TakaGoto/rag-learning-academy
A structured, multi-agent Claude Code learning environment for mastering Retrieval-Augmented Generation (RAG)
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Copy this rig
# review before running: this installs third-party code
$ npx degit TakaGoto/rag-learning-academy/.claude ./rig-rag-learning-academy # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit TakaGoto/rag-learning-academy/.claude/skills/architecture .claude/skills/architecture $ npx degit TakaGoto/rag-learning-academy/.claude/skills/audit-content .claude/skills/audit-content $ npx degit TakaGoto/rag-learning-academy/.claude/skills/benchmark .claude/skills/benchmark $ npx degit TakaGoto/rag-learning-academy/.claude/skills/break-it .claude/skills/break-it $ npx degit TakaGoto/rag-learning-academy/.claude/skills/challenge .claude/skills/challenge $ npx degit TakaGoto/rag-learning-academy/.claude/skills/code-review .claude/skills/code-review $ npx degit TakaGoto/rag-learning-academy/.claude/skills/compare .claude/skills/compare $ npx degit TakaGoto/rag-learning-academy/.claude/skills/debug-rag .claude/skills/debug-rag $ npx degit TakaGoto/rag-learning-academy/.claude/skills/evaluate .claude/skills/evaluate $ npx degit TakaGoto/rag-learning-academy/.claude/skills/explain .claude/skills/explain $ npx degit TakaGoto/rag-learning-academy/.claude/skills/fix .claude/skills/fix $ npx degit TakaGoto/rag-learning-academy/.claude/skills/glossary .claude/skills/glossary $ npx degit TakaGoto/rag-learning-academy/.claude/skills/journal .claude/skills/journal $ npx degit TakaGoto/rag-learning-academy/.claude/skills/lesson .claude/skills/lesson $ npx degit TakaGoto/rag-learning-academy/.claude/skills/paper-review .claude/skills/paper-review $ npx degit TakaGoto/rag-learning-academy/.claude/skills/quiz .claude/skills/quiz $ npx degit TakaGoto/rag-learning-academy/.claude/skills/recap .claude/skills/recap $ npx degit TakaGoto/rag-learning-academy/.claude/skills/roadmap .claude/skills/roadmap $ npx degit TakaGoto/rag-learning-academy/.claude/skills/sandbox .claude/skills/sandbox $ npx degit TakaGoto/rag-learning-academy/.claude/skills/start .claude/skills/start $ npx degit TakaGoto/rag-learning-academy/.claude/skills/triage .claude/skills/triage
$ curl -fsSL --create-dirs -o .claude/agents/architecture-director.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/architecture-director.md $ curl -fsSL --create-dirs -o .claude/agents/chunking-strategist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/chunking-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/curriculum-director.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/curriculum-director.md $ curl -fsSL --create-dirs -o .claude/agents/deployment-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/deployment-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/document-parser.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/document-parser.md $ curl -fsSL --create-dirs -o .claude/agents/embedding-lead.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/embedding-lead.md $ curl -fsSL --create-dirs -o .claude/agents/evaluation-lead.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/evaluation-lead.md $ curl -fsSL --create-dirs -o .claude/agents/evaluation-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/evaluation-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/graph-rag-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/graph-rag-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/hybrid-search-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/hybrid-search-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/indexing-lead.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/indexing-lead.md $ curl -fsSL --create-dirs -o .claude/agents/integration-lead.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/integration-lead.md $ curl -fsSL --create-dirs -o .claude/agents/metadata-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/metadata-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/multimodal-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/multimodal-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/prompt-engineer.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/prompt-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/query-analyst.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/query-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/reranking-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/reranking-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/research-director.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/research-director.md $ curl -fsSL --create-dirs -o .claude/agents/retrieval-lead.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/retrieval-lead.md $ curl -fsSL --create-dirs -o .claude/agents/vector-db-specialist.md https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/vector-db-specialist.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(sudo *)",
"Bash(chmod *)",
"Bash(rm -rf *)",
"Bash(git push --force*)",
"Bash(git push -f*)",
"Bash(git reset --hard*)",
"Bash(cat .env*)",
"Bash(less .env*)",
"Bash(more .env*)",
"Read(.env*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/validate-code.sh"
}
]
}
]
}
} Skills (21)
architectureaudit-contentbenchmarkbreak-itchallengecode-reviewcomparedebug-ragevaluateexplainfixglossaryjournallessonpaper-reviewquizrecaproadmapsandboxstarttriage
Subagents (20)
