agentleFS
Sign inStart free
sandraschisandraschi/calibremcp/skills/agentic_workflow/SKILL.md

agentic_workflow

Skill50 starsChanged 23 days agoMITView on GitHub

Description: Chain multiple CalibreMCP tools in one flow for discovery, search, and action. Supports FastMCP 3.1 sampling for autonomous multi-step ebook processing, batch operations, and import pipelines. For import workflows: managelibraries(operation="list") → managelibraries(operation="switch", libraryname="import") → querybooks(sort="timestamp", limit=50) for newly added → manageanalysis(operation="health") to check quality → managemetadata fixes for any issues → tag normalized batch. "Open a random unread science fiction book." → managelibraries(operation="switch", libraryname="main") → querybooks(tags=["sci-fi"], unread=True, sort="random", limit=1) → extract bookid → manageviewer(operation="open", bookid=...).

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Analyze: Run manage_analysis() to detect duplicates, health issues, or reading patterns before taking action.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agentic Workflow

Description: Chain multiple CalibreMCP tools in one flow for discovery, search, and action. Supports FastMCP 3.1 sampling for autonomous multi-step ebook processing, batch operations, and import pipelines.

Trigger Phrases

  • "Automate [task] across my library"
  • "Batch process all new books"
  • "Set up an import pipeline for [folder]"
  • "Find and fix [issue] in my library"
  • "Process my Calibre library automatically"

Tools

  • manage_libraries(operation="list") — List available Calibre libraries.
  • manage_libraries(operation="switch", library_name="...") — Switch active library context.
  • query_books(search="...", tags=[...], authors=[...], sort="...", unread=True/False) — Structured book queries.
  • calibre_metadata_search(query="...", top_k=10) — Semantic metadata search.
  • search_fulltext(query="...") — Full-text content search.
  • manage_viewer(operation="open", book_id=...) — Open book in Calibre viewer.
  • manage_metadata(operation="show"/"update", book_id=...) — Read or modify book metadata.
  • manage_tags(operation="add"/"remove", book_id=..., tags=[...]) — Tag management.
  • manage_analysis(operation="duplicates"/"health"/"reading_stats") — Library analysis tools.

Workflow

  1. Discover: manage_libraries(operation="list") to identify the active library. Switch via manage_libraries(operation="switch", library_name="...") if multi-library setup.
  2. Search: Combine query_books with calibre_metadata_search or search_fulltext depending on intent. Use conversational returns (each tool returns success, message, data dict) to decide next step.
  3. Analyze: Run manage_analysis() to detect duplicates, health issues, or reading patterns before taking action.
  4. Act: Apply changes via manage_metadata, manage_tags, or bulk operations. For books to read, chain manage_viewer(operation="open") as final step.
  5. Verify: Optionally re-run analysis to confirm changes took effect.

Batch Pipeline Pattern

For import workflows: manage_libraries(operation="list") → manage_libraries(operation="switch", library_name="import") → query_books(sort="timestamp", limit=50) for newly added → manage_analysis(operation="health") to check quality → manage_metadata fixes for any issues → tag normalized batch.

Example

"Open a random unread science fiction book." → manage_libraries(operation="switch", library_name="main") → query_books(tags=["sci-fi"], unread=True, sort="random", limit=1) → extract book_id → manage_viewer(operation="open", book_id=...).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free