agentsclimarketplace

Python library review

Skill 2702207741-dev/agent-skills-pipeline/examples/external-repos/python-library/skills/python-library-review

Review changes to this Python library for API compatibility, behavioral regressions, missing tests, and release readiness.From its SKILL.md

Install
npx -y skills add 2702207741-dev/agent-skills-pipeline --skill python-library-review

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

2 things 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.
  • runs commandsInstructs the agent to run 1 command, including `python -m unittest discover -s tests -v`.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.3 KB, 228 tokens by cl100k_base, as published. Nobody here has run it

Python Library Review

Review changes to the sample library as a maintainer would review a pull request. Findings come before summaries and every approval names its evidence.

When to Use

  • A pull request changes public Python functions or their error behavior.
  • Tests, packaging metadata, or release notes change.
  • A maintainer needs an approve or request-changes recommendation.

Do not use this skill to author a feature from scratch or to publish a release.

Workflow

  1. Read the issue, diff, public functions, and nearby tests.
  2. Reproduce the reported behavior with the smallest safe command.
  3. Check compatibility, failure handling, boundary cases, and release impact.
  4. Run python -m unittest discover -s tests -v.
  5. Report findings by severity, then state approve or request changes.

Verification Checklist

  • The issue and affected public behavior are identified.
  • Success, failure, and boundary behavior are covered.
  • Tests pass without network access or credentials.
  • Release impact and rollback are stated.
  • The final recommendation is explicit.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. 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.