[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K4SFASKKVFHK3CVC8YWHH":3,"skill-same:01M75K4SFASKKVFHK3CVC8YWHH":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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M75K4SFASKKVFHK3CVC8YWHH","research-library",null,"Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references. Async extraction. Backup + restore.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjonbuckles\u002Fresearch-library\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: research-library\ndescription: Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references. Async extraction. Backup + restore.\nversion: 0.1.0\nauthor: Sage (for Jon Buckles)\nlicense: MIT\ntags:\n  - knowledge-management\n  - research\n  - hardware\n  - documentation\n  - sqlite\n  - fts5\nrepository: https:\u002F\u002Fgithub.com\u002F[user]\u002Fresearch-library\nkeywords:\n  - library\n  - search\n  - extraction\n  - project-management\n  - knowledge-base\n---\n\n# Research Library Skill\n\nA local-first multimedia research library for capturing, organizing, and searching hardware project knowledge.\n\n## What It Does\n\n- **Store documents** — Code, PDFs, CAD files, images, schematics\n- **Extract automatically** — Text from PDFs, EXIF from images, functions from code\n- **Search intelligently** — Full-text with material-type weighting (your work ranks higher than external research)\n- **Project isolation** — Arduino separate from CNC; no contamination\n- **Cross-reference** — Link knowledge: \"this servo tuning applies to that project\"\n- **Async extraction** — Searches never block while OCR runs\n- **Backup daily** — 30-day rolling snapshots\n\n## Installation\n\n```bash\nclawhub install research-library\n# OR\npip install \u002Fpath\u002Fto\u002Fresearch-library\n```\n\n## Quick Start\n\n```bash\n# Initialize database\nreslib status\n\n# Add a project\nreslib add ~\u002Fprojects\u002Farduino\u002Fservo.py --project arduino --material-type reference\n\n# Search\nreslib search \"servo tuning\"\n\n# Link knowledge\nreslib link 5 12 --type applies_to\n```\n\n## Features\n\n### CLI Commands\n- `reslib add` — Import documents (auto-detect + extract)\n- `reslib search` — Full-text search with filters\n- `reslib get` — View document details\n- `reslib archive` \u002F `reslib unarchive` — Manage documents\n- `reslib export` — Export as JSON\u002FMarkdown\n- `reslib link` — Create document relationships\n- `reslib projects` — Manage projects\n- `reslib tags` — Manage tags\n- `reslib status` — System overview\n- `reslib backup` \u002F `reslib restore` — Snapshots\n- `reslib smoke_test.sh` — Quick validation\n\n### Technical\n- **Storage:** SQLite 3.45+ with FTS5 virtual table\n- **Extraction:** PDF (pdfplumber + OCR), images (EXIF + OCR), code (AST + regex)\n- **Confidence Scoring:** 0.0-1.0 based on quality + source\n- **Material Weighting:** Reference (1.0) vs Research (0.5)\n- **Project Isolation:** Scoped searches, no contamination\n- **Async Workers:** 2-4 configurable extraction workers\n- **Catalog Separation:** real_world vs openclaw projects\n- **Backup:** Daily snapshots, 30-day retention\n\n## Configuration\n\nCopy `reslib\u002Fconfig.json` and customize:\n\n```json\n{\n  \"db_path\": \"~\u002F.openclaw\u002Fresearch\u002Flibrary.db\",\n  \"num_workers\": 2,\n  \"worker_timeout_sec\": 300,\n  \"max_retries\": 3,\n  \"backup_retention_days\": 30,\n  \"backup_dir\": \"~\u002F.openclaw\u002Fresearch\u002Fbackups\",\n  \"file_size_limit_mb\": 200,\n  \"project_size_limit_gb\": 2\n}\n```\n\n## Integration with War Room\n\nUse RL1 protocol in war room DNA:\n\n```python\nfrom reslib import ResearchDatabase, ResearchSearch\n\ndb = ResearchDatabase()\nsearch = ResearchSearch(db)\n\n# Before researching, check existing knowledge\nprior = search.search(\"servo tuning\", project=\"rc-quadcopter\")\nif prior:\n    print(f\"Found {len(prior)} prior items\")\nelse:\n    # New research needed...