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
82%
Does it follow best practices?
Impact
100%
2.27xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (git bisect automation, flaky test handling, comprehensive reporting), provides explicit trigger guidance with natural user language, and occupies a distinct niche. The description uses proper third-person voice and balances conciseness with completeness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific 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'. | 3 / 3 |
Completeness | Clearly answers both what ('performs git bisect to identify the first bad commit', 'handles flaky tests', 'provides reports') AND when ('Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'git bisect', 'debugging regressions', 'test started failing', 'commit broke functionality', 'bad commit', 'bug'. These cover common variations of how users describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on git bisect operations with distinct triggers like 'bisect', 'regression', 'which commit broke'. Unlikely to conflict with general git skills or debugging tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable guidance for running git bisect with good concrete examples and parameter documentation. However, it lacks validation checkpoints in the workflow (e.g., verifying the identified commit actually causes the failure), and could be more concise by removing obvious tips and consolidating redundant information about exit codes.
Suggestions
Add explicit validation step after bisect completes: 'Verify the identified commit by checking out the commit before and after to confirm the behavior change'
Remove redundant/obvious content like 'use focused tests rather than full test suites for faster bisect' and the repeated exit code explanations
Add a feedback loop for when bisect results seem incorrect (e.g., 'If the identified commit doesn't seem related to the bug, consider: test command may have false positives, try increasing retries')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - the 'Test Command Guidelines' section repeats exit code information already implied, and the 'Tips' section contains some obvious advice Claude would know (like 'use focused tests for faster bisect'). | 2 / 3 |
Actionability | Provides fully executable commands with concrete examples for multiple scenarios. All code snippets are copy-paste ready with real parameter values and clear expected behaviors. | 3 / 3 |
Workflow Clarity | The workflow section lists steps but lacks explicit validation checkpoints. There's no guidance on verifying the bisect results are correct, no feedback loop for when results seem wrong, and no validation step before acting on the identified bad commit. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the document is somewhat long (~150 lines) with all content inline. The troubleshooting and tips sections could be separate files, and there are no references to external documentation for advanced usage. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ArabelaTso/Skills-4-SE
- Commit
0f00a4f
- Reviewed
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.