#01
LlamaIndex
Data framework for building RAG and knowledge workflows around agent tasks.
100
Quality
79
Trust
—
Proven
RAGJun 1, 2026 pushMITNeeds first agent run
$ npx skills add run-llama/llama_indexKnowledge skills
RAG and knowledge base skills for AI agents.
Find skills for document ingestion, chunking, embeddings, retrieval, source citation, semantic search, and grounded agent answers.
Built for builders searching for RAG, retrieval, knowledge base, embedding, and document ingestion skills for agents.
Matched
6
Stars
324K
Workflow
Retrieve
Data
Docs
Agent jobs
Start from a real workflow, not a keyword.
These pages are built for high-intent search and for agents that need a structured shortlist with install commands, trust signals, audit links, and real outcome evidence before installing third-party code.
01
Build a RAG knowledge base over product docs
02
Crawl documentation and prepare searchable markdown
03
Retrieve relevant source passages before answering
04
Compare embedding, indexing, and retrieval options
Task routes
Task pages agents can call.
Build RAG
Build a RAG knowledge base
Ingest docs, chunk content, retrieve relevant passages, and cite sources in agent answers.
Crawl docs
Crawl a documentation site
Turn documentation pages into clean markdown or records that an agent can search and reuse.
PDF to markdown
Convert PDFs to markdown
Extract readable text, tables, and metadata from PDFs for agent workflows.
Ranked shortlist
High-signal skills to inspect first.
42K stars
#02
MarkItDown
Convert PDFs, Office documents, and web files into clean markdown for agents.
100
Quality
79
Trust
—
Proven
Document ProcessingJun 1, 2026 pushMITNeeds first agent run
$ npx skills add microsoft/markitdown#03
Firecrawl
Turn websites into clean markdown or structured data for retrieval and agents.
100
Quality
80
Trust
—
Proven
Web ScrapingJun 1, 2026 pushAGPL-3.0Needs first agent run
$ npx skills add mendableai/firecrawl163K stars
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
100
Quality
97
Trust
77
Proven
design-creativeJul 17, 2026 pushSource terms (see LICENSE.txt)Promising agent evidence
$ npx skills add anthropics/skills --skill canvas-design2.6K stars
Rank recent market-moving news and explain likely effects on equities, commodities, monetary policy, and earnings.
100
Quality
79
Trust
—
Proven
FinanceAug 10, 2026 pushMITNeeds first agent run
$ npx -y skills add tradermonty/claude-trading-skills --skill market-news-analyst2.6K stars
Research a US equity across fundamentals, valuation, technical context, peers, and current market data.
100
Quality
81
Trust
—
Proven
FinanceAug 10, 2026 pushMITNeeds first agent run
$ npx -y skills add tradermonty/claude-trading-skills --skill us-stock-analysisEvaluation
How to choose the right skill.
Preserves source URLs and citation metadata
Separates ingestion, retrieval, and generation steps
Documents chunking and evaluation assumptions
Can be tested against a known question set
Questions
What should an agent check before using a RAG skill?
Check source preservation, retrieval quality, chunking strategy, supported data stores, and whether the workflow can cite evidence.
Are RAG skills different from document parsing skills?
Yes. Document parsing prepares clean text or tables; RAG skills usually add indexing, retrieval, and source-grounded answer workflows.