CtrlK
BlogDocsLog inGet started
Tessl Logo

git-bisect-assistant

Automatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and confidence levels.

88

2.27x
Quality

82%

Does it follow best practices?

Impact

100%

2.27x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

28%

Regression Hunt: Statistics Library

Script usage and report generation

Criteria
Without context
With context

Uses bisect script

0%

100%

Uses --good parameter

0%

100%

Test command exit code convention

70%

100%

Focused test command

100%

100%

Report saved to file

100%

100%

Report: First Bad Commit

100%

100%

Report: Confidence Level

100%

100%

Report: Tested Commits

100%

100%

Report: Bisect Log

100%

100%

Correct bad commit identified

100%

100%

100%

90%

Intermittent Test Failure: Find the Culprit Commit

Flaky test retry configuration

Criteria
Without context
With context

Uses bisect script

0%

100%

Uses --retries flag

0%

100%

Retries value 3–5

0%

100%

Report: High confidence

0%

100%

Report: Assumptions mentions retries

0%

100%

Report saved to file

100%

100%

100%

50%

Build Regression: CLI Tool Stopped Compiling

Build step and timeout usage

Criteria
Without context
With context

Uses bisect script

0%

100%

Uses --timeout flag

0%

100%

Timeout value is reasonable

50%

100%

Test command includes build step

100%

100%

Uses --bad for non-HEAD revision

100%

100%

Uses --repo flag

0%

100%

Report: Assumptions with timeout

100%

100%

Report saved to file

100%

100%

Repository
ArabelaTso/Skills-4-SE
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.