RAG Web Fallback

RAG Web Fallback is an AI Engineering skill for Claude Code, published by lyonzin in knowledge-rag.

265 stars38 forkson lyonzin/knowledge-ragAdded 2026/09/02+2% in starsRepository updated 2026/09/01

antigravityclaudeclaude-codeclaude-code-clicodexcursor-aidocument-searchhybrid-searchinteligencia-artificialknowledge-baselocal-aimcpmcp-serverragrag-chatbotrag-pipelinererankingretrieval-augmented-generationsemantic-searchvector-database

Install in seconds

Install RAG Web Fallback

Copy RAG Web Fallback into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/lyonzin/knowledge-rag/tree/master/skills/workflow/rag-web-fallback ~/.claude/skills/rag-web-fallback

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/lyonzin/knowledge-rag.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/workflow/rag-web-fallback/SKILL.md in lyonzin/knowledge-rag
Installs to: ~/.claude/skills/rag-web-fallback
Collection: One of 10 skills cataloged from this repository
Category: AI Engineering — 2631 skills

What RAG Web Fallback does

RAG Web Fallback forces an agent to search the local knowledge base before using external web tools. It is used when a question might be answered from indexed docs and the agent must explain why it escalated if local coverage is missing.

RAG Web Fallback is cataloged under AI Engineering on DirSkills. RAG Web Fallback comes from a repository tagged antigravity, claude, claude-code, claude-code-cli and codex.

Documentation

README

Excerpt

rag-web-fallback — local first, web only when necessary

When to use this skill

Whenever the agent is tempted to call an external tool for information (WebSearch, WebFetch, mcp__exa__*, mcp__context7__*, etc.), route through this skill's checklist first.

Applies to:

Any request that could be answered from indexed docs before hitting the network
Any factual claim the agent is about to look up externally
Any "give me the latest on X" question where X might be in the corpus

Does NOT apply to:

Deliberate freshness requests: "what happened today", "current news"
User explicitly asks for a web search
Live infra queries (external API calls that are the actual task, not for context)

What this skill commits to

The agent will:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about RAG Web Fallback

What else does lyonzin publish alongside RAG Web Fallback?
RAG Web Fallback is one of 10 skills that DirSkills catalogs from lyonzin/knowledge-rag, the repository it ships in. Its siblings there include RAG Check First, RAG Code Review and RAG Evaluate Quality. Each one is a separate skill with its own page in this directory, installs the same way RAG Web Fallback does, and is maintained by lyonzin in that same repository. The rest of the collection is listed on the lyonzin/knowledge-rag page.
How does RAG Web Fallback compare to other AI Engineering skills?
RAG Web Fallback ranks #2245 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of RAG Web Fallback against them. Open each page to compare what they document and how they install.