embedding-anisotropy-check SKILL.md skillA
embedding-anisotropy-check from github/awesome-copilot is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add github/awesome-copilot/embedding-anisotropy-check@git:20261029.7bf142ePins git:20261029.7bf142e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- github/awesome-copilot
- Path
skills/embedding-anisotropy-check/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261029.7bf142e, committed Oct 29, 2026
- First version recorded
- Sep 29, 2026
- Size
- 7,348 bytes
- Repository stars
- 40,941
- License
- MIT
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…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Embedding anisotropy check Raw cosine between embeddings is rarely centred on zero. Most sentence encoders and most hidden-state layers place every vector near one shared direction, so two unrelated inputs can score 0.6, 0.9 or 0.99. A matched pair at 0.9 is then not evidence of anything by itself, and a gap of 0.01 between two conditions can be the whole signal or none of it. This skill makes every such comparison carry its own floor. ## How an agent reaches this skill The agent does not vectorise anything here. The skill applies at the point where the agent is about to report a cosine number, whoever produced the vectors: - **The agent wrote the evaluation.** A request such as "write a retrieval eval for our index" or "check that the 4-bit export of this encoder still matches bf16" ends in a script that prints a mean cosine. Before the agent says "0.91, the export is fine", it runs the same model's unrelated pairs through the script and reports the floor beside the matched figure. - **The vectors already exist in the workspace.** An `embeddings.npy`, a probe or adapter evaluated on saved hidden …
Read the whole file at its exact version.
How to install
mdr add github/awesome-copilot/embedding-anisotropy-check@sha256:c763f4bb1c239861The line at the top of this page pins the label git:20261029.7bf142e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lbozdcdvqpncv7ki)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 29, 2026 and Oct 29, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261029.7bf142e latest | 2026-10-29 | 7bf142e | 7,348 B | A | view · diff |
| git:20261013.789d196 | 2026-10-13 | 789d196 | 6,921 B | A | view · diff |
| git:20260929.7ced8bc | 2026-09-29 | 7ced8bc | 5,737 B | A | view · diff |
| git:20260929.fe58182 | 2026-09-29 | fe58182 | 5,131 B | A | view · diff |
| git:20260929.ac611c5 | 2026-09-29 | ac611c5 | 5,014 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7348 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
github/awesome-copilot · 40,941 stars · license MIT · pushed 2026-11-09 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lbozdcdvqpncv7ki GET https://markdownregistry.com/api/v1/resolve?ref=github/awesome-copilot/embedding-anisotropy-check GET https://markdownregistry.com/api/v1/blob/c763f4bb1c239861b5707ada9e137a9f4c3be97e8fd03e071d554a4f9e7fa77c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.