semantic_search

semantic_search is a skill for Claude Code from sandraschi/calibremcp. It costs 0 tokens per session (599 once invoked), scanned A, original, MIT.

A meaning-based search tool for a Calibre ebook library. It searches book details such as titles, authors, tags, notes, and series, and can also search the text inside ebooks when that content has been indexed.

In plain words
What is it for?
Finding books about a subject, locating books similar to a known title, searching by theme or author, and filtering results by metadata.
Why use it?
It helps you find books by describing an idea or topic instead of remembering exact words from a title or description.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the calibre-mcp plugin — 6 skills shipped together

Good fit Finding books about a subject, locating books similar to a known title, searching by theme or author, and filtering results by metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/calibremcp/semantic_search
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sandraschi/calibremcp --skill semantic_search
Clone the repo
git clone --depth 1 https://github.com/sandraschi/calibremcp

Made for: Claude Code.

Or install calibre-mcp, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for semantic_search

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/calibremcp/semantic_search/github.svg)](https://agentmods.dev/skills/sandraschi/calibremcp/semantic_search)
Your own site
<a href="https://agentmods.dev/skills/sandraschi/calibremcp/semantic_search"><img src="https://agentmods.dev/badge/skills/sandraschi/calibremcp/semantic_search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for semantic_search

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandraschi/calibremcp/semantic_search"><img src="https://agentmods.dev/badge/skills/sandraschi/calibremcp/semantic_search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00599
Opus 5 $0.00000 $0.00300
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured 9d ago against content hash 9249bd9f8a2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

semantic_search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/semantic_search/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Search (Metadata RAG)

Description: Find books by meaning using LanceDB over title, authors, tags, comments, and series. Supports hybrid keyword + vector search across your entire Calibre library.

Trigger Phrases

  • "Find books about [topic]"
  • "Search my library for [query]"
  • "What do I have on [subject]?"
  • "Show me books similar to [title]"
  • "Find [author] books about [theme]"

Tools

  • calibre_metadata_index_build() — Build or rebuild the LanceDB metadata index. Run once per library or after large batch imports.
  • calibre_metadata_search(query="...", top_k=10) — Natural-language semantic search over book metadata. Returns ranked results with relevance scores.
  • rag_index_build() — Build full-text content index from ebook text (requires epub/mobi extraction).
  • rag_retrieve(query="...", top_k=5) — Semantic search over full book contents, not just metadata.
  • search_fulltext(query="...") — Legacy full-text search with exact phrase matching and boolean operators.
  • query_books(search="...", tags=[...], authors=[...]) — Structured metadata filtering with AND/OR logic.

Workflow

  1. Index check: If no index exists, call calibre_metadata_index_build() first (runs async, takes 1-5 min per 1000 books).
  2. Metadata search: Use calibre_metadata_search() for broad semantic queries. Combine with top_k to control result breadth.
  3. Filter refinement: Narrow results by chaining with query_books() using author, tag, or series filters.
  4. Deep content search: For research-style queries, call rag_retrieve() to search inside book text. Caveat: works best on epub format.
  5. Result presentation: Return title, author, relevance score, and match highlights. Include calibre book_id for follow-up actions (open, metadata edit, export).

Search Operators

  • Phrase match: Use quotes in search_fulltext"machine learning"
  • Boolean: search_fulltext(query="python AND (data science OR ML)")
  • Tag filter: query_books(tags=["python", "tutorial"], limit=20)
  • Date range: query_books(added_since="2024-01-01")

Read the full file on GitHub · 42 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 42 lines · 0 tokens per session scan A 9249bd9f8a2d

Subscribe to this mod's changes

semantic_search is a skill published in the GitHub repository sandraschi/calibremcp (42 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 599 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

write-oql-queries

Write OQL for Mendix VIEW entities — joins, aggregates, calculated fields, and the syntax the runtime actually accepts. Use when creating a VIEW entity or building a report or analytics query.

mendixlabs/mxcli · 44 tokens

database-connections

Connect a Mendix app to an external database over JDBC with the External Database Connector, and define the queries microflows run against it. Use when the app must read or write Oracle, PostgreSQL, MySQL or SQL Server directly from a microflow.

mendixlabs/mxcli · 55 tokens

demo-data

Seed a Mendix app's PostgreSQL database directly, bypassing the runtime — Mendix's internal ID system, association storage, and bulk import from an external database. Use when populating test or demo data, when data is needed before the UI exists, or for imports too large for the runtime.

mendixlabs/mxcli · 66 tokens

connect-rapidminer-graph

Fetch data from a RapidMiner graph mart or any SPARQL 1.1 HTTP endpoint (AnzoGraph and friends) and surface it as Mendix entities. Use when a graph database with a SPARQL endpoint has to feed a Mendix app read-only.

mendixlabs/mxcli · 62 tokens

mendix-odata-pushdown

Push OData query options into the SQL of a Mendix resource served by a read microflow, so $filter, $orderby, $top, $skip, $count and the key lookup reach the database instead of being silently dropped. Use when publishing an OData resource over data Mendix has no table for — a warehouse view, a legacy database, a…

mendixlabs/mxcli · 117 tokens

generate-domain-model

Generate a complete Mendix domain model in MDL — entities, attributes, associations, enumerations — and validate it. Use when asked for a domain model for a business area (e-commerce, HR, CRM, …) rather than a single entity.

mendixlabs/mxcli · 55 tokens