Docs Seeker

This is a smart wrapper around the llms.txt standard that knows how to hunt down technical documentation through multiple fallback strategies. It starts by checking context7.com for standardized AI-friendly docs, then falls back to GitHub repo analysis via Repomix, and finally deploys parallel Explorer agents if needed. The workflow is thorough: it handles versioning, knows common documentation patterns across frameworks, and spins up multiple agents when dealing with large doc sets. Honest take: the context7.com prioritization is clever since it's an aggregator, but the real value is in the fallback chain. You're basically getting a documentation retrieval system that won't give up easily, which beats manually clicking through docs sites when you need to pull reference material into your context window.

skills.sh installs: 408
GitHub stars: 2.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mrgoonie/claudekit-skills --skill docs-seeker --agent claude-code

Installs into .claude/skills of the current project.

Files

Documentation Discovery & Analysis

Overview

Intelligent discovery and analysis of technical documentation through multiple strategies:

llms.txt-first: Search for standardized AI-friendly documentation
Repository analysis: Use Repomix to analyze GitHub repositories
Parallel exploration: Deploy multiple Explorer agents for comprehensive coverage
Fallback research: Use Researcher agents when other methods unavailable

Core Workflow

Phase 1: Initial Discovery

Identify target
- Extract library/framework name from user request
- Note version requirements (default: latest)
- Clarify scope if ambiguous
- Identify if target is GitHub repository or website
Search for llms.txt (PRIORITIZE context7.com)

First: Try context7.com patterns