[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMYC8M66K4BASKTW574HAX":3,"skill-same:01M7AMYC8M66K4BASKTW574HAX":73},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AMYC8M66K4BASKTW574HAX","rag-architect",null,"Use when the user asks to design a RAG pipeline, choose a chunking strategy or embedding model, pick a vector database, or evaluate retrieval quality (precision@k, recall@k, NDCG). Examples: 'design a RAG system for our docs', 'what chunk size should I use for this corpus', 'evaluate my retriever against ground truth'. NOT for general LLM cost tuning (use llm-cost-optimizer) or agent loops over retrieval (use agenthub).","Cyrilthetecchieee\u002Fcyril-code-","Cyrilthetecchieee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219787998?v=4","01M7AF0MMMKRAA0H61XMJPV92H","Julian Cyril D ","01M7AF0MQ10AVG6QJQ1C2BC0F5",2,"MIT","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"rag-architect\"\ndescription: \"Use when the user asks to design a RAG pipeline, choose a chunking strategy or embedding model, pick a vector database, or evaluate retrieval quality (precision@k, recall@k, NDCG). Examples: 'design a RAG system for our docs', 'what chunk size should I use for this corpus', 'evaluate my retriever against ground truth'. NOT for general LLM cost tuning (use llm-cost-optimizer) or agent loops over retrieval (use agenthub).\"\n---\n\n# RAG Architect\n\nDesign, tune, and evaluate production RAG pipelines with three deterministic tools. Run the tools against the actual corpus and requirements — do not pick chunk sizes or databases by intuition.\n\n## Hard rules\n\n1. **Never present model names or vendor prices as current facts.** Embedding models and vector-DB pricing rot in months. Recommend a *tier* (see table below), name a current-generation candidate, and tell the user to verify against the provider's live pricing page.\n2. **Every design ends with an evaluation run.** A RAG design without `retrieval_evaluator.py` numbers is a hypothesis, not a deliverable.\n3. **Chunking is corpus-driven.** Run `chunking_optimizer.py` on the real documents before choosing a strategy.\n\n## Embedding model tiers (pattern, not price list)\n\n| Tier | Current-generation examples (verify before use) | When |\n|---|---|---|\n| Fast \u002F self-hosted | `all-MiniLM-L6-v2`, `bge-small` | Cost-sensitive, small scale, real-time |\n| Balanced open | `all-mpnet-base-v2`, `bge-large`, `e5-large` | Quality without API dependency |\n| Quality API | `text-embedding-3-large`, `voyage-3-large` | Accuracy-priority general retrieval |\n| Code | `voyage-code-3`, CodeBERT-family | Code search corpora |\n\n**Pricing discipline:** build the cost model with a placeholder table — columns `model | $\u002F1M tokens (verify) | dims | as-of date` — and have the user fill in live numbers. Same for vector DBs (Pinecone\u002FWeaviate\u002FQdrant\u002FChroma\u002Fpgvector): the selection criteria (managed vs self-hosted, scale, filtering, existing Postgres) are durable; the dollar figures are not.\n\n## Workflow\n\nAll paths relative to this skill folder. Outputs chain: corpus analysis → design → evaluation.\n\n### 1. Analyze the corpus and pick chunking\n\n```bash\npython3 chunking_optimizer.py \u002Fpath\u002Fto\u002Fdocs --extensions .md .txt -o chunking.json\n```\n\nEmits `chunking.json` with `corpus_info`, per-strategy `strategy_results`, a `recommendation`, and `sample_chunks`. Use `recommendation.strategy` and its config; show the user 2-3 `sample_chunks` so they can sanity-check boundaries.\n\n### 2. Design the pipeline from requirements\n\nWrite a requirements JSON with these keys (all required): `document_types[]`, `document_count`, `avg_document_size` (chars), `queries_per_day`, `query_patterns[]`, `latency_requirement`, `budget_monthly`, `accuracy_priority` (0-1), `cost_priority` (0-1), `maintenance_complexity`.\n\n```bash\npython3 rag_pipeline_designer.py requirements.json -o design.json\n```\n\nEmits `design.json` with `chunking`, `embedding`, `vector_db`, `retrieval`, `reranking`, `evaluation`, `total_cost`, `architecture_diagram` (mermaid), and `config_templates`. Present the diagram; label every `cost_monthly` figure as an estimate to verify (rule 1).