home / skills / samhvw8 / dotfiles / docs-discovery

docs-discovery skill

safe

This skill quickly locates official library and framework documentation using context7 and web search to answer API and usage questions.

npx playbooks add skill samhvw8/dotfiles --skill docs-discovery

Review the files below or copy the command above to add this skill to your agents.

Files (20)

SKILL.md

1.8 KB

---
name: docs-discovery
description: "Technical documentation discovery via context7 and web search. Capabilities: library/framework docs lookup, topic-specific search. Keywords: llms.txt, context7, documentation, library docs, API docs. Use when: searching library documentation, finding framework guides, looking up API references."
version: 7.0.0
---

# 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

| Step | Tool | Purpose |
|------|------|---------|
| 1 | `mcp__context7__resolve-library-id` | Get context7 library ID |
| 1 | `mcp__context7__get-library-docs` | Fetch docs from context7 |
| 2 | `WebSearch` | Search for llms.txt and docs URLs |
| 3 | `WebFetch` | Fetch 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

Overview

This skill locates official library and framework documentation quickly using context7 and targeted web search. It prioritizes curated context7 results, then falls back to parallel web searches for llms.txt and official docs, fetching and extracting relevant content for topic-specific needs.

How this skill works

First, it attempts to resolve the library ID and retrieve docs from context7 for a fast, curated result. If that fails, it runs parallel WebSearch queries for "{library} llms.txt" and "{library} official documentation", then WebFetches discovered URLs. Finally, it parses fetched pages and llms.txt files and presents filtered, topic-specific excerpts or links.

When to use it

Searching for official API references or developer guides
Finding framework how-tos or migration guides
Looking up library-specific llms.txt or model usage notes
Needing topic-filtered documentation (e.g., authentication, configuration)
Verifying authoritative docs when URL patterns are uncertain

Best practices

Always try context7 first to leverage curated sources and reduce noise
Run WebSearch queries in parallel to reduce latency when context7 has no match
Search explicitly for "llms.txt" to surface machine-readable docs and usage notes
Filter results by topic parameter to avoid irrelevant sections of large docs
Fetch and parse discovered URLs rather than guessing URL patterns

Example use cases

User asks for Django authentication docs: resolve via context7 or fetch official guide sections for authentication
Developer requests TensorFlow API reference for a specific layer: attempt context7 then search and fetch API pages and llms.txt notes
Engineer needs migration steps for library X v2→v3: search for official migration guide and extract the relevant section
Integrate tooling that reads llms.txt for recommended models and usage instructions from a library repository

FAQ

What if context7 returns partial or outdated docs?

If context7 results are incomplete, the skill falls back to web search and fetch to locate the latest official pages and llms.txt entries, then merges and presents the most relevant content.

Why search for llms.txt specifically?

llms.txt often contains machine-readable usage guidance, model recommendations, and API notes not prominent in standard docs. Searching for it surfaces concise, actionable details.