Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →arabelatso/szz-bug-introducing-commit-identifier
Identifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame information.
Passed 17 of 19 test cases with the skill, and 10 of 19 without it.
and 7 more in the full report
8 fixed12 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
If I execute `python scripts/szz_analyzer.py 4b2a10` without providing the `--top` flag, how many top candidate commits will the script display by default?
| Checked | Without skill | With skill |
|---|---|---|
| States that the default top candidate count is 10 | Missed | Passed |
The instructions your model reads when the skill loads.
This skill performs SZZ (Śliwerski-Zimmermann-Zeller) algorithm analysis to identify bug-introducing commits in git repositories. Given a bug-fixing commit, it traces modified lines back through version history using git blame to find candidate commits that originally introduced the buggy code.
Start by identifying the commit that fixes the bug. This can be obtained from:
Use the provided script to perform the analysis:
python scripts/szz_analyzer.py <fix-commit-hash>
Options:
--repo <path>: Specify repository path (default: current directory)--json: Output results in JSON format for programmatic processing--top <n>: Number of top candidates to show (default: 10)Example:
python scripts/szz_analyzer.py abc123def --repo /path/to/repo --top 5
The script outputs a ranked list of candidate bug-introducing commits with:
test cases passed, vs 10 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.