\n\n### 3. Evaluate retrieval quality\n\nPrepare `queries.json` (list of `{id, text}` or `{\"queries\": [...]}`) and `ground_truth.json` (`{query_id: [relevant_doc_ids]}`), then:\n\n```bash\npython3 retrieval_evaluator.py queries.json \u002Fpath\u002Fto\u002Fdocs ground_truth.json --k-values 3 5 10 -o eval.json\n```\n\nReports precision@k, recall@k, MRR, NDCG@k, plus `poor_precision_examples` \u002F `poor_recall_examples` for failure analysis.\n\n### 4. Verification loop\n\nThe design is done only when:\n\n1. `eval.json` meets targets — typical floors: precision@5 ≥ 0.8, recall@10 ≥ 0.85 (set per use case with the user).\n2. If below target: inspect the poor-example lists, then change **one** variable (chunking strategy → re-run step 1; embedding tier; add reranking; hybrid retrieval) and re-run step 3. Repeat.\n3. Every recommended model\u002Fprice in the deliverable carries a \"verify current pricing\u002Fmodel availability\" note with an as-of date.\n\n## References\n\n- `references\u002Fchunking_strategies_comparison.md` — strategy trade-offs the optimizer implements\n- `references\u002Fembedding_model_benchmark.md` — benchmark *methodology* (dated snapshot; staleness warning at top)\n- `references\u002Frag_evaluation_framework.md` — metric definitions (faithfulness, relevance, precision\u002Frecall\u002FNDCG)\n","# RAG Architect\n\nDesign, tune, and evaluate production RAG pipelines with three deterministic tools. Run the tools against the actual corpus and requirements — do not pick chunk sizes or databases by intuition.\n\n## Hard rules\n\n1. **Never present model names or vendor prices as current facts.** Embedding models and vector-DB pricing rot in months. Recommend a *tier* (see table below), name a current-generation candidate, and tell the user to verify against the provider's live pricing page.\n2. **Every design ends with an evaluation run.** A RAG design without `retrieval_evaluator.py` numbers is a hypothesis, not a deliverable.\n3. **Chunking is corpus-driven.** Run `chunking_optimizer.py` on the real documents before choosing a strategy.\n\n## Embedding model tiers (pattern, not price list)\n\n| Tier | Current-generation examples (verify before use) | When |\n|---|---|---|\n| Fast \u002F self-hosted | `all-MiniLM-L6-v2`, `bge-small` | Cost-sensitive, small scale, real-time |\n| Balanced open | `all-mpnet-base-v2`, `bge-large`, `e5-large` | Quality without API dependency |\n| Quality API | `text-embedding-3-large`, `voyage-3-large` | Accuracy-priority general retrieval |\n| Code | `voyage-code-3`, CodeBERT-family | Code search corpora |\n\n**Pricing discipline:** build the cost model with a placeholder table — columns `model | $\u002F1M tokens (verify) | dims | as-of date` — and have the user fill in live numbers. Same for vector DBs (Pinecone\u002FWeaviate\u002FQdrant\u002FChroma\u002Fpgvector): the selection criteria (managed vs self-hosted, scale, filtering, existing Postgres) are durable; the dollar figures are not.\n\n## Workflow\n\nAll paths relative to this skill folder. Outputs chain: corpus analysis → design → evaluation.\n\n### 1. Analyze the corpus and pick chunking\n\n```bash\npython3 chunking_optimizer.py \u002Fpath\u002Fto\u002Fdocs --extensions .md .txt -o chunking.json\n```\n\nEmits `chunking.json` with `corpus_info`, per-strategy `strategy_results`, a `recommendation`, and `sample_chunks`. Use `recommendation.strategy` and its config; show the user 2-3 `sample_chunks` so they can sanity-check boundaries.\n\n### 2. Design the pipeline from requirements\n\nWrite a requirements JSON with these keys (all required): `document_types[]`, `document_count`, `avg_document_size` (chars), `queries_per_day`, `query_patterns[]`, `latency_requirement`, `budget_monthly`, `accuracy_priority` (0-1), `cost_priority` (0-1), `maintenance_complexity`.\n\n```bash\npython3 rag_pipeline_designer.py requirements.json -o design.json\n```\n\nEmits `design.json` with `chunking`, `embedding`, `vector_db`, `retrieval`, `reranking`, `evaluation`, `total_cost`, `architecture_diagram` (mermaid), and `config_templates`. Present the diagram; label every `cost_monthly` figure as an estimate to verify (rule 1).\n\n### 3. Evaluate retrieval quality\n\nPrepare `queries.json` (list of `{id, text}` or `{\"queries\": [...]