# Embedding anisotropy check

> Embedding anisotropy check is an open-source agent skill for knowledge and memory. Use before reporting any cosine similarity computed over embeddings or transformer hidden states, whether the agent computed the vectors or. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/github/awesome-copilot/tree/main/skills/embedding-anisotropy-check
- **Repository:** https://github.com/github/awesome-copilot
- **GitHub stars:** 41,254
- **License:** MIT
- **Skill name:** embedding-anisotropy-check
- **Collection:** https://github.com/github/awesome-copilot
- **Categories:** knowledge and memory
- **Listing updated:** 2026-11-17

## About

Use before reporting any cosine similarity computed over embeddings or transformer hidden states, whether the agent computed the vectors or loaded them. Measures the anisotropy of each side, centres by the population mean, and scores matched pairs against a permuted floor taken from the same comparison. Use when comparing one model's embeddings across precisions, runtimes or layers, when evaluating retrieval, probes or adapters, or before calling a similarity high, two conditions in agreement, or a small gap a null.

## When your agent uses it

> Use before reporting any cosine similarity computed over embeddings or transformer hidden states, whether the agent computed the vectors or loaded them. Measures the anisotropy of each side, centres by the population mean, and scores matched pairs against a permuted floor taken from the same comparison. Use when comparing one model's embeddings across precisions, runtimes or layers, when evaluating retrieval, probes or adapters, or before calling a similarity high, two conditions in agreement, or a small gap a null.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs Python scripts](https://github.com/github/awesome-copilot/tree/HEAD/skills/embedding-anisotropy-check)
- [No network calls found in its scripts](https://github.com/github/awesome-copilot/tree/HEAD/skills/embedding-anisotropy-check)
- [License: MIT](https://github.com/github/awesome-copilot/tree/HEAD/skills/embedding-anisotropy-check)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/embedding-anisotropy-check` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/embedding-anisotropy-check &&
cp -R "$tmp/skills/embedding-anisotropy-check" ~/.claude/skills/embedding-anisotropy-check &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/embedding-anisotropy-check` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/embedding-anisotropy-check` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/embedding-anisotropy-check &&
cp -R "$tmp/skills/embedding-anisotropy-check" ~/.agents/skills/embedding-anisotropy-check &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/embedding-anisotropy-check` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/embedding-anisotropy-check` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/embedding-anisotropy-check &&
cp -R "$tmp/skills/embedding-anisotropy-check" ~/.cursor/skills/embedding-anisotropy-check &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/embedding-anisotropy-check` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/github/awesome-copilot.git --path skills/embedding-anisotropy-check
```

Or copy the folder to `~/.gemini/skills/embedding-anisotropy-check` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/embedding-anisotropy-check`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/embedding-anisotropy-check &&
cp -R "$tmp/skills/embedding-anisotropy-check" ~/.copilot/skills/embedding-anisotropy-check &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/embedding-anisotropy-check` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/github/awesome-copilot.git
```

Then copy `awesome-copilot/skills/embedding-anisotropy-check` into your agent's skills folder as `embedding-anisotropy-check`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Embedding anisotropy check in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/embedding-anisotropy-check to use it in all your projects, or to .claude/skills/embedding-anisotropy-check in one project.

### Does Embedding anisotropy check run scripts?

Yes. It runs Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Embedding anisotropy check?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Embedding anisotropy check?

The closest alternatives to Embedding anisotropy check are Claude API, Qdrant vertical scaling, Pinecone rag, Qdrant horizontal scaling and Qdrant scaling query volume.

## Alternatives

- [Claude API](https://ai-powered.com/skills/claude-api): Claude API is an agent skill for ai models and llm tooling.
- [Qdrant vertical scaling](https://ai-powered.com/skills/qdrant-vertical-scaling): Qdrant vertical scaling is an open-source agent skill for knowledge and memory.
- [Pinecone rag](https://ai-powered.com/skills/pinecone-rag): Pinecone rag is an open-source agent skill for knowledge and memory.
- [Qdrant horizontal scaling](https://ai-powered.com/skills/qdrant-horizontal-scaling): Qdrant horizontal scaling is an open-source agent skill for knowledge and memory.
- [Qdrant scaling query volume](https://ai-powered.com/skills/qdrant-scaling-query-volume): Qdrant scaling query volume is an open-source agent skill for knowledge and memory.
- [Qdrant search quality diagnosis](https://ai-powered.com/skills/qdrant-search-quality-diagnosis): Qdrant search quality diagnosis is an open-source agent skill for knowledge and memory.
- [Qdrant monitoring setup](https://ai-powered.com/skills/qdrant-monitoring-setup): Qdrant monitoring setup is an open-source agent skill for knowledge and memory.
- [Qdrant deployment options](https://ai-powered.com/skills/qdrant-deployment-options): Qdrant deployment options is an open-source agent skill for knowledge and memory.

---
Source: https://ai-powered.com/skills/embedding-anisotropy-check
