[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6N1DPTT3M4BN90A4HAPFP82":3,"skill-same:01M6N1DPTT3M4BN90A4HAPFP82":80},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":28,"updatedAt":29,"install":30,"resources":43},"01M6N1DPTT3M4BN90A4HAPFP82","ouyang",null,"Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002FSKILL.md",[],[5],"2026-11-10 10:12:30",false,"---\nname: jasper-recall\ndescription: Local RAG system for agent memory using ChromaDB and sentence-transformers. Provides semantic search over session logs, daily notes, and memory files. Use when you need persistent memory across sessions, want to search past conversations, or build agents that remember context. Commands: recall \"query\", index-digests, digest-sessions.\n---\n\n# Jasper Recall\n\nLocal RAG (Retrieval-Augmented Generation) system for AI agent memory. Gives your agent the ability to remember and search past conversations.\n\n## When to Use\n\n- **Memory recall**: Search past sessions for context before answering\n- **Continuous learning**: Index daily notes and decisions for future reference\n- **Session continuity**: Remember what happened across restarts\n- **Knowledge base**: Build searchable documentation from your agent's experience\n\n## Quick Start\n\n### Setup\n\nOne command installs everything:\n\n```bash\nnpx jasper-recall setup\n```\n\nThis creates:\n- Python venv at `~\u002F.openclaw\u002Frag-env`\n- ChromaDB database at `~\u002F.openclaw\u002Fchroma-db`\n- CLI scripts in `~\u002F.local\u002Fbin\u002F`\n\n### Basic Usage\n\n**Search your memory:**\n```bash\nrecall \"what did we decide about the API design\"\nrecall \"hopeIDS patterns\" --limit 10\nrecall \"meeting notes\" --json\n```\n\n**Index your files:**\n```bash\nindex-digests  # Index memory files into ChromaDB\n```\n\n**Create session digests:**\n```bash\ndigest-sessions          # Process new sessions\ndigest-sessions --dry-run  # Preview what would be processed\n```\n\n## How It Works\n\n### Three Components\n\n1. **digest-sessions** — Extracts key info from session logs (topics, tools used)\n2. **index-digests** — Chunks and embeds markdown files into ChromaDB\n3. **recall** — Semantic search across your indexed memory\n\n### What Gets Indexed\n\nBy default, indexes files from `~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002F`:\n\n- `*.md` — Daily notes, MEMORY.md\n- `session-digests\u002F*.md` — Session summaries\n- `repos\u002F*.md` — Project documentation\n- `founder-logs\u002F*.md` — Development logs (if present)\n\n### Embedding Model\n\nUses `sentence-transformers\u002Fall-MiniLM-L6-v2`:\n- 384-dimensional embeddings\n- ~80MB download on first run\n- Runs locally, no API needed\n\n## Agent Integration\n\n### Memory-Augmented Responses\n\n```python\n# Before answering questions about past work\nresults = exec(\"recall 'project setup decisions' --json\")\n# Include relevant context in your response\n```\n\n### Automated Indexing (Heartbeat)\n\nAdd to HEARTBEAT.md:\n```markdown\n## Memory Maintenance\n- [ ] New session logs? → `digest-sessions`\n- [ ] Memory files updated? → `index-digests`\n```\n\n### Cron Job\n\nSchedule regular indexing:\n```json\n{\n  \"schedule\": { \"kind\": \"cron\", \"expr\": \"0 *\u002F6 * * *\" },\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Run index-digests to update the memory index\"\n  },\n  \"sessionTarget\": \"isolated\"\n}\n```\n\n## CLI Reference\n\n### recall\n\n```\nrecall \"query\" [OPTIONS]\n\nOptions:\n  -n, --limit N     Number of results (default: 5)\n  --json            Output as JSON\n  -v, --verbose     Show similarity scores\n```\n\n### index-digests\n\n```\nindex-digests\n\nIndexes markdown files from:\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Fsession-digests\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Frepos\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Ffounder-logs\u002F*.md\n\nSkips files that haven't changed (content hash check).\n```\n\n### digest-sessions\n\n```\ndigest-sessions [OPTIONS]\n\nOptions:\n  --dry-run    Preview without writing\n  --all        Process all sessions (not just new)\n  --recent N   Process only N most recent sessions\n```\n\n## Configuration\n\n### Custom Paths\n\nSet environment variables:\n\n```bash\nexport RECALL_WORKSPACE=~\u002F.openclaw\u002Fworkspace\nexport RECALL_CHROMA_DB=~\u002F.openclaw\u002Fchroma-db\nexport RECALL_SESSIONS_DIR=~\u002F.openclaw\u002Fagents\u002Fmain\u002Fsessions\n```\n\n### Chunking\n\nDefault settings in index-digests:\n- Chunk size: 500 characters\n- Overlap: 100 characters\n\n## Troubleshooting\n\n**\"No index found\"**\n```bash\nindex-digests  # Create the index first\n```\n\n**\"Collection not found\"**\n```bash\nrm -rf ~\u002F.openclaw\u002Fchroma-db  # Clear and rebuild\nindex-digests\n```\n\n**Model download slow**\nFirst run downloads ~80MB model. Subsequent runs are instant.