[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C55Y9WBZJHZPMYPC2TRSFE":3,"skill-same:01M6C55Y9WBZJHZPMYPC2TRSFE":102},{"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":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6C55Y9WBZJHZPMYPC2TRSFE","clawsec-clawhub-checker",null,"ClawHub reputation checker for ClawSec suite. Enhances guarded skill installer with VirusTotal Code Insight reputation scores and additional safety checks.","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"clawhub","clawsec clawhub checker","security","skill installer","code","https","VirusTotal","Safety","curl","jq","prompt","reputation","2026-11-10 10:12:30",false,"---\nname: clawsec-clawhub-checker\nversion: 0.0.1\ndescription: ClawHub reputation checker for ClawSec suite. Enhances guarded skill installer with VirusTotal Code Insight reputation scores and additional safety checks.\nhomepage: https:\u002F\u002Fclawsec.prompt.security\nclawdis:\n  emoji: \"?️\"\n  requires:\n    bins: [clawhub, curl, jq]\n  depends_on: [clawsec-suite]\n---\n\n# ClawSec ClawHub Checker\n\nEnhances the ClawSec suite's guarded skill installer with ClawHub reputation checks. Adds a second layer of security by checking VirusTotal Code Insight scores and other reputation signals before allowing skill installation.\n\n## What It Does\n\n1. **Wraps `clawhub install`** - Intercepts skill installation requests\n2. **Checks VirusTotal reputation** - Uses ClawHub's built-in VirusTotal Code Insight\n3. **Adds double confirmation** - For suspicious skills (reputation score below threshold)\n4. **Integrates with advisory feed** - Works alongside existing clawsec-suite advisories\n5. **Provides detailed reports** - Shows why a skill is flagged as suspicious\n\n## Installation\n\nThis skill must be installed **after** `clawsec-suite`:\n\n```bash\n# First install the suite\nnpx clawhub@latest install clawsec-suite\n\n# Then install the checker\nnpx clawhub@latest install clawsec-clawhub-checker\n\n# Run the setup script to integrate with clawsec-suite\nnode ~\u002F.openclaw\u002Fskills\u002Fclawsec-clawhub-checker\u002Fscripts\u002Fsetup_reputation_hook.mjs\n\n# Restart OpenClaw gateway for changes to take effect\nopenclaw gateway restart\n```\n\nAfter setup, the checker adds `enhanced_guarded_install.mjs` and\n`guarded_skill_install_wrapper.mjs` under `clawsec-suite\u002Fscripts` and updates the advisory\nguardian hook. The original `guarded_skill_install.mjs` is not replaced.\n\n## How It Works\n\n### Enhanced Guarded Installer\n\nAfter setup, run the wrapper (drop-in path) or the enhanced script directly:\n```bash\n# Recommended drop-in wrapper\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill some-skill --version 1.0.0\n\n# Or call the enhanced script directly\nnode scripts\u002Fenhanced_guarded_install.mjs --skill some-skill --version 1.0.0\n```\n\nThe enhanced flow:\n1. **Advisory check** (existing) - Checks clawsec advisory feed\n2. **Reputation check** (new) - Queries ClawHub for VirusTotal scores\n3. **Risk assessment** - Combines advisory + reputation signals\n4. **Double confirmation** - If risky, requires explicit `--confirm-reputation`\n\n### Reputation Signals Checked\n\n1. **VirusTotal Code Insight** - Malicious code patterns, external dependencies (Docker usage, network calls, eval usage, crypto keys)\n2. **Skill age & updates** - New skills vs established ones\n3. **Author reputation** - Other skills by same author\n4. **Download statistics** - Popularity signals\n\n### Exit Codes\n\n- `0` - Safe to install (no advisories, good reputation)\n- `42` - Advisory match found (existing behavior)\n- `43` - Reputation warning (new - requires `--confirm-reputation`)\n- `1` - Error\n\n## Configuration\n\nEnvironment variables:\n- `CLAWHUB_REPUTATION_THRESHOLD` - Minimum reputation score (0-100, default: 70)\n\n## Integration with Existing Suite\n\nThe checker enhances but doesn't replace existing security:\n- **Advisory feed still primary** - Known malicious skills blocked first\n- **Reputation is secondary** - Unknown\u002Fsuspicious skills get extra scrutiny\n- **Double confirmation preserved** - Both layers require explicit user approval\n\n## Example Usage\n\n```bash\n# Try to install a skill\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0\n\n# Output might show:\n# WARNING: Skill \"suspicious-skill\" has low reputation score (45\u002F100)\n# - Flagged by VirusTotal Code Insight: crypto keys, external APIs, eval usage\n# - Author has no other published skills\n# - Skill is less than 7 days old\n# \n# To install despite reputation warning, run:\n# node scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0 --confirm-reputation\n\n# Install with confirmation\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0 --confirm-reputation\n```\n\n## Safety Notes\n\n- This is a **defense-in-depth** layer, not a replacement for advisory feeds\n- VirusTotal scores are **heuristic**, not definitive\n- **False positives possible** - Legitimate skills with novel patterns might be flagged\n- Always **review skill code** before installing with `--confirm-reputation`\n\n## Current Limitations\n\n### Missing OpenClaw Internal Check Data\nClawHub shows two security badges on skill pages:\n1. **VirusTotal Code Insight** - ✅ Our checker catches these flags\n2. **OpenClaw internal check** - ❌ Not exposed via API (only on website)\n\nExample from `clawsec-suite` page:\n- VirusTotal: \"Benign\" ✓\n- OpenClaw internal check: \"The package is internally consistent with a feed-monitoring \u002F advisory-guardian purpose, but a few operational details and optional bypasses deserve attention before installing.