Agent skill · AI & Agents

embedding-strategy-skill

PROTECTED: Manage chunking strategies and embedding dimensions. Changes require user approval + full impact analysis.'

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill embedding-strategy-skill --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/ai-ml/embedding-strategy-skill/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: embedding-strategy version: 1.0 last_updated: 2025-12-04 description: PROTECTED - Chunking strategy and embedding dimension management license: MIT priority: critical triggers: - "chunking", "embedding", "dimension", "overlap", "splitting" dependencies: - docs/protected-schemas.md - templates/rag-checklist.md --- # 📐 Embedding Strategy SKILL ## Purpose **PROTECTED:** Manage chunking strategies and embedding dimensions. Changes require user approval + full impact analysis. --- ## Chunking Strategies ### 1. RecursiveCharacterTextSplitter (Recommended) ```python from langchain.text_splitter import RecursiveCharacterTextSplitter splitter = RecursiveCharacterTextSplitter( chunk_size=512, # PROTECTED chunk_overlap=50, # PROTECTED separators=["\n\n", "\n", " ", ""], length_function=len ) chunks = splitter.split_text(document) ``` **When to use:** General purpose (paragraphs, sentences) **Chunk Size Guidelines:** - **256 tokens:** Very focused Q&A - **512 tokens:** Balanced (recommended for most cases) - **1024 tokens:** Broad context (summarization) - **2048 tokens:** Document understanding --- ### 2. TokenTextSplitter ```python from langchain.text_splitter import TokenTextSpli

What's inside
Steps it walks through
  1. Purpose
  2. Chunking Strategies
  3. 1. RecursiveCharacterTextSplitter (Recommended)
  4. 2. TokenTextSplitter
  5. 3. MarkdownTextSplitter
  6. Chunk Overlap Strategy
  7. Why Overlap Matters
  8. Overlap Guidelines
  9. Embedding Dimensions (PROTECTED)
  10. Common Models
  11. Protection Rule
  12. Chunk Size Optimization
  13. A/B Testing
  14. Pre-Processing Best Practices
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the embedding-strategy-skill skill do?

PROTECTED: Manage chunking strategies and embedding dimensions. Changes require user approval + full impact analysis.'

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill embedding-strategy-skill --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.

Keep going