Embedding Generator

Embedding Generator is a skill for Claude Code, Codex from eddiebelaval/squire. It costs 17 tokens per session (1,448 once invoked), scanned A, original, MIT.

A guide for turning text into numerical representations that capture meaning, so similar text can be compared by software.

In plain words
What is it for?
Use it to create text-embedding pipelines for search, clustering, similarity matching, and classification, including model selection and quality checks.
Why use it?
It helps build semantic search and similarity features without treating different wording as completely unrelated. It also addresses choices around preparing, storing, and querying these representations.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/eddiebelaval/squire/embedding-generator
Any agent
npx skills add eddiebelaval/squire --skill embedding-generator
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

Made for: Claude Code, Codex.

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 Embedding Generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/eddiebelaval/squire/embedding-generator.svg)](https://agentmods.dev/skills/eddiebelaval/squire/embedding-generator)
Your own site
<a href="https://agentmods.dev/skills/eddiebelaval/squire/embedding-generator"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/embedding-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.01448
Opus 5 $0.00009 $0.00724
Sonnet 5 $0.00003 $0.00290
Haiku 4.5 $0.00002 $0.00145

Measured yesterday against content hash 7f29c17cb418, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Embedding Generator 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 yesterday.

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.

skills/embedding-generator/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Embedding Generator

The Embedding Generator skill helps you create, manage, and utilize text embeddings for semantic search, similarity matching, clustering, and classification tasks. It guides you through selecting appropriate embedding models, preprocessing text for optimal vectorization, and storing/querying embeddings efficiently.

Text embeddings transform words, sentences, or documents into dense numerical vectors that capture semantic meaning. Similar concepts end up close together in vector space, enabling powerful AI applications like semantic search, recommendations, and content understanding.

This skill covers everything from choosing the right model (OpenAI, Cohere, sentence-transformers, etc.) to implementing production-ready embedding pipelines with proper batching, caching, and quality validation.

Core Workflows

Workflow 1: Generate Embeddings for Text Corpus

  1. Analyze the text corpus:
    • Content type (documents, sentences, queries)
    • Average length and variation
    • Language(s) present
    • Domain specificity
  2. Select embedding model:
    • Consider dimensionality vs performance tradeoff
    • Match model to content type
    • Evaluate cost and latency constraints
  3. Preprocess text:
    • Clean and normalize
    • Chunk long documents appropriately
    • Handle special characters and formatting
  4. Generate embeddings with batching
  5. Validate quality with spot checks
  6. Store in appropriate vector database

Workflow 2: Choose Embedding Model

  1. Gather requirements:
    • Use case (search, clustering, classification)
    • Latency requirements
    • Cost constraints
    • Accuracy needs
  2. Compare models:
    Model Dims Speed Quality Cost
    OpenAI text-embedding-3-small 1536 Fast Good $$
    OpenAI text-embedding-3-large 3072 Fast Best $$$
    Cohere embed-english-v3 1024 Fast Great $$
    sentence-transformers 384-768 Varies Good Free
    Voyage AI 1024 Fast Great $$
  3. Benchmark on representative samples
  4. Document decision rationale

Read the full file on GitHub · 188 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. yesterday First seen · 188 lines · 17 tokens per session scan A 7f29c17cb418

Subscribe to this mod's changes

Embedding Generator is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 1,448 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.

Related

Other skills, from other repositories

Embedding Generator

Generate and manage text embeddings for semantic search, clustering, and similarity tasks.

jmsktm/claude-settings · 17 tokens

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Orchestra-Research/AI-Research-SKILLs · 46 tokens

vector-database-management

Comprehensive guide for managing vector databases including Pinecone, Weaviate, and Chroma for semantic search, RAG systems, and similarity-based applications.

manutej/luxor-claude-marketplace · 35 tokens

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…

davila7/claude-code-templates · 63 tokens

qdrant-scaling-query-volume

Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.

qdrant/skills · 56 tokens

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

davila7/claude-code-templates · 46 tokens