Menu

Individual skill

embeddings-guide

Work with text embeddings — choosing models, pooling, similarity measures, evaluation, and multilingual considerations. Use when building semantic search, clustering, or any similarity-based feature.

skills/embeddings-guide/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
53
Repository last updated
Oct 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Embeddings Guide

Embeddings turn text into vectors where similarity means relatedness. They're the foundation of 
semantic search, RAG retrieval, clustering, and recommendations. The skill is choosing the right 
model, using it correctly, and evaluating on your data.

## Overview

An embedding model maps text to a dense vector; cosine similarity (usually) measures relatedness. 
Quality varies by domain, language, and text length — a model great at English Wikipedia may fail 
on your support tickets. Key choices: the model itself, how you handle long texts (chunk + pool), 
whether to use task-specific instructions (asymmetric search: query vs. document phrasing differs), 
and how you evaluate (on your data, not the leaderboard).