\n    db.add_research(title=\"...\", content=\"...\", ...)\n```\n\n## Performance\n\nAll targets exceeded:\n\n| Operation | Target | Actual |\n|-----------|--------|--------|\n| PDF extraction | \u003C100ms | 20.6ms |\n| Search (50 docs) | \u003C100ms | 0.33ms |\n| Worker throughput | >6\u002Fsec | 414.69\u002Fsec |\n\n## Testing\n\n```bash\n# Run all tests\npytest tests\u002F\n\n# Quick smoke test\nbash reslib\u002Fsmoke_test.sh\n\n# Performance tests\npytest tests\u002Ftest_integration.py -v -k stress\n```\n\n## Known Limitations (Phase 2)\n\n- OCR quality varies on hand-drawn sketches\n- FTS5 designed for \u003C10K documents (PostgreSQL path for scale)\n- No automatic web research gathering (manual only)\n- Vector embeddings ready but inactive\n- CAD file parsing is metadata-only\n\n## Documentation\n\nSee `\u002Fdocs\u002F`:\n- `CLI-REFERENCE.md` — All commands + examples\n- `EXTRACTION-GUIDE.md` — How extraction works\n- `SEARCH-GUIDE.md` — Ranking + weighting\n- `WORKER-GUIDE.md` — Async queue details\n- `INTEGRATION.md` — War room RL1 protocol\n\n## Phase 2 Roadmap\n\n- Real-world PDF calibration\n- FTS5 scaling tests (10K docs)\n- Auto-detection (reference vs research)\n- Web research enrichment\n- Vector embeddings (semantic search)\n- PostgreSQL upgrade path\n\n## Building From Source\n\n```bash\ncd research-library\npip install -e .\npytest tests\u002F\npython -m reslib status\n```\n\n## Support\n\nIssues? See TECHNICAL-NOTES.md for troubleshooting.\n\n---\n\n*Production-ready MVP. 214 tests passing. 15K lines. Ready to use.*\n","# Research Library Skill\n\nA local-first multimedia research library for capturing, organizing, and searching hardware project knowledge.\n\n## What It Does\n\n- **Store documents** — Code, PDFs, CAD files, images, schematics\n- **Extract automatically** — Text from PDFs, EXIF from images, functions from code\n- **Search intelligently** — Full-text with material-type weighting (your work ranks higher than external research)\n- **Project isolation** — Arduino separate from CNC; no contamination\n- **Cross-reference** — Link knowledge: \"this servo tuning applies to that project\"\n- **Async extraction** — Searches never block while OCR runs\n- **Backup daily** — 30-day rolling snapshots\n\n## Installation\n\n```bash\nclawhub install research-library\n# OR\npip install \u002Fpath\u002Fto\u002Fresearch-library\n```\n\n## Quick Start\n\n```bash\n# Initialize database\nreslib status\n\n# Add a project\nreslib add ~\u002Fprojects\u002Farduino\u002Fservo.py --project arduino --material-type reference\n\n# Search\nreslib search \"servo tuning\"\n\n# Link knowledge\nreslib link 5 12 --type applies_to\n```\n\n## Features\n\n### CLI Commands\n- `reslib add` — Import documents (auto-detect + extract)\n- `reslib search` — Full-text search with filters\n- `reslib get` — View document details\n- `reslib archive` \u002F `reslib unarchive` — Manage documents\n- `reslib export` — Export as JSON\u002FMarkdown\n- `reslib link` — Create document relationships\n- `reslib projects` — Manage projects\n- `reslib tags` — Manage tags\n- `reslib status` — System overview\n- `reslib backup` \u002F `reslib restore` — Snapshots\n- `reslib smoke_test.sh` — Quick validation\n\n### Technical\n- **Storage:** SQLite 3.45+ with FTS5 virtual table\n- **Extraction:** PDF (pdfplumber + OCR), images (EXIF + OCR), code (AST + regex)\n- **Confidence Scoring:** 0.0-1.0 based on quality + source\n- **Material Weighting:** Reference (1.0) vs Research (0.5)\n- **Project Isolation:** Scoped searches, no contamination\n- **Async Workers:** 2-4 configurable extraction workers\n- **Catalog Separation:** real_world vs