running-mutation-tests
This skill enables Claude to validate test suite quality by performing mutation testing. It is triggered when the user asks to run mutation tests, analyze test effectiveness, or improve test coverage. The skill introduces code mutations, runs tests against the mutated code, and reports on the "survival rate" of the mutations, indicating the effectiveness of the test suite. Use this skill when the user requests to assess the quality of their tests using mutation testing techniques. Specific trigger terms include "mutation testing", "test effectiveness", "mutation score", and "surviving mutants".
63
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/testing/mutation-test-runner/skills/mutation-test-runner/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 well-crafted skill description that clearly defines its purpose, lists concrete actions, provides explicit trigger guidance, and occupies a distinct niche. It covers both the 'what' and 'when' thoroughly, with natural trigger terms that users would actually say. The only minor note is slight redundancy between the opening sentence and the 'Use this skill when' clause, but this doesn't detract from quality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions: introduces code mutations, runs tests against mutated code, reports on survival rate, and analyzes test effectiveness. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (validates test suite quality by performing mutation testing, introduces mutations, runs tests, reports survival rate) and 'when' (explicit 'Use this skill when...' clause plus specific trigger terms listed). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'mutation testing', 'test effectiveness', 'mutation score', 