skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / AI Agents & MCP / RAG Architect Skill by @alirezarezvani
The skill is the engineering/skills/rag-architect folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Guides the design of a retrieval pipeline: chunking, embedding tier, vector store choice and retrieval quality checks.
Insists on running its bundled tools against the real corpus instead of guessing chunk sizes or databases. It deliberately avoids quoting model names or prices as current, framing embedding choices as tiers, and closes with a verification loop on retrieval quality.
The original SKILL.md is organised into these sections:
Written and maintained by @alirezarezvani. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
# RAG Architect Design, 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. ## Hard rules 1. **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. 2. **Every design ends with an evaluation run.** A RAG design without `retrieval_evaluator.py` numbers is a hypothesis, not a deliverable. 3. **Chunking is corpus-driven.** Run `chunking_optimizer.py` on the real documents before choosing a strategy. ## Embedding model tiers (pattern, not price list) | Tier | Current-generation examples (verify before use) | When | |---|---|---| | Fast / self-hosted | `all-MiniLM-L6-v2`, `bge-small` | Cost-sensitive, small scale, real-time | …
Excerpt only, quoted from the author's repository. Open the repository for the complete file.