[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K49PRPCC65WQGQGG455Z8":3,"skill-same:01M75K49PRPCC65WQGQGG455Z8":74},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M75K49PRPCC65WQGQGG455Z8","rag-eval",null,"Evaluate your RAG pipeline quality using Ragas metrics (faithfulness, answer relevancy, context precision).","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\u002Fjonathanjing\u002Frag-eval\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: rag-eval\ndescription: \"Evaluate your RAG pipeline quality using Ragas metrics (faithfulness, answer relevancy, context precision).\"\nversion: \"1.2.1\"\nmetadata:\n  {\n    \"openclaw\": {\n      \"emoji\": \"🧪\",\n      \"requires\": {\n        \"anyBins\": [\"python3\", \"pip\"],\n        \"anyEnv\": [\"OPENAI_API_KEY\", \"ANTHROPIC_API_KEY\", \"RAGAS_LLM\"]\n      },\n      \"envVars\": {\n        \"OPENAI_API_KEY\": { \"description\": \"OpenAI API key (default LLM judge)\", \"required\": false },\n        \"ANTHROPIC_API_KEY\": { \"description\": \"Anthropic API key (alternative LLM judge)\", \"required\": false },\n        \"RAGAS_LLM\": { \"description\": \"Custom LLM endpoint for judge (e.g. ollama\u002Fllama3 for local)\", \"required\": false },\n        \"RAGAS_PASS_THRESHOLD\": { \"description\": \"Score threshold for PASS verdict (default: 0.85)\", \"required\": false },\n        \"RAGAS_REVIEW_THRESHOLD\": { \"description\": \"Score threshold for REVIEW verdict (default: 0.70)\", \"required\": false },\n        \"RAGAS_OPENAI_MODEL\": { \"description\": \"OpenAI model for judge (default: gpt-4o)\", \"required\": false },\n        \"RAGAS_ANTHROPIC_MODEL\": { \"description\": \"Anthropic model for judge (default: claude-haiku-4-5)\", \"required\": false }\n      }\n    }\n  }\n---\n\n# RAG Eval — Quality Testing for Your RAG Pipeline\n\nTest and monitor your RAG pipeline's output quality.\n\n## 🛠️ Installation\n\n### 1. Ask OpenClaw (Recommended)\nTell OpenClaw: *\"Install the rag-eval skill.\"* The agent will handle the installation and configuration automatically.\n\n### 2. Manual Installation (CLI)\nIf you prefer the terminal, run:\n```bash\nclawhub install rag-eval\n```\n\n## ⚠️ Prerequisites\n1. Your OpenClaw must have a **RAG system** (vector DB + retrieval pipeline). This skill evaluates the *output quality* of that pipeline — it does not provide RAG functionality itself.\n2. **At least one LLM API key** is required — Ragas uses an LLM as judge internally. Set one of:\n   - `OPENAI_API_KEY` (default, uses GPT-4o)\n   - `ANTHROPIC_API_KEY` (uses Claude Haiku)\n   - `RAGAS_LLM=ollama\u002Fllama3` (for local\u002Foffline evaluation)\n\n## Setup (first run only)\n\n```bash\nbash scripts\u002Fsetup.sh\n```\n\nThis installs `ragas`, `datasets`, and other dependencies.\n\n## Single Response Evaluation\n\nWhen user asks to evaluate an answer, collect:\n1. **question** — the original user question\n2. **answer** — the LLM output to evaluate\n3. **contexts** — list of text chunks used to generate the answer (retrieved docs)\n\n**⚠️ SECURITY: Never interpolate user content directly into shell commands.**\nWrite the input to a temp JSON file first, then pipe it to the evaluator:\n\n```bash\n# Step 1: Write input to a temp file (agent should use the write\u002Fedit tool, NOT echo)\n# Write this JSON to \u002Ftmp\u002Frag-eval-input.json using the file write tool:\n# {\"question\": \"...\", \"answer\": \"...