mcpField
D
docs-discovery

docs-discovery

github.com/samhvw8Development1541 installsUpdated 1d ago
Repository

About docs-discovery

docs-discovery is a skill for locating official library and framework documentation. It tries Context7 first, then searches for documentation URLs and fetches the resulting pages.

Key features

  1. 01Resolve library IDs with Context7
  2. 02Retrieve topic-specific library docs
  3. 03Search for llms.txt and official docs
  4. 04Fetch and parse discovered documentation

Use cases

  1. 01Find official docs for a library
  2. 02Research a specific library topic
  3. 03Locate and inspect llms.txt documentation

MCP support

The skill uses Context7 MCP tools first to resolve library IDs and retrieve documentation, then falls back to WebSearch and WebFetch.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/samhvw8/dotfiles --skill docs-discovery

After installing, type/docs-discoveryin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

COMPARISON.md
README.md
REFACTORING_SUMMARY.md
archive/
dot_env.example
package.json
archive/references/
advanced.md
context7-patterns.md
errors.md
archive/scripts/
analyze-llms-txt.js
detect-topic.js
fetch-docs.js
archive/scripts/tests/
run-tests.js
test-analyze-llms.js
test-detect-topic.js
test-fetch-docs.js
archive/scripts/utils/
env-loader.js
archive/workflows/
library-search.md
repo-analysis.md
topic-search.md

Details

From the project README

Documentation Discovery

Mission: Find official library/framework documentation quickly.

Strategy

Step 1: Try context7 First
mcp__context7__resolve-library-id("{library}")
→ Success? → mcp__context7__get-library-docs("{id}", topic="{topic}")
→ Fail? → Step 2
Step 2: Search for Documentation URLs

If context7 fails, run these searches in parallel:

WebSearch: "{library} llms.txt"
WebSearch: "{library} official documentation"
Step 3: Fetch Found URLs

WebFetch the URLs found from Step 2:

  • llms.txt links → fetch and parse
  • Documentation pages → fetch and extract content

Workflow Summary

1. context7 (fast, curated)
   ↓ fail
2. WebSearch (parallel):
   - "{library} llms.txt"
   - "{library} official documentation"
   ↓ found URLs
3. WebFetch found URLs
   ↓ content
4. Parse & present to user

Tools

StepToolPurpose
1mcp__context7__resolve-library-idGet context7 library ID
1mcp__context7__get-library-docsFetch docs from context7
2WebSearchSearch for llms.txt and docs URLs
3WebFetchFetch documentation content

Key Rules

  • context7 first - Fastest, already curated
  • Search, don't guess - Don't guess URL patterns, search for them
  • Parallel search - Run multiple WebSearch queries together
  • Topic filtering - Use topic param in context7, filter search results by topic

Comments

Markdown supported