rag-architect

80 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By jeffallan/claude-skills (GitHub) · coding · 12,305 stars · scanned at commit 078a25c

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing.

Works with any agent that supports SKILL.md skills.

What this skill can do

Can call paid AI services billed to you

The author does not mention this.

Found in 6 places.

skills/rag-architect/SKILL.md, line 66from openai import OpenAI
skills/rag-architect/references/chunking-strategies.md, line 640from openai import OpenAI
skills/rag-architect/references/embedding-models.md, line 99from openai import OpenAI

Show 3 more

skills/rag-architect/references/embedding-models.md, line 481from openai import AsyncOpenAI
skills/rag-architect/references/rag-evaluation.md, line 376from openai import OpenAI
skills/rag-architect/references/retrieval-optimization.md, line 243from openai import OpenAI

Sends data to these websites: api.openai.com

The author does not mention this.

Found in 6 places.

skills/rag-architect/SKILL.md, line 66from openai import OpenAI
skills/rag-architect/references/chunking-strategies.md, line 640from openai import OpenAI
skills/rag-architect/references/embedding-models.md, line 99from openai import OpenAI

Show 3 more

skills/rag-architect/references/embedding-models.md, line 481from openai import AsyncOpenAI
skills/rag-architect/references/rag-evaluation.md, line 376from openai import OpenAI
skills/rag-architect/references/retrieval-optimization.md, line 243from openai import OpenAI

Runs commands on your computer

The author does not mention this. Expected for a coding skill.

Found in 1 place.

skills/rag-architect/references/embedding-models.md, line 223"def install_package(name):\n subprocess.run(['pip', 'install', name])",

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'rag-architect' ] || [ -L ~/.agents/skills/'rag-architect' ]; then echo 'A skill folder named rag-architect already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/jeffallan/claude-skills' "$d" && git -C "$d" checkout --quiet '078a25cc5bfd8011459be7b91d004e900c1d02d3' -- 'skills/rag-architect' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/rag-architect' ~/.agents/skills/'rag-architect' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'rag-architect' ~/.claude/skills/'rag-architect' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for jeffallan/claude-skills shows the score of its lowest-scoring skill.

SkillTrust badge for jeffallan/claude-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/jeffallan/claude-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/jeffallan/claude-skills/)

Score history

Date	Version	Score
2026-11-08	`078a25c`	80