docs-discovery_skill

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