Skip to main content
skill CX Codex

ai-rag-pipeline — Claude Code skill: RAG with web search and LLM

ai-rag-pipeline — a skill for building RAG pipelines: web search supplies the facts, a model writes the cited answer. Handy for research agents and claim checking.

no license 240 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill ai-rag-pipeline -a claude-code
Open on GitHub

What ai-rag-pipeline does

The skill lays out how to assemble retrieval pipelines from hosted apps on inference.sh. Search brings back fresh results, the model receives them inside the prompt and answers with sources attached. You get a few shapes to pick from: one search plus one answer, two search engines merged into a single analysis, or URL content pulled and condensed.

Commands run as belt app run against tavily/search-assistant, exa/search, exa/answer, tavily/extract, and models routed through openrouter/ such as GPT-4o and Gemini 2.5 Pro. The agent stores search output in a shell variable and pastes it into the next prompt. Claim checking has its own flow: gather evidence first, then return a verdict alongside supporting and contradicting material.

You need the belt CLI (npx skills add belt-sh/cli) plus a session from belt login; belt app run fails without it. The skill's permission is scoped to Bash(belt *), so it stays out of the rest of your shell. Long search dumps are meant to be summarised first — otherwise the model's context fills up fast.

What it helps with

  • answer a question from live search results with sources attached
  • fact-check a claim against collected evidence and get a verdict
  • merge Tavily and Exa output into one analysis that flags contradictions
  • extract readable text from a set of URLs and boil it down
  • produce a topic report with stats and expert commentary

Example prompts for the agent

  • Run a RAG pass on quantum computing: search with tavily/search-assistant, then have openrouter/ write a summary with citations
  • Fact-check a claim about generative AI in creative work — gather research first, then give me a verdict and sources
  • Pull the content from these URLs with tavily/extract and list the key findings

How to install ai-rag-pipeline

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-rag-pipeline -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-rag-pipeline/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-rag-pipeline/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ai-rag-pipeline

How do I install ai-rag-pipeline in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-rag-pipeline -a claude-code. The skill file ends up at ~/.claude/skills/ai-rag-pipeline/SKILL.md.

What does ai-rag-pipeline do?

It gives the agent a working recipe for pairing web search with a language model: results go into the prompt, the answer comes back cited. Separate flows cover claim checking and report writing.

What else do I need for it to work?

The belt CLI, installed with npx skills add belt-sh/cli, and a login through belt login. Everything the skill calls goes through belt app run.

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
nano-banana nano-banana — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that calls Google Gemini native image models through the inference.sh CLI. CX Codex +1 241installs python-sdk python-sdk teaches your coding assistant how to use the inference.sh Python package to run generative apps and assemble agents. CX Codex +1 241installs twitter-thread-creation twitter-thread-creation guides your agent in writing high-engagement X threads, formatting hook tweets, and dispatching posts via the belt CLI. CX Codex +1 240installs pitch-deck-visuals pitch-deck-visuals builds an investor-deck outline with slide design rules and data visuals. Use it for fundraising decks, demo days, grant proposals, or startup presentations. CX Codex +1 240installs nano-banana-2 Generates images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) through the belt CLI. Runs on text prompts, edits existing images, and accepts up to 14 input files. CX Codex +1 240installs qwen-image-2 qwen-image-2 is a Claude Code skill for creating and editing images with Alibaba Qwen-Image-2.0. It responds to Qwen Image and image-generation requests. CX Codex +1 240installs qwen-image-2-pro qwen-image-2-pro — a skill for Claude Code and Cursor that generates images via Alibaba Qwen-Image-2.0-Pro. Renders multi-line text in posters and banners. CX Codex +1 239installs linkedin-content linkedin-content — a skill for drafting LinkedIn posts: hook formulas, formatting rules, post types, character limits and the signals the feed rewards. CX Codex +1 239installs

Project sponsors

Companies that keep this analytics open