ck:docs-seeker

Name: ck:docs-seeker
Availability: InStock
Author: EdgeHunt

Detect topics, fetch context7 docs, and analyze llms.txt for agent planning.

Updated Apr 2, 2026

Search Tags:#automation #documentation #discovery #scripts #llms.txt #context7 #topic-detection

Ready to run

npx skills add https://github.com/EdgeHunt/EdgeHunt --skill ck-docs-seeker-edgehunt

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ck:docs-seeker
Source: https://github.com/EdgeHunt/EdgeHunt/tree/main/.claude/skills/docs-seeker
Command: npx skills add https://github.com/EdgeHunt/EdgeHunt --skill ck-docs-seeker-edgehunt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Documentation discovery for libraries and frameworks often requires many manual searches across multiple sources. This skill provides a script-first workflow to detect topic relevance, fetch authoritative docs, and analyze results to guide agent deployment.

Core Features & Use Cases

Script-first discovery that classifies queries into topic-specific or general and routes to the appropriate docs sources.
Automated fetch of llms.txt content from context7.com with automatic fallbacks and error handling.
Analysis of collected URLs to determine priority, workload distribution, and recommended agent counts for efficient exploration.

Quick Start

Start by running the topic-detection script on a user query to classify it as topic-specific or general, then fetch documentation with the docs-fetching script, and finally analyze the llms.txt results to plan agent deployment.

Frequently Asked Questions about ck:docs-seeker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate documentation discovery for libraries and frameworks?▼

Automating documentation discovery is handled through a script-first workflow that classifies queries, fetches context7 docs, and analyzes llms.txt results to plan agent deployment. This removes the need for manual searches across multiple sources.

How does the llms.txt analysis workflow determine priority and workload distribution?▼

The llms.txt analysis workflow evaluates collected URLs to determine priority, workload distribution, and recommended agent counts. It outputs JSON data that drives downstream agents for efficient documentation exploration.

Can I use context7 to fetch llms.txt content with fallbacks for offline or failed requests?▼

Yes, context7 fetches llms.txt content with automatic fallbacks and error handling. This ensures the documentation discovery process continues smoothly even if the primary source fails.

What's the best way to route topic-specific and general queries for documentation fetching?▼

Routing topic-specific and general queries is achieved by running a topic-detection script first. This deterministic script classifies the query and then routes it to the appropriate context7 docs sources.

Do I need specific environment configuration to run script-initiated documentation workflows?▼

Yes, the skill relies on environment-driven configuration to support script-initiated workflows. This setup enables zero-token context loading and generates JSON outputs for downstream agents.

Why does automated docs discovery use JSON outputs instead of raw markdown text?▼

Automated docs discovery uses JSON outputs to drive downstream agents directly. This structured format includes planning data, priority rankings, and agent-distribution guidance, which raw text cannot easily provide.