Docs Seeker
Docs Seeker instantly finds relevant documentation snippets based on your query, saving you time searching for information.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add docs-seeker npx -- -y @trustedskills/docs-seeker
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"docs-seeker": {
"command": "npx",
"args": [
"-y",
"@trustedskills/docs-seeker"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
Docs Seeker is designed to quickly locate and analyze relevant documentation for software libraries, frameworks, or websites. It prioritizes finding standardized llms.txt files (often hosted on context7.com) which contain AI-friendly documentation snippets. When a direct llms.txt isn't found, it falls back to analyzing GitHub repositories using Repomix and performing web searches. The skill can also leverage multiple "Explorer" agents in parallel to comprehensively cover large documentation sets.
When to use it
- You need to quickly find information about a specific software library or framework.
- You're struggling to locate the relevant documentation through traditional search methods.
- You want to understand the AI-friendly documentation for a project (e.g., identifying supported models).
- You're researching a GitHub repository and need to quickly extract key information from its documentation.
- You’re looking for details on a specific feature within a library or framework.
Key capabilities
llms.txtSearch: Prioritizes finding standardized AI-friendly documentation files hosted atcontext7.com.- GitHub Repository Analysis: Uses Repomix to analyze GitHub repositories when
llms.txtis unavailable. - Parallel Exploration: Deploys multiple "Explorer" agents concurrently for comprehensive documentation coverage.
- Fallback Research: Utilizes web searches and Researcher agents as a last resort.
- Topic-Specific Searches: Allows searching within
llms.txtfiles for information related to specific topics (e.g., “date”, “cache”).
Example prompts
- "Find the documentation for the imagick library."
- "What's the installation process for Next.js?"
- "Show me the llms.txt file for byteplus ModelArk."
- “How do I use caching in vercel/next.js?”
Tips & gotchas
- The skill prioritizes finding
llms.txtfiles, so its effectiveness depends on whether these files are available for your target library or framework. - For websites, the skill uses a normalized domain path to construct the
context7.comURL; this may not always be accurate. - When analyzing GitHub repositories, Repomix must be installed globally (
npm install -g rep).
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.