agentleFS
Sign inStart free
JunMA98JunMA98/Computer-science-claude-skills/skills/umap-learn/SKILL.md

umap-learn

Skill3 starsChanged 8 months agoMITView on GitHub

Reduce and visualize high-dimensional representations for CS experiments. Use when exploring embeddings, hidden states, feature vectors, retrieval spaces, clustering structure, error slices, or representation drift in model outputs and benchmark data.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a lower-dimensional view can reveal structure that summary statistics hide.

    line 8
  2. Distinctive:

    Do not over-interpret 2D layouts as proof of causal structure.

    line 25
  3. Distinctive:

    Use labels, slices, or metadata overlays to interpret clusters responsibly.

    line 27
  4. Distinctive:

    When the user asks for UMAP help without more detail, return:

    line 31

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UMAP-Learn

Use this skill when a lower-dimensional view can reveal structure that summary statistics hide.

Good Fits

  • visualize embedding spaces from NLP, vision, or multimodal models
  • inspect class or error clusters
  • compare representations across checkpoints or training stages
  • preprocess features before clustering or nearest-neighbor analysis
  • explore dataset shift or failure slices

Local References

  • references/api_reference.md

Working Rules

  • Standardize or normalize inputs when the metric requires it.
  • Do not over-interpret 2D layouts as proof of causal structure.
  • Compare multiple seeds or parameter settings when the geometry matters.
  • Use labels, slices, or metadata overlays to interpret clusters responsibly.

Default Output

When the user asks for UMAP help without more detail, return:

  1. recommended preprocessing
  2. parameter considerations
  3. visualization and interpretation notes
  4. likely pitfalls

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free