}`) and `ground_truth.json` (`{query_id: [relevant_doc_ids]}`), then:\n\n```bash\npython3 retrieval_evaluator.py queries.json \u002Fpath\u002Fto\u002Fdocs ground_truth.json --k-values 3 5 10 -o eval.json\n```\n\nReports precision@k, recall@k, MRR, NDCG@k, plus `poor_precision_examples` \u002F `poor_recall_examples` for failure analysis.\n\n### 4. Verification loop\n\nThe design is done only when:\n\n1. `eval.json` meets targets — typical floors: precision@5 ≥ 0.8, recall@10 ≥ 0.85 (set per use case with the user).\n2. If below target: inspect the poor-example lists, then change **one** variable (chunking strategy → re-run step 1; embedding tier; add reranking; hybrid retrieval) and re-run step 3. Repeat.\n3. Every recommended model\u002Fprice in the deliverable carries a \"verify current pricing\u002Fmodel availability\" note with an as-of date.\n\n## References\n\n- `references\u002Fchunking_strategies_comparison.md` — strategy trade-offs the optimizer implements\n- `references\u002Fembedding_model_benchmark.md` — benchmark *methodology* (dated snapshot; staleness warning at top)\n- `references\u002Frag_evaluation_framework.md` — metric definitions (faithfulness, relevance, precision\u002Frecall\u002FNDCG)\n",{"name":5,"description":7},"main","57e7aa6b6e03bce1a7d7862ba9c2ec312f7f19b5","src\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect",0,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee","https:\u002F\u002Fwithcyril.me\u002F","Hi, I’m Julian Cyril D, a Computer Science and Business Systems student at PSNACET.\r\nI’m passionate about full-stack development, UI\u002FUX design, and building sma","2026-11-04 23:28:50",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Cyrilthetecchieee\u002Fcyril-code- --skill rag-architect",{"tool":39,"command":40},"bunx","bunx skills add Cyrilthetecchieee\u002Fcyril-code- --skill rag-architect",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Cyrilthetecchieee\u002Fcyril-code- --skill rag-architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002FSKILL.md",true,[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"chunking_optimizer.py.txt","REFERENCE","参考文档",29512,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Fchunking_optimizer.py.txt",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"rag_pipeline_designer.py.txt",28221,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Frag_pipeline_designer.py.txt",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fchunking_strategies_comparison.md",10181,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Freferences\u002Fchunking_strategies_comparison.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fembedding_model_benchmark.md",12729,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Freferences\u002Fembedding_model_benchmark.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frag_evaluation_framework.md",15137,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Freferences\u002Frag_evaluation_framework.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"retrieval_evaluator.py.txt",23603,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering\u002Fskills\u002Frag-architect\u002Fretrieval_evaluator.py.txt",[74,83,90,98,105,112],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AQV6CYX8RMC78420V9WZ62","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FSKILL.md",[],[],{"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":19},"01M7AQV2895N3S1MEX6K76G6G2","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fvideo-downloader\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":78,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7AQTRNX62DNKVZ5GXEHRBKB","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7AQTNNVHAAN9H6DA8T6ZVE0","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftemplate-skill\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7AQTJ3MQ6AKX152MEX2MYCC","tailored-resume-generator","Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftailored-resume-generator\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7AQTD7D5MYET2YWG7HG9WM3","slack-gif-creator","Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like \"make me a GIF for Slack of X doing Y\".","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FSKILL.md",[],[]]