\", \"contexts\": [\"chunk1\", \"chunk2\"]}\n\n# Step 2: Pipe the file to the evaluator\npython3 scripts\u002Frun_eval.py \u003C \u002Ftmp\u002Frag-eval-input.json\n\n# Step 3: Clean up\nrm -f \u002Ftmp\u002Frag-eval-input.json\n```\n\nAlternatively, use `--input-file`:\n```bash\npython3 scripts\u002Frun_eval.py --input-file \u002Ftmp\u002Frag-eval-input.json\n```\n\nOutput JSON:\n```json\n{\n  \"faithfulness\": 0.92,\n  \"answer_relevancy\": 0.87,\n  \"context_precision\": 0.79,\n  \"overall_score\": 0.86,\n  \"verdict\": \"PASS\",\n  \"flags\": []\n}\n```\n\nPost results to user with human-readable summary:\n```\n🧪 Eval Results\n• Faithfulness: 0.92 ✅ (no hallucination detected)\n• Answer Relevancy: 0.87 ✅\n• Context Precision: 0.79 ⚠️ (some irrelevant context retrieved)\n• Overall: 0.86 — PASS\n```\n\nSave to `memory\u002Feval-results\u002FYYYY-MM-DD.jsonl`.\n\n## Batch Evaluation\n\nFor a JSONL dataset file (each line: `{\"question\":..., \"answer\":..., \"contexts\":[...]}`):\n\n```bash\npython3 scripts\u002Fbatch_eval.py --input references\u002Fsample_dataset.jsonl --output memory\u002Feval-results\u002Fbatch-YYYY-MM-DD.json\n```\n\n## Score Interpretation\n\n| Score | Verdict | Meaning |\n|-------|---------|---------|\n| 0.85+ | ✅ PASS | Production-ready quality |\n| 0.70-0.84 | ⚠️ REVIEW | Needs improvement |\n| \u003C 0.70 | ❌ FAIL | Significant quality issues |\n\n## Faithfulness Deep-Dive\n\nIf faithfulness \u003C 0.80, run:\n```bash\npython3 scripts\u002Frun_eval.py --explain --metric faithfulness\n```\nThis outputs which sentences in the answer are NOT supported by context.\n\n## Notes\n- Ragas uses an LLM internally as judge (uses your configured OpenAI\u002FAnthropic key)\n- Evaluation costs ~$0.01-0.05 per response depending on length\n- For offline use, set `RAGAS_LLM=ollama\u002Fllama3` in environment\n","# RAG Eval — Quality Testing for Your RAG Pipeline\n\nTest and monitor your RAG pipeline's output quality.\n\n## 🛠️ Installation\n\n### 1. Ask OpenClaw (Recommended)\nTell OpenClaw: *\"Install the rag-eval skill.\"* The agent will handle the installation and configuration automatically.\n\n### 2. Manual Installation (CLI)\nIf you prefer the terminal, run:\n```bash\nclawhub install rag-eval\n```\n\n## ⚠️ Prerequisites\n1. Your OpenClaw must have a **RAG system** (vector DB + retrieval pipeline). This skill evaluates the *output quality* of that pipeline — it does not provide RAG functionality itself.\n2. **At least one LLM API key** is required — Ragas uses an LLM as judge internally. Set one of:\n   - `OPENAI_API_KEY` (default, uses GPT-4o)\n   - `ANTHROPIC_API_KEY` (uses Claude Haiku)\n   - `RAGAS_LLM=ollama\u002Fllama3` (for local\u002Foffline evaluation)\n\n## Setup (first run only)\n\n```bash\nbash scripts\u002Fsetup.sh\n```\n\nThis installs `ragas`, `datasets`, and other dependencies.\n\n## Single Response Evaluation\n\nWhen user asks to evaluate an answer, collect:\n1. **question** — the original user question\n2. **answer** — the LLM output to evaluate\n3. **contexts** — list of text chunks used to generate the answer (retrieved docs)\n\n**⚠️ SECURITY: Never interpolate user content directly into shell commands.**\nWrite the input to a temp JSON file first, then pipe it to the evaluator:\n\n```bash\n# Step 1: Write input to a temp file (agent should use the write\u002Fedit tool, NOT echo)\n# Write this JSON to \u002Ftmp\u002Frag-eval-input.json using the file write tool:\n# {\"question\": \"...\", \"answer\": \"...