tracking-regression-tests
This skill enables Claude to track and run regression tests, ensuring new changes don't break existing functionality. It is triggered when the user asks to "track regression", "run regression tests", or uses the shortcut "reg". The skill helps in maintaining code stability by identifying critical tests, automating their execution, and analyzing the impact of changes. It also provides insights into test history and identifies flaky tests. The skill uses the `regression-test-tracker` plugin.
86
53%
Does it follow best practices?
Impact
92%
1.41xAverage score across 9 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/testing/regression-test-tracker/skills/regression-test-tracker/SKILL.mdQuality
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 a strong skill description that clearly communicates what the skill does (tracks and runs regression tests, identifies flaky tests, analyzes change impact) and when to use it (explicit trigger terms including a shortcut). The description is specific, includes natural trigger terms, and occupies a distinct niche. Minor improvement could be made by using more concise phrasing and avoiding slightly fluffy language like 'maintaining code stability'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: tracking regression tests, running them, identifying critical tests, automating execution, analyzing impact of changes, providing test history insights, and identifying flaky tests. | 3 / 3 |
Completeness | Clearly answers both 'what' (track and run regression tests, identify critical tests, analyze impact, identify flaky tests) and 'when' (explicitly states triggers: 'track regression', 'run regression tests', or 'reg' shortcut). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'track regression', 'run regression tests', 'reg' shortcut, plus contextual terms like 'flaky tests', 'test history', and 'regression'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around regression testing specifically, with distinct triggers ('regression', 'reg') and mentions a specific plugin ('regression-test-tracker'). Unlikely to conflict with general testing or code quality skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely descriptive rather than instructive. It explains what regression testing is and why it matters—things Claude already knows—while failing to provide any concrete commands, tool invocations, code examples, or plugin-specific details that would make it actionable. The referenced `regression-test-tracker` plugin is never shown in use.
Suggestions
Replace abstract descriptions with concrete, executable commands showing how to invoke the `regression-test-tracker` plugin (e.g., exact CLI syntax for marking tests, running the suite, and viewing results).
Remove the 'Overview', 'Best Practices', and 'Integration' sections—they explain concepts Claude already knows and add no actionable value.
Add a concrete example with actual input and expected output (e.g., sample terminal output from running the regression suite, including how failures and flaky tests are reported).
Include validation/error-handling steps in the workflow, such as what to do when tests fail, how to identify flaky tests from the tool's output, and how to re-run specific failed tests.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows (what regression tests are, why they matter, what software quality means). The 'Overview', 'When to Use', 'Best Practices', and 'Integration' sections are almost entirely filler that adds no actionable information. | 1 / 3 |
Actionability | There are no concrete commands, executable code, or specific tool invocations. The skill references a `regression-test-tracker` plugin but never shows how to invoke it. Examples describe what the skill 'will do' in abstract terms rather than providing actual commands or expected outputs. | 1 / 3 |
Workflow Clarity | The multi-step processes described ('Identify', 'Execute', 'Analyze') are vague and lack specific commands, validation checkpoints, or error recovery steps. There is no concrete sequence Claude could follow to actually perform regression testing. | 1 / 3 |
Progressive Disclosure | The content is organized into sections with headers, which provides some structure. However, there are no references to external files, no bundle files exist, and content that could be split (e.g., detailed plugin API usage) is neither inline nor referenced—it's simply absent. | 2 / 3 |
Total | 5 / 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.
- Commit
13d35b8
- 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.