| Architecture Director model: opus | Guides RAG system design decisions, component integration, trade-off analysis, and architectural patterns for building robust retrieval-augmented generation systems. |
| Chunking Strategist model: sonnet | Teaches document splitting strategies including fixed, recursive, semantic, and agentic chunking, overlap optimization, and chunk size tuning for optimal RAG performance. |
| Curriculum Director model: opus | Oversees the RAG learning path, tracks learner progression, detects knowledge gaps, and orchestrates the overall learning experience across all agents. |
| Deployment Specialist model: sonnet | Teaches production RAG deployment including caching strategies, scaling patterns, monitoring, cost optimization, latency reduction, and operational best practices. |
| Document Parser model: sonnet | Teaches PDF, HTML, and markdown parsing, table extraction, OCR, multimodal document handling, and data cleaning strategies for RAG ingestion pipelines. |
| Embedding Lead model: sonnet | Teaches embedding models, vector space concepts, similarity metrics, dimensionality reduction, and model selection for RAG applications. |
| Evaluation Lead model: sonnet | Teaches RAG evaluation frameworks, metrics design, quality gates, and systematic approaches to measuring and improving RAG system performance. |
| Evaluation Specialist model: sonnet | Teaches hands-on RAGAS implementation, custom metric design, A/B testing for RAG systems, regression detection, and continuous evaluation workflows. |
| Graph RAG Specialist model: sonnet | Teaches knowledge graph integration with RAG, entity extraction, graph construction, GraphRAG patterns, and structured knowledge retrieval techniques. |
| Hybrid Search Specialist model: sonnet | Teaches BM25 + dense retrieval fusion, reciprocal rank fusion, sparse embeddings (SPLADE), and hybrid search pipeline design for comprehensive retrieval. |
| Indexing Lead model: sonnet | Teaches vector database architecture, indexing algorithms (HNSW, IVF, PQ), storage optimization, and the internals of how vector search actually works. |
| Integration Lead model: sonnet | Teaches end-to-end RAG pipeline construction, framework selection (LangChain vs LlamaIndex vs custom), deployment strategies, and connecting all RAG components into working systems. |
| Metadata Specialist model: sonnet | Teaches metadata extraction, filtering strategies, namespace design, tagging taxonomies, and how to leverage metadata to dramatically improve RAG retrieval quality. |
| Multimodal Specialist model: sonnet | Teaches image, table, and chart RAG, vision embeddings, multimodal retrieval, and techniques for building RAG systems that go beyond text. |
| Prompt Engineer model: sonnet | Teaches context injection patterns, prompt templates for RAG, few-shot RAG, citation formatting, and the art of instructing LLMs to use retrieved context effectively. |
| Query Analyst model: sonnet | Teaches query understanding, expansion, decomposition, HyDE (Hypothetical Document Embeddings), step-back prompting, and query preprocessing for improved RAG retrieval. |
| Reranking Specialist model: sonnet | Teaches cross-encoder reranking, ColBERT, Cohere Rerank, and reranking pipeline design for improving retrieval precision in RAG systems. |
| Research Director model: opus | Tracks the latest RAG research papers, emerging techniques, benchmark comparisons, and translates academic advances into practical learning content. |
| Retrieval Lead model: sonnet | Teaches search strategies including dense, sparse, and hybrid retrieval, ranking algorithms, and retrieval optimization for RAG systems. |
| Vector DB Specialist model: sonnet | Provides hands-on guidance for working with vector databases including Chroma, Pinecone, Weaviate, pgvector, and Qdrant — setup, migration, querying, and operational best practices. |
Hooks (4)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | .claude/hooks/session-start.sh |
| SessionStart | * | .claude/hooks/check-freshness.sh |
| PreToolUse | Bash | .claude/hooks/validate-code.sh |
| Stop | * | .claude/hooks/session-stop.sh |
Permissions
deny (10)
Bash(sudo *)
Bash(chmod *)
Bash(rm -rf *)
Bash(git push --force*)
Bash(git push -f*)
Bash(git reset --hard*)
Bash(cat .env*)
Bash(less .env*)
Bash(more .env*)
Read(.env*)
ask (0)
—
allow (11)
Bash(git status*)
Bash(git diff*)
Bash(git log*)
Bash(git branch*)
Bash(python *)
Bash(python3 *)
Bash(pytest*)
Bash(pip install*)
Bash(pip3 install*)
Bash(ls*)
Bash(jq*)
Similar rigs
lightpointventures/claude-code-starter
Claude Code starter kit: ready-to-use CLAUDE.md templates and 36 practical Skills | Claude Code 新手模板：开箱即用的 CLAUDE.md 模板和实用 Skills
Skill Collector 1.6k tok ·
rafagomes/ai-workflow
AI-assisted development workflow toolkit for Claude Code, Cursor, and Codex — skills, agents, and conventions for the full SDLC
Skill Collector 4.0k tok ·
demetrius2017/claude-booster
Self-installing Claude Code configuration: rules, Python hook scripts, slash commands, agent protocols, and a safely-merged settings.json. One repo → reproducible Claude Code deployment on macOS + Linux + WSL2.
Skill Collector 1.6k tok ·
tammai/ai-sdlc
Claude Code plugin for vibe coding on the AI-native SDLC playbook: intent → design → spec → plan → verify → review → ship. Runs on a Claude subscription, with opinionated stacks (Nuxt/Next + Cloudflare, Go + Postgres, Flutter, Tauri) and de
Orchestrator 3.2k tok ·