[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-8aa6dc4a-ed30-465d-b6a6-e79f6f06ca98":3,"$fqwQb0w6H9N863dB5HomnJlcj3nKQ67_govFphIIki20":42},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":33},"8aa6dc4a-ed30-465d-b6a6-e79f6f06ca98","bdistill-knowledge-extraction","从AI模型中提取会话中的结构化领域知识或通过Ollama从本地开源模型中提取。无需API密钥。","cat_coding_backend","mod_coding","sickn33,coding","---\nname: bdistill-knowledge-extraction\ndescription: \"Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.\"\ncategory: ai-research\nrisk: safe\nsource: community\ndate_added: \"2026-03-20\"\nauthor: FrancyJGLisboa\ntags: [ai, knowledge-extraction, domain-specific, data-moat, mcp, reference-data]\ntools: [claude, cursor, codex, copilot]\n---\n\n# Knowledge Extraction\n\nExtract structured, quality-scored domain knowledge from any AI model — in-session from closed models (no API key) or locally from open-source models via Ollama.\n\n## Overview\n\nbdistill turns your AI subscription sessions into a compounding knowledge base. The agent answers targeted domain questions, bdistill structures and quality-scores the responses, and the output accumulates into a searchable, exportable reference dataset.\n\nAdversarial mode challenges the agent's claims — forcing evidence, corrections, and acknowledged limitations — producing validated knowledge entries.\n\n## When to Use This Skill\n\n- Use when you need structured reference data on any domain (medical, legal, finance, cybersecurity)\n- Use when building lookup tables, Q&A datasets, or research corpora\n- Use when generating training data for traditional ML models (regression, classification — NOT competing LLMs)\n- Use when you want cross-model comparison on domain knowledge\n\n## How It Works\n\n### Step 1: Install\n\n```bash\npip install bdistill\nclaude mcp add bdistill -- bdistill-mcp   # Claude Code\n```\n\n### Step 2: Extract knowledge in-session\n\n```\n\u002Fdistill medical cardiology                    # Preset domain\n\u002Fdistill --custom kubernetes docker helm       # Custom terms\n\u002Fdistill --adversarial medical                 # With adversarial validation\n```\n\n### Step 3: Search, export, compound\n\n```bash\nbdistill kb list                               # Show all domains\nbdistill kb search \"atrial fibrillation\"       # Keyword search\nbdistill kb export -d medical -f csv           # Export as spreadsheet\nbdistill kb export -d medical -f markdown      # Readable knowledge document\n```\n\n## Output Format\n\nStructured reference JSONL — not training data:\n\n```json\n{\n  \"question\": \"What causes myocardial infarction?\",\n  \"answer\": \"Myocardial infarction results from acute coronary artery occlusion...\",\n  \"domain\": \"medical\",\n  \"category\": \"cardiology\",\n  \"tags\": [\"mechanistic\", \"evidence-based\"],\n  \"quality_score\": 0.73,\n  \"confidence\": 1.08,\n  \"validated\": true,\n  \"source_model\": \"Claude Sonnet 4\"\n}\n```\n\n## Tabular ML Data Generation\n\nGenerate structured training data for traditional ML models:\n\n```\n\u002Fschema sepsis | hr:float, bp:float, temp:float, wbc:float | risk:category[low,moderate,high,critical]\n```\n\nExports as CSV ready for pandas\u002Fsklearn. Each row tracks source_model for cross-model analysis.\n\n## Local Model Extraction (Ollama)\n\nFor open-source models running locally:\n\n```bash\n# Install Ollama from https:\u002F\u002Follama.com\nollama serve\nollama pull qwen3:4b\n\nbdistill extract --domain medical --model qwen3:4b\n```\n\n## Security & Safety Notes\n\n- In-session extraction uses your existing subscription — no additional API keys\n- Local extraction runs entirely on your machine via Ollama\n- No data is sent to external services\n- Output is reference data, not LLM training format\n\n## Related Skills\n\n- `@bdistill-behavioral-xray` - X-ray a model's behavioral patterns\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,104,1942,"2026-05-16 13:08:33",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"编程开发","coding","mdi-code-braces","代码生成、调试、审查，提升开发效率",2,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":25,"skillCount":32,"createdAt":26},"后端开发","backend","mdi-server","API、数据库、服务端架构",296,[34],{"id":35,"skillId":4,"version":36,"fileName":37,"fileSize":38,"filePath":39,"fileHash":40,"manifest":41,"createdAt":19},"0052d2fd-f7ae-4400-8d4d-80e981519a1c","1.0.0","bdistill-knowledge-extraction.zip",1812,"uploads\u002Fskills\u002F8aa6dc4a-ed30-465d-b6a6-e79f6f06ca98\u002Fbdistill-knowledge-extraction.zip","bb067e6efa88f63db22166bb2a1f8e3d354cd9751481b0fde0af47b704289bec","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":3716}]",{"code":43,"message":44,"data":45},200,"success",{"items":46,"stats":47,"page":50},[],{"averageRating":48,"totalRatings":48,"ratingCounts":49},0,[48,48,48,48,48],{"limit":51,"offset":48,"hasMore":52,"nextOffset":51,"ratedOnly":16},15,false]