agentsclimarketplace

Hf release prep

Skill maximussthegreat/ml-researcher-os/skills/hf-release-prep

Agent skills and workflows for reproducible ML research.

Install
npx -y skills add maximussthegreat/ml-researcher-os --skill hf-release-prep

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when preparing Hugging Face model cards, dataset cards, Space demos, or release notes for ML artifacts.

SKILL.md

1.0 KB, as published. Nobody here has run it

Hugging Face Release Prep

Use this skill when a project is ready to publish an ML artifact.

Goal

Prepare a release that is useful, reproducible, licensed clearly, and explicit about limitations.

Release types

Support:

  • model repo
  • dataset repo
  • Space demo
  • paper reproduction artifact

Required output

Produce a release checklist with:

  1. Artifact type
  2. Intended users
  3. Required files
  4. Model or dataset card fields
  5. Evaluation summary
  6. Limitations
  7. License and data rights
  8. Safety or misuse notes
  9. Reproduction command
  10. Demo script

Card rules

  • State training data source clearly.
  • State evaluation setup clearly.
  • Include known failure modes.
  • Include intended and out-of-scope uses.
  • Do not imply clinical, legal, or production suitability without evidence.

Final check

End with:

Ready to publish: yes/no
Blocking issues:
- ...

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.