\n\n## Links\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FE-x-O-Entertainment-Studios-Inc\u002Fjasper-recall\n- **npm**: https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fjasper-recall\n- **ClawHub**: https:\u002F\u002Fclawhub.ai\u002Fskills\u002Fjasper-recall\n","# Jasper Recall\n\nLocal RAG (Retrieval-Augmented Generation) system for AI agent memory. Gives your agent the ability to remember and search past conversations.\n\n## When to Use\n\n- **Memory recall**: Search past sessions for context before answering\n- **Continuous learning**: Index daily notes and decisions for future reference\n- **Session continuity**: Remember what happened across restarts\n- **Knowledge base**: Build searchable documentation from your agent's experience\n\n## Quick Start\n\n### Setup\n\nOne command installs everything:\n\n```bash\nnpx jasper-recall setup\n```\n\nThis creates:\n- Python venv at `~\u002F.openclaw\u002Frag-env`\n- ChromaDB database at `~\u002F.openclaw\u002Fchroma-db`\n- CLI scripts in `~\u002F.local\u002Fbin\u002F`\n\n### Basic Usage\n\n**Search your memory:**\n```bash\nrecall \"what did we decide about the API design\"\nrecall \"hopeIDS patterns\" --limit 10\nrecall \"meeting notes\" --json\n```\n\n**Index your files:**\n```bash\nindex-digests  # Index memory files into ChromaDB\n```\n\n**Create session digests:**\n```bash\ndigest-sessions          # Process new sessions\ndigest-sessions --dry-run  # Preview what would be processed\n```\n\n## How It Works\n\n### Three Components\n\n1. **digest-sessions** — Extracts key info from session logs (topics, tools used)\n2. **index-digests** — Chunks and embeds markdown files into ChromaDB\n3. **recall** — Semantic search across your indexed memory\n\n### What Gets Indexed\n\nBy default, indexes files from `~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002F`:\n\n- `*.md` — Daily notes, MEMORY.md\n- `session-digests\u002F*.md` — Session summaries\n- `repos\u002F*.md` — Project documentation\n- `founder-logs\u002F*.md` — Development logs (if present)\n\n### Embedding Model\n\nUses `sentence-transformers\u002Fall-MiniLM-L6-v2`:\n- 384-dimensional embeddings\n- ~80MB download on first run\n- Runs locally, no API needed\n\n## Agent Integration\n\n### Memory-Augmented Responses\n\n```python\n# Before answering questions about past work\nresults = exec(\"recall 'project setup decisions' --json\")\n# Include relevant context in your response\n```\n\n### Automated Indexing (Heartbeat)\n\nAdd to HEARTBEAT.md:\n```markdown\n## Memory Maintenance\n- [ ] New session logs? → `digest-sessions`\n- [ ] Memory files updated? → `index-digests`\n```\n\n### Cron Job\n\nSchedule regular indexing:\n```json\n{\n  \"schedule\": { \"kind\": \"cron\", \"expr\": \"0 *\u002F6 * * *\" },\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Run index-digests to update the memory index\"\n  },\n  \"sessionTarget\": \"isolated\"\n}\n```\n\n## CLI Reference\n\n### recall\n\n```\nrecall \"query\" [OPTIONS]\n\nOptions:\n  -n, --limit N     Number of results (default: 5)\n  --json            Output as JSON\n  -v, --verbose     Show similarity scores\n```\n\n### index-digests\n\n```\nindex-digests\n\nIndexes markdown files from:\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Fsession-digests\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Frepos\u002F*.md\n  ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Ffounder-logs\u002F*.md\n\nSkips files that haven't changed (content hash check).\n```\n\n### digest-sessions\n\n```\ndigest-sessions [OPTIONS]\n\nOptions:\n  --dry-run    Preview without writing\n  --all        Process all sessions (not just new)\n  --recent N   Process only N most recent sessions\n```\n\n## Configuration\n\n### Custom Paths\n\nSet environment variables:\n\n```bash\nexport RECALL_WORKSPACE=~\u002F.openclaw\u002Fworkspace\nexport RECALL_CHROMA_DB=~\u002F.openclaw\u002Fchroma-db\nexport RECALL_SESSIONS_DIR=~\u002F.openclaw\u002Fagents\u002Fmain\u002Fsessions\n```\n\n### Chunking\n\nDefault settings in index-digests:\n- Chunk size: 500 characters\n- Overlap: 100 characters\n\n## Troubleshooting\n\n**\"No index found\"**\n```bash\nindex-digests  # Create the index first\n```\n\n**\"Collection not found\"**\n```bash\nrm -rf ~\u002F.openclaw\u002Fchroma-db  # Clear and rebuild\nindex-digests\n```\n\n**Model download slow**\nFirst run downloads ~80MB model. Subsequent runs are instant.