Skip to content
TrustedSkillsbeta
Back to all skills

Docs Seeker

Checked
mrgoonie·vlatest·writing

Docs Seeker instantly finds relevant documentation snippets based on your query, saving you time searching for information.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add mrgoonie/claudekit-skills --skill docs-seeker -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

mrgoonie

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned mrgoonie/claudekit-skills at 80113d86bc.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
80113d86bc
Manifest
.claude/skills/docs-seeker/SKILL.md
Scanned
8 files, 3,635 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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.txt Search: Prioritizes finding standardized AI-friendly documentation files hosted at context7.com.
  • GitHub Repository Analysis: Uses Repomix to analyze GitHub repositories when llms.txt is 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.txt files 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.txt files, 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.com URL; this may not always be accurate.
  • When analyzing GitHub repositories, Repomix must be installed globally (npm install -g rep).