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.

2.27x

Quality

80%

Does it follow best practices?

Impact

100%

2.27x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with copy-paste commands tied to a real bundled script, but its workflow section omits the validation/feedback checkpoints that a repo-mutating batch operation like git bisect requires, capping workflow clarity. Conciseness is good but dampened by repeated scenario examples.

Suggestions

Add a validation checkpoint to the workflow: a first step to verify a clean working tree ('git status') and confirm the good/bad refs resolve before starting bisect, plus a feedback loop if bisect fails to start.

Tighten the Common Scenarios section by collapsing the three near-identical CLI blocks into one parameterized example, reducing token cost without losing coverage.

Trim the Test Command Guidelines section's restatement of exit-code semantics already implied by the Parameters section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no over-explanation of concepts Claude already knows, but the three Common Scenarios repeat the same CLI invocation pattern and the Test Command Guidelines reiterate exit-code semantics that were already stated, which could be tightened.	3 / 5
Actionability	Fully executable copy-paste bash commands referencing a real bundled script (scripts/git_bisect_runner.py), with concrete parameter docs and examples covering the common cases (pytest, npm, make, flaky tests).	5 / 5
Workflow Clarity	The three-step workflow is sequenced but lacks validation checkpoints for a destructive/batch operation that mutates repo state (git bisect start/bad/good, HEAD checkout, reset); per the rubric cap this cannot exceed 3 without an explicit verify/feedback step.	3 / 5
Progressive Disclosure	Well-organized into clear sections with the single bundled script clearly signaled via executable commands; not a 5 only because no one-level-deep references are used, which is appropriate here but leaves the structure one notch short of the 'clear overview with well-signaled references' anchor.	4 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit 'Use when' trigger guidance and concrete capabilities. It is slightly shy of perfect trigger-term coverage only because it omits some synonyms and the literal 'git bisect' keyword as a user phrase.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'performs git bisect', 'identify the first bad commit', 'Handles flaky tests with retry logic', 'provides comprehensive reports with bisect logs and confidence levels' — giving comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (performs git bisect to identify the first bad commit) and 'when' ('Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('debugging regressions', 'tracking down when a test started failing', 'identifying which commit broke functionality') but missing some synonyms and the literal term 'git bisect' as a user-spoken trigger, placing it just below the comprehensive-coverage anchor.	4 / 5
Distinctiveness Conflict Risk	Git bisect is a clear, distinct niche with specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/git-bisect-assistant/SKILL.md
Commit: 4f38503

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.