Rag Troubleshoot

Rag Troubleshoot 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 Troubleshoot

Copy Rag Troubleshoot 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-troubleshoot ~/.claude/skills/rag-troubleshoot

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

What Rag Troubleshoot does

Rag Troubleshoot searches the knowledge corpus for prior errors, fixes, runbooks, and incidents before general debugging. Use it when a user reports a bug, exception, stack trace, failed CI run, or unexpected behavior.

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

Documentation

README

Excerpt

rag-troubleshoot — RAG-first debugging

When to use this skill

Trigger the moment the user reports:

A specific error message, stack trace, or exception
"It broke", "it fails", "not working", "returns null when it shouldn't"
Unexpected behavior in a component
Alert / incident triage
"Why does X do Y" where Y is wrong
A pasted log line
A failed CI/CD run

The core insight: many bugs are already solved somewhere in your corpus — runbook, postmortem, incident report, prior fix commit, ADR, chat thread indexed via add_from_url. Search first.

What this skill commits to

Before proposing a fix, the agent searches for:

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

Frequently asked about Rag Troubleshoot

What else does lyonzin publish alongside Rag Troubleshoot?
Rag Troubleshoot 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 Troubleshoot 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 Troubleshoot compare to other AI Engineering skills?
Rag Troubleshoot ranks #2244 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 Troubleshoot against them. Open each page to compare what they document and how they install.