\n\n## Links\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FE-x-O-Entertainment-Studios-Inc\u002Fjasper-recall\n- **npm**: https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fjasper-recall\n- **ClawHub**: https:\u002F\u002Fclawhub.ai\u002Fskills\u002Fjasper-recall\n",{},"main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","人工智能与大型语言模型\u002Fouyang",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":7,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill ouyang",{"tool":36,"command":37},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill ouyang",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill ouyang","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002FSKILL.md",true,[44,50,56,60,64,68,72,76],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"_meta.json","REFERENCE","参考文档",263,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002F_meta.json",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"cli\u002Fjasper-recall.js","SCRIPT","脚本",5544,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fcli\u002Fjasper-recall.js",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"package.json",957,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fpackage.json",{"path":61,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":62,"sourceHtmlUrl":63},"README.md",4413,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002FREADME.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fdigest-sessions.sh",3872,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fscripts\u002Fdigest-sessions.sh",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Findex-digests.py",6026,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fscripts\u002Findex-digests.py",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Frecall.py",3566,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fscripts\u002Frecall.py",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"src\u002Findex.js",1707,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fouyang\u002Fsrc\u002Findex.js",[81,105,141,152,162,192],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":17},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[83,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":106,"name":107,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":123,"publishedAt":17},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[110,115,118],{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":116,"categoryName":117,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[124,125,126,127,128,129,130,90,131,94,132,133,134,135,136,137,138,139,140],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":142,"name":143,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":149,"publishedAt":17},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[146,147,148],{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},{"categoryNo":116,"categoryName":117,"taxonomyType":113,"taxonomyTypeDesc":114},{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[124,150,151,125,126,127,128,129,130,90,131,94,133,134,135,136,137,138,139,140],"api skill","zerion api skill",{"skillNo":153,"name":154,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":17},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[157,158,159],{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},{"categoryNo":116,"categoryName":117,"taxonomyType":113,"taxonomyTypeDesc":114},{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[127,124,161,125,126,128,129,90,131,94,132,133,134,135,136,137,138,139,140],"zerion api mcp",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":17},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000040","财务",[172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data","for",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":199,"publishedAt":17},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[198],{"categoryNo":169,"categoryName":170,"taxonomyType":121,"taxonomyTypeDesc":122},[172,173,175,200,201,202,203,204,205,183,206,207,208,209,210,211,212,213,140,190],"cli","homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]