agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/python-ml/SKILL.md

python-ml

Skill2 starsChanged 31 days agoMITView on GitHub

Implements Python services, data processing, model training/eval, and reproducible ML experiment workflows

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Keep training, evaluation, and inference entrypoints explicit and documented.

    line 21
  2. Distinctive:

    Add unit tests for transforms/metrics and smoke tests for training/inference when feasible.

    line 26
  3. Distinctive:

    Do not commit secrets, raw PII datasets, or production model credentials

    line 31
  4. Distinctive:

    Do not silently change evaluation metrics or baselines to force a “win”

    line 32
  5. Distinctive:

    Do not run expensive cloud training without Captain approval and a budget

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Python and Machine Learning

Use this Skill when

Working on Python services, data pipelines, model training/evaluation, inference, experiment logging, dataset contracts, or ML reproducibility requirements.

Inputs

  • Approved IMPLEMENTATION_PLAN.md
  • Existing Python package layout, dependency manager (pip/poetry/uv), and test runner
  • Dataset and experiment constraints from PROJECT_CONTEXT.md

Procedure

  1. Match existing project packaging and lint/test tooling.
  2. Keep training, evaluation, and inference entrypoints explicit and documented.
  3. Pin or lock dependencies according to project convention; record versions in evidence when relevant.
  4. Separate raw data, processed data, and model artifacts; do not commit large datasets or weights by default.
  5. Define dataset contracts (schema, split, labels) before changing training code.
  6. Log experiment configuration (seed, hyperparams, data revision) for reproducibility.
  7. Add unit tests for transforms/metrics and smoke tests for training/inference when feasible.
  8. Record commands, metrics, and artifact locations under .agent/evidence/.

Prohibited actions

  • Do not commit secrets, raw PII datasets, or production model credentials
  • Do not silently change evaluation metrics or baselines to force a “win”
  • Do not run expensive cloud training without Captain approval and a budget

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