← ClaudeAtlas

oreillylisted

O'Reilly Learning Platform search routing. Two tools wrapped via mcp-gateway: chapter-level (v2) and whole-book (v1) search across 60K+ books, 100K+ video segments, 200K+ live events. Coverage spans Manning, Packt, Pearson, Apress, Wiley, Microsoft Press, MIT Press, IBM Redbooks. Use as the practitioner-grade complement to academic research (arxiv/semantic-scholar) when the question is "how do people actually build/operate X" rather than "what's the SOTA".
MikkoParkkola/nab · ★ 4 · AI & Automation · score 83
Install: claude install-skill MikkoParkkola/nab
# O'Reilly Learning Platform Skill ## Decision tree ``` Q: "What's the canonical book on X?" → fulcrum:oreilly_books_search (v1) Q: "Find chapters/segments about X" → fulcrum:oreilly_search (v2) Q: "ISBN of <title>" → fulcrum:oreilly_books_search Q: "Latest 2025 books on rust async" → fulcrum:oreilly_search + sort=date Q: "Manning books on LLM systems" → fulcrum:oreilly_search + publishers Q: "Hands-on patterns for KV cache" → fulcrum:oreilly_search Q: "Compare academic vs practitioner view" → run alongside research skill ``` ## High-leverage workflows ### 1. Practitioner counterpart to academic research When `research` skill returns a SOTA paper, run a parallel `oreilly_search` for the same topic. The arxiv view tells us where the frontier is; the O'Reilly view tells us what's already in production books / vendor-shipped patterns. ``` research (arxiv + S2) → "what's novel?" oreilly_search (parallel) → "what's the deployed practice?" gap between them → moat opportunity ``` ### 2. ISBN/citation enrichment ```python gateway_execute("fulcrum:oreilly_books_search", { "query": "<title> <first-author-lastname>", "limit": 3 }) # returns ISBN-13 + canonical archive_id for citation graphs ``` ### 3. Topic landscape mapping ```python # Get format facets + topic facets in one call res = gateway_execute("fulcrum:oreilly_search", { "query": "kv cache attention", "limit": 10,