nEdit `config.json` to customize:\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\n  \"patterns_to_detect\": [\n    \"error_resolution\",\n    \"user_corrections\",\n    \"workarounds\",\n    \"debugging_techniques\",\n    \"project_specific\"\n  ],\n  \"ignore_patterns\": [\n    \"simple_typos\",\n    \"one_time_fixes\",\n    \"external_api_issues\"\n  ]\n}\n```\n\n## Pattern Types\n\n| Pattern | Description |\n|---------|-------------|\n| `error_resolution` | How specific errors were resolved |\n| `user_corrections` | Patterns from user corrections |\n| `workarounds` | Solutions to framework\u002Flibrary quirks |\n| `debugging_techniques` | Effective debugging approaches |\n| `project_specific` | Project-specific conventions |\n\n## Hook Setup\n\nAdd to your `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## Why Stop Hook?\n\n- **Lightweight**: Runs once at session end\n- **Non-blocking**: Doesn't add latency to every message\n- **Complete context**: Has access to full session transcript\n\n## Related\n\n- [The Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - Section on continuous learning\n- `\u002Flearn` command - Manual pattern extraction mid-session\n\n---\n\n## Comparison Notes (Research: Jan 2025)\n\n### vs Homunculus (github.com\u002Fhumanplane\u002Fhomunculus)\n\nHomunculus v2 takes a more sophisticated approach:\n\n| Feature | Our Approach | Homunculus v2 |\n|---------|--------------|---------------|\n| Observation | Stop hook (end of session) | PreToolUse\u002FPostToolUse hooks (100% reliable) |\n| Analysis | Main context | Background agent (Haiku) |\n| Granularity | Full skills | Atomic \"instincts\" |\n| Confidence | None | 0.3-0.9 weighted |\n| Evolution | Direct to skill | Instincts → cluster → skill\u002Fcommand\u002Fagent |\n| Sharing | None | Export\u002Fimport instincts |\n\n**Key insight from homunculus:**\n> \"v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time. v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior.\"\n\n### Potential v2 Enhancements\n\n1. **Instinct-based learning** - Smaller, atomic behaviors with confidence scoring\n2. **Background observer** - Haiku agent analyzing in parallel\n3. **Confidence decay** - Instincts lose confidence if contradicted\n4. **Domain tagging** - code-style, testing, git, debugging, etc.\n5. **Evolution path** - Cluster related instincts into skills\u002Fcommands\n\nSee the continuous-learning-v2 spec for full details.\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fcontinuous-learning","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":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add rubicanjr\u002FFinCognis --skill continuous-learning",{"tool":51,"command":52},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill continuous-learning",{"tool":54,"command":55},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill continuous-learning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fcontinuous-learning\u002FSKILL.md",true,[59,65],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"config.json","REFERENCE","参考文档",391,"https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fcontinuous-learning\u002Fconfig.json",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"evaluate-session.sh","SCRIPT","脚本",2015,"https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh",[72,93,102,121,149,168],{"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":83,"publishedAt":32},"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":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[84,85,86,87,88,89,90,91,92],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":32},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[95,100,101],"verification","false",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":111,"publishedAt":32},"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",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000015","视觉设计",[112,28,113,114,115,116,117,118,119,120],"websocket","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":131,"publishedAt":32},"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",[127,130],{"categoryNo":128,"categoryName":129,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[132,133,134,135,136,137,138,139,140,31,141,142,143,114,144,145,146,147,26,148],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","fixes","dimensions","frontend","development","qa","screenshot","returns","frontend development",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":32},"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",[],[156,157,100,158,159,160,161,162,163,164,165,166,167],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":32},"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",[],[175,176,177,178,28,179,180,181,182,118,183,184,185,186,187,31,188,189],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]