\"\n\n**Our checker cannot access OpenClaw internal check warnings** as they're not exposed via `clawhub` CLI or API.\n\n### Recommendation for ClawHub\nTo enable complete reputation checking, ClawHub should expose internal check results via:\n- `clawhub inspect --json` endpoint\n- Additional API field for security tools\n- Or include in `clawhub install` warning output\n\n### Workaround\nOur heuristic checks (skill age, author reputation, downloads, updates) provide similar risk assessment but miss specific operational warnings about bypasses, missing signatures, etc. Always check the ClawHub website for complete security assessment.\n\n## Development\n\nTo modify the reputation checking logic, edit:\n- `scripts\u002Fenhanced_guarded_install.mjs` - Main enhanced installer\n- `scripts\u002Fcheck_clawhub_reputation.mjs` - Reputation checking logic\n- `hooks\u002Fclawsec-advisory-guardian\u002Flib\u002Freputation.mjs` - Hook integration\n\n## License\n\nGNU AGPL v3.0 or later - Part of the ClawSec security suite\n","# ClawSec ClawHub Checker\n\nEnhances the ClawSec suite's guarded skill installer with ClawHub reputation checks. Adds a second layer of security by checking VirusTotal Code Insight scores and other reputation signals before allowing skill installation.\n\n## What It Does\n\n1. **Wraps `clawhub install`** - Intercepts skill installation requests\n2. **Checks VirusTotal reputation** - Uses ClawHub's built-in VirusTotal Code Insight\n3. **Adds double confirmation** - For suspicious skills (reputation score below threshold)\n4. **Integrates with advisory feed** - Works alongside existing clawsec-suite advisories\n5. **Provides detailed reports** - Shows why a skill is flagged as suspicious\n\n## Installation\n\nThis skill must be installed **after** `clawsec-suite`:\n\n```bash\n# First install the suite\nnpx clawhub@latest install clawsec-suite\n\n# Then install the checker\nnpx clawhub@latest install clawsec-clawhub-checker\n\n# Run the setup script to integrate with clawsec-suite\nnode ~\u002F.openclaw\u002Fskills\u002Fclawsec-clawhub-checker\u002Fscripts\u002Fsetup_reputation_hook.mjs\n\n# Restart OpenClaw gateway for changes to take effect\nopenclaw gateway restart\n```\n\nAfter setup, the checker adds `enhanced_guarded_install.mjs` and\n`guarded_skill_install_wrapper.mjs` under `clawsec-suite\u002Fscripts` and updates the advisory\nguardian hook. The original `guarded_skill_install.mjs` is not replaced.\n\n## How It Works\n\n### Enhanced Guarded Installer\n\nAfter setup, run the wrapper (drop-in path) or the enhanced script directly:\n```bash\n# Recommended drop-in wrapper\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill some-skill --version 1.0.0\n\n# Or call the enhanced script directly\nnode scripts\u002Fenhanced_guarded_install.mjs --skill some-skill --version 1.0.0\n```\n\nThe enhanced flow:\n1. **Advisory check** (existing) - Checks clawsec advisory feed\n2. **Reputation check** (new) - Queries ClawHub for VirusTotal scores\n3. **Risk assessment** - Combines advisory + reputation signals\n4. **Double confirmation** - If risky, requires explicit `--confirm-reputation`\n\n### Reputation Signals Checked\n\n1. **VirusTotal Code Insight** - Malicious code patterns, external dependencies (Docker usage, network calls, eval usage, crypto keys)\n2. **Skill age & updates** - New skills vs established ones\n3. **Author reputation** - Other skills by same author\n4. **Download statistics** - Popularity signals\n\n### Exit Codes\n\n- `0` - Safe to install (no advisories, good reputation)\n- `42` - Advisory match found (existing behavior)\n- `43` - Reputation warning (new - requires `--confirm-reputation`)\n- `1` - Error\n\n## Configuration\n\nEnvironment variables:\n- `CLAWHUB_REPUTATION_THRESHOLD` - Minimum reputation score (0-100, default: 70)\n\n## Integration with Existing Suite\n\nThe checker enhances but doesn't replace existing security:\n- **Advisory feed still primary** - Known malicious skills blocked first\n- **Reputation is secondary** - Unknown\u002Fsuspicious skills get extra scrutiny\n- **Double confirmation preserved** - Both layers require explicit user approval\n\n## Example Usage\n\n```bash\n# Try to install a skill\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0\n\n# Output might show:\n# WARNING: Skill \"suspicious-skill\" has low reputation score (45\u002F100)\n# - Flagged by VirusTotal Code Insight: crypto keys, external APIs, eval usage\n# - Author has no other published skills\n# - Skill is less than 7 days old\n# \n# To install despite reputation warning, run:\n# node scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0 --confirm-reputation\n\n# Install with confirmation\nnode scripts\u002Fguarded_skill_install_wrapper.mjs --skill suspicious-skill --version 1.0.0 --confirm-reputation\n```\n\n## Safety Notes\n\n- This is a **defense-in-depth** layer, not a replacement for advisory feeds\n- VirusTotal scores are **heuristic**, not definitive\n- **False positives possible** - Legitimate skills with novel patterns might be flagged\n- Always **review skill code** before installing with `--confirm-reputation`\n\n## Current Limitations\n\n### Missing OpenClaw Internal Check Data\nClawHub shows two security badges on skill pages:\n1. **VirusTotal Code Insight** - ✅ Our checker catches these flags\n2. **OpenClaw internal check** - ❌ Not exposed via API (only on website)\n\nExample from `clawsec-suite` page:\n- VirusTotal: \"Benign\" ✓\n- OpenClaw internal check: \"The package is internally consistent with a feed-monitoring \u002F advisory-guardian purpose, but a few operational details and optional bypasses deserve attention before installing.\"\n\n**Our checker cannot access OpenClaw internal check warnings** as they're not exposed via `clawhub` CLI or API.\n\n### Recommendation for ClawHub\nTo enable complete reputation checking, ClawHub should expose internal check results via:\n- `clawhub inspect --json` endpoint\n- Additional API field for security tools\n- Or include in `clawhub install` warning output\n\n### Workaround\nOur heuristic checks (skill age, author reputation, downloads, updates) provide similar risk assessment but miss specific operational warnings about bypasses, missing signatures, etc. Always check the ClawHub website for complete security assessment.\n\n## Development\n\nTo modify the reputation checking logic, edit:\n- `scripts\u002Fenhanced_guarded_install.mjs` - Main enhanced installer\n- `scripts\u002Fcheck_clawhub_reputation.mjs` - Reputation checking logic\n- `hooks\u002Fclawsec-advisory-guardian\u002Flib\u002Freputation.mjs` - Hook integration\n\n## License\n\nGNU AGPL v3.0 or later - Part of the ClawSec security suite\n",{"name":5,"clawdis":41,"version":47,"homepage":48,"description":7},{"emoji":42,"requires":43,"depends_on":45},"?️",{"bins":44},[24,32,33],[46],"clawsec-suite","0.0.1","https:\u002F\u002Fclawsec.prompt.security","main","1ca81b0a7de199942400f965edd4d7544077ac5d",".agents\u002Fskills\u002Fclawsec-clawhub-checker","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add CoralShades\u002Facm-ai --skill clawsec-clawhub-checker",{"tool":62,"command":63},"bunx","bunx skills add CoralShades\u002Facm-ai --skill clawsec-clawhub-checker",{"tool":65,"command":66},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill clawsec-clawhub-checker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002FSKILL.md",true,[70,76,82,86,90,94,98],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"hooks\u002Fclawsec-advisory-guardian\u002Flib\u002Freputation.mjs","SCRIPT","脚本",3129,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Fhooks\u002Fclawsec-advisory-guardian\u002Flib\u002Freputation.mjs",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"README.md","REFERENCE","参考文档",4050,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002FREADME.md",{"path":83,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fcheck_clawhub_reputation.mjs",8327,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Fscripts\u002Fcheck_clawhub_reputation.mjs",{"path":87,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fenhanced_guarded_install.mjs",7708,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Fscripts\u002Fenhanced_guarded_install.mjs",{"path":91,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Fsetup_reputation_hook.mjs",7091,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Fscripts\u002Fsetup_reputation_hook.mjs",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"skill.json",2464,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Fskill.json",{"path":99,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":100,"sourceHtmlUrl":101},"test\u002Freputation_check.test.mjs",15195,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawsec-clawhub-checker\u002Ftest\u002Freputation_check.test.mjs",[103,124,137,153,175,185],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":112,"publishedAt":36},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[105,113,114,115,116,117,28,118,119,120,121,122,123],"github","frontend","css","codex","react","linear","ui","vue","generated","use","html",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":36},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl","Runpod CLI to manage your GPU workloads.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[126,132,133,134,135,136],"macos","cli","linux","gpu","Bash",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":36},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152],"langgraph persistence","langgraph","persistence","travel","history","scoping","remember","state","configure",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":164,"publishedAt":36},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":162,"taxonomyTypeDesc":163},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[165,166,145,167,168,169,170,171,172,173,174],"langgraph human in the loop","loop","workflows","error handling","validation","human-in-the-loop","command","strategy","approval","resume",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":36},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[182,145,168,151,183,184,171,28],"langgraph fundamentals","streaming","writing",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":36},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[192,193,194,195,196,197,198,199,200,201],"rag","langchain rag","langchain","embeddings","vector","openai","chroma","faiss","vector stores","system"]