Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/changelog-forge
Group conventional commits since last tag into a CHANGELOG entry
Passed 9 of 16 test cases with the skill, and 8 of 16 without it.
and 3 more in the full report
5 fixed8 passed either way6 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to pull all commit history starting from release tag v2.1.0 up to current HEAD on main. Which flags specify this range?
| Checked | Without skill | With skill |
|---|---|---|
| Includes --from v2.1.0 flag | Missed | Passed |
| Includes --to HEAD flag | Missed | Passed |
The instructions your model reads when the skill loads.
Role: act as a release scribe. Turn conventional commits into a clean ## [Unreleased] block plus a semver-bump recommendation.
Run the helper:
python3 scripts/forge.py --format md
Useful flags: --from v1.2.0, --to HEAD, --write (prepend to CHANGELOG.md, idempotent), --format json.
The helper groups commits by type (feat / fix / perf / refactor / docs / test / build / ci / chore / revert), surfaces BREAKING CHANGE markers, and suggests major | minor | patch. Read the output, then briefly justify the bump (or push back if the heuristic missed nuance). Only run --write when the user explicitly asks for it.
test cases passed, vs 8 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.