\", \"contexts\": [\"chunk1\", \"chunk2\"]}\n\n# Step 2: Pipe the file to the evaluator\npython3 scripts\u002Frun_eval.py \u003C \u002Ftmp\u002Frag-eval-input.json\n\n# Step 3: Clean up\nrm -f \u002Ftmp\u002Frag-eval-input.json\n```\n\nAlternatively, use `--input-file`:\n```bash\npython3 scripts\u002Frun_eval.py --input-file \u002Ftmp\u002Frag-eval-input.json\n```\n\nOutput JSON:\n```json\n{\n  \"faithfulness\": 0.92,\n  \"answer_relevancy\": 0.87,\n  \"context_precision\": 0.79,\n  \"overall_score\": 0.86,\n  \"verdict\": \"PASS\",\n  \"flags\": []\n}\n```\n\nPost results to user with human-readable summary:\n```\n🧪 Eval Results\n• Faithfulness: 0.92 ✅ (no hallucination detected)\n• Answer Relevancy: 0.87 ✅\n• Context Precision: 0.79 ⚠️ (some irrelevant context retrieved)\n• Overall: 0.86 — PASS\n```\n\nSave to `memory\u002Feval-results\u002FYYYY-MM-DD.jsonl`.\n\n## Batch Evaluation\n\nFor a JSONL dataset file (each line: `{\"question\":..., \"answer\":..., \"contexts\":[...]}`):\n\n```bash\npython3 scripts\u002Fbatch_eval.py --input references\u002Fsample_dataset.jsonl --output memory\u002Feval-results\u002Fbatch-YYYY-MM-DD.json\n```\n\n## Score Interpretation\n\n| Score | Verdict | Meaning |\n|-------|---------|---------|\n| 0.85+ | ✅ PASS | Production-ready quality |\n| 0.70-0.84 | ⚠️ REVIEW | Needs improvement |\n| \u003C 0.70 | ❌ FAIL | Significant quality issues |\n\n## Faithfulness Deep-Dive\n\nIf faithfulness \u003C 0.80, run:\n```bash\npython3 scripts\u002Frun_eval.py --explain --metric faithfulness\n```\nThis outputs which sentences in the answer are NOT supported by context.\n\n## Notes\n- Ragas uses an LLM internally as judge (uses your configured OpenAI\u002FAnthropic key)\n- Evaluation costs ~$0.01-0.05 per response depending on length\n- For offline use, set `RAGAS_LLM=ollama\u002Fllama3` in environment\n",{"name":5,"version":24,"metadata":25,"description":7},"1.2.1",{"openclaw":26},{"emoji":27,"envVars":28,"requires":43},"🧪",{"RAGAS_LLM":29,"OPENAI_API_KEY":31,"ANTHROPIC_API_KEY":33,"RAGAS_OPENAI_MODEL":35,"RAGAS_PASS_THRESHOLD":37,"RAGAS_ANTHROPIC_MODEL":39,"RAGAS_REVIEW_THRESHOLD":41},{"required":20,"description":30},"Custom LLM endpoint for judge (e.g. ollama\u002Fllama3 for local)",{"required":20,"description":32},"OpenAI API key (default LLM judge)",{"required":20,"description":34},"Anthropic API key (alternative LLM judge)",{"required":20,"description":36},"OpenAI model for judge (default: gpt-4o)",{"required":20,"description":38},"Score threshold for PASS verdict (default: 0.85)",{"required":20,"description":40},"Anthropic model for judge (default: claude-haiku-4-5)",{"required":20,"description":42},"Score threshold for REVIEW verdict (default: 0.70)",{"anyEnv":44,"anyBins":48},[45,46,47],"OPENAI_API_KEY","ANTHROPIC_API_KEY","RAGAS_LLM",[49,50],"python3","pip","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fjonathanjing\u002Frag-eval",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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill rag-eval",{"tool":66,"command":67},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill rag-eval",{"tool":69,"command":70},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill rag-eval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjonathanjing\u002Frag-eval\u002FSKILL.md",true,[],[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":82},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":82},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":82},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":82},"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":82},"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",[],[]]