openclaw projects\n- **Backup:** Daily snapshots, 30-day retention\n\n## Configuration\n\nCopy `reslib\u002Fconfig.json` and customize:\n\n```json\n{\n  \"db_path\": \"~\u002F.openclaw\u002Fresearch\u002Flibrary.db\",\n  \"num_workers\": 2,\n  \"worker_timeout_sec\": 300,\n  \"max_retries\": 3,\n  \"backup_retention_days\": 30,\n  \"backup_dir\": \"~\u002F.openclaw\u002Fresearch\u002Fbackups\",\n  \"file_size_limit_mb\": 200,\n  \"project_size_limit_gb\": 2\n}\n```\n\n## Integration with War Room\n\nUse RL1 protocol in war room DNA:\n\n```python\nfrom reslib import ResearchDatabase, ResearchSearch\n\ndb = ResearchDatabase()\nsearch = ResearchSearch(db)\n\n# Before researching, check existing knowledge\nprior = search.search(\"servo tuning\", project=\"rc-quadcopter\")\nif prior:\n    print(f\"Found {len(prior)} prior items\")\nelse:\n    # New research needed...\n    db.add_research(title=\"...\", content=\"...\", ...)\n```\n\n## Performance\n\nAll targets exceeded:\n\n| Operation | Target | Actual |\n|-----------|--------|--------|\n| PDF extraction | \u003C100ms | 20.6ms |\n| Search (50 docs) | \u003C100ms | 0.33ms |\n| Worker throughput | >6\u002Fsec | 414.69\u002Fsec |\n\n## Testing\n\n```bash\n# Run all tests\npytest tests\u002F\n\n# Quick smoke test\nbash reslib\u002Fsmoke_test.sh\n\n# Performance tests\npytest tests\u002Ftest_integration.py -v -k stress\n```\n\n## Known Limitations (Phase 2)\n\n- OCR quality varies on hand-drawn sketches\n- FTS5 designed for \u003C10K documents (PostgreSQL path for scale)\n- No automatic web research gathering (manual only)\n- Vector embeddings ready but inactive\n- CAD file parsing is metadata-only\n\n## Documentation\n\nSee `\u002Fdocs\u002F`:\n- `CLI-REFERENCE.md` — All commands + examples\n- `EXTRACTION-GUIDE.md` — How extraction works\n- `SEARCH-GUIDE.md` — Ranking + weighting\n- `WORKER-GUIDE.md` — Async queue details\n- `INTEGRATION.md` — War room RL1 protocol\n\n## Phase 2 Roadmap\n\n- Real-world PDF calibration\n- FTS5 scaling tests (10K docs)\n- Auto-detection (reference vs research)\n- Web research enrichment\n- Vector embeddings (semantic search)\n- PostgreSQL upgrade path\n\n## Building From Source\n\n```bash\ncd research-library\npip install -e .\npytest tests\u002F\npython -m reslib status\n```\n\n## Support\n\nIssues? See TECHNICAL-NOTES.md for troubleshooting.\n\n---\n\n*Production-ready MVP. 214 tests passing. 15K lines. Ready to use.*\n",{"name":5,"tags":24,"author":31,"license":15,"version":32,"keywords":33,"repository":39,"description":7},[25,26,27,28,29,30],"knowledge-management","research","hardware","documentation","sqlite","fts5","Sage (for Jon Buckles)","0.1.0",[34,35,36,37,38],"library","search","extraction","project-management","knowledge-base","https:\u002F\u002Fgithub.com\u002F[user]\u002Fresearch-library","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fjonbuckles\u002Fresearch-library",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill research-library",{"tool":55,"command":56},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill research-library",{"tool":58,"command":59},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill research-library","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjonbuckles\u002Fresearch-library\u002FSKILL.md",true,[],[64,72,79,86,93,100],{"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":70,"publishedAt":71},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":78,"publishedAt":71},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":71},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":71},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"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":71},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":71},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]