npx skills add majiayu000/claude-skill-registry --skill embedding-models --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Provides a comprehensive guide to text embedding models and usage, including concepts, multiple model implementations, and basic utilities for comparison and selection.
How it works
Describes embedding concepts (dense vectors, semantic similarity, dimensionality, distance metrics) and provides concrete code sections for:
- OpenAI embeddings: class with embed_text, embed_texts, get_embedding_dimension
- Sentence Transformers: class with embed_text, embed_texts, embed_documents, compute_similarity
- Cohere embeddings: class with embed_text, embed_texts, embed_documents
- BGE models: class with embed_text, embed_query, embed_documents, compute_scores Additionally, it offers model selection utilities:
- EmbeddingModelComparison with get_model_recommendation and compare_models
- EmbeddingModelSelector with select_model and get_model_config And a grouping of sections for embedding generation, including batch processing (code snippet truncated in the provided view).
When to use it
Use when evaluating embedding options for natural language tasks, needing side‑by‑side model comparisons, or selecting a model based on use-case, budget, and performance priorities.
What it can touch
This skill references the following tools and inputs within its code examples: OpenAI API (class OpenAIEmbeddings), SentenceTransformer (class SentenceTransformerEmbeddings), Cohere API (class CohereEmbeddings), and model name/batch configurations.
Caveats
License declared: MIT. The skill provides example code with placeholders (e.g., api_key strings) and illustrative usage; actual API access and environment setup are not provided. No guarantees of runtime success are stated.
# Embedding Models ## Overview Comprehensive guide for text embedding models and usage. --- ## 1. Embedding Concepts ### 1.1 What are Embeddings? ```python """ Embeddings are dense vector representations of text that capture semantic meaning. Key Concepts: - Dense vectors: Fixed-size numerical representations - Semantic similarity: Similar meanings have similar vectors - Dimensionality: Number of dimensions in the vector - Distance metrics: Cosine similarity, Euclidean distance Example: "cat" -> [0.2, -0.5, 0.8, ...] # 384-dim vector "dog" -> [0.3, -0.4, 0.7, ...] # 384-dim vector The vectors for "cat" and "dog" are similar because they're both animals. """ class EmbeddingConcepts: """Understanding embedding concepts.""" @staticmethod def explain_embeddings(): """Explain embedding concepts.""" return { "dense_vectors": "Fixed-size numerical representations of text", "semantic_similarity": "Similar meanings have similar vectors", "dimensionality": "Number of dimensions in the vector", "distance_metrics": "Cosine similarity, Euclidean distance" } @staticmethod def compare_distance_metrics(): """Compare different distance metrics.""" import numpy as np # Example vectors vec1 = np.arra
- Overview
- 1. Embedding Concepts
- 1.1 What are Embeddings?
- 2. Popular Models
- 2.1 OpenAI Embeddings
- 2.2 Sentence Transformers
- 2.3 Cohere Embeddings
- 2.4 BGE Models
- 3. Model Selection Criteria
- 3.1 Model Comparison
- 3.2 Selection Decision Tree
- 4. Embedding Generation
- 4.1 Batch Processing
- 4.2 Caching
What does the embedding-models skill do?
Comprehensive guide for text embedding models and usage.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill embedding-models --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.