OpenAgentSkill
GitHub200+

Use-case shortlist

Best Agent Skills for RAG and Knowledge Workflows

Find skills for document ingestion, retrieval, embeddings, source-grounded answers, and agent workflows that need reliable private knowledge.

Find skills for this taskRun resolve APIView use caseAgent API docs

Decision prompt

I need my agent to build a RAG workflow over documents, retrieve reliable context, and answer with grounded sources.

4
Shortlist
best
Intent
RAG and knowledgeSource-based selection · not a runtime test

Published by OpenAgentSkill. Candidates are matched to this guide from available registry metadata. Repository stars describe popularity, not task success or safety. Check each source, license and current review before installing.

Recommended shortlist

Start with these skills

Task-matched candidates · not exhaustive
Adopt100/100
LlamaIndex

Data framework for building RAG and knowledge workflows around agent tasks.

Stars42K
Trust79/100
Audit87/100
Quality100/100
RiskSafe to try
Claude CodeOpenAI AgentsRAG and knowledge
$ npx skills add run-llama/llama_index
Adopt100/100
Firecrawl

Turn websites into clean markdown or structured data for retrieval and agents.

Stars34K
Trust80/100
Audit87/100
Quality100/100
RiskSafe to try
Claude CodeOpenAI AgentsCursor
$ npx skills add mendableai/firecrawl
Adopt100/100
Canvas Design

Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

Stars163K
Trust88/100
Audit89/100
Quality100/100
RiskSafe to try
Claude CodeOpenAI AgentsCursor
$ npx skills add anthropics/skills --skill canvas-design
Adopt100/100
MarkItDown

Convert PDFs, Office documents, and web files into clean markdown for agents.

Stars80K
Trust79/100
Audit87/100
Quality100/100
RiskSafe to try
Claude CodeOpenAI AgentsCursor
$ npx skills add microsoft/markitdown

How to use this guide

Move from search to adoption

01

Choose a source corpus

Pick a small but representative set of documents before scaling ingestion.

02

Measure retrieval quality

Ask known-answer questions and inspect whether the right source material appears.

03

Add citations or proof points

Require the agent to show the evidence behind each answer before shipping.

Evaluation notes

What to check before installing

RAG skills should reduce answer risk

The point of a RAG skill is not only retrieval. It should help an agent ingest clean material, retrieve relevant context, and keep answers grounded in sources.

  • +Look for clear ingestion and retrieval behavior.
  • +Prefer skills that make source provenance visible.
  • +Validate chunking and retrieval quality against real documents.

Pair RAG with upstream preparation

Many failures happen before retrieval. Web scraping, PDF parsing, OCR, and document cleanup skills often matter as much as the RAG layer.

  • +Use document processing for messy PDFs and tables.
  • +Use web extraction for public-source knowledge bases.
  • +Use data analysis skills when retrieved context becomes structured metrics.

FAQ

Common questions

Do I need a separate scraping skill for RAG?

If the source material lives on the web, a scraping skill can be the upstream ingestion layer. For private files, document processing may be more important.

What is the first RAG skill to install?

Start with a skill that can ingest and retrieve from your actual source format, then add companions for parsing, crawling, or evaluation.

Next guides

Keep building the workflow

Use-case shortlist

Web scraping skills

Compare skills for crawling sites, extracting structured data, converting pages to markdown, and feeding reliable web context into agent workflows.

Platform shortlist

Codex skills

A focused guide for builders using Codex-style coding agents: repository inspection, issue triage, implementation planning, testing, and browser verification skills.

Installation guide

Install in Codex

A step-by-step workflow for adding install-ready skills to a Codex-style agent setup while keeping validation, permissions, and rollback in mind.