Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →liaohch3/push-release
Push to GitHub and optionally bump version to trigger PyPI release
Passed 18 of 22 test cases with the skill, and 13 of 22 without it.
and 5 more in the full report
6 fixed12 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
After updating version numbers and amending the local commit, what exact git command should be used to send the changes to the remote repository?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies git push origin main | Missed | Passed |
The instructions your model reads when the skill loads.
Push code to GitHub. If the pending commits contain feature changes, bump the version number so CI auto-publishes to PyPI.
Check working tree: Ensure no uncommitted changes (prompt user to commit first if dirty).
Determine whether a version bump is needed:
pyproject.tomlgit log origin/main..HEAD --oneline to inspect pending commitsIf bump is needed:
version field in pyproject.toml__version__ in claude_tap/__init__.pygit commit --amend to fold the version bump into the last commit (avoids extra commits)Push:
git push origin main
Confirm CI status:
The CI pipeline works as follows: push to main → auto-tag (only if version changed) → PyPI publish (triggered by new tag).
A version bump is the ONLY way to trigger a new PyPI release. If you push without bumping the version, CI will skip tagging and nothing gets published. So whenever commits include meaningful code changes (features, fixes, improvements), you MUST bump the version before pushing.
pyproject.toml and claude_tap/__init__.py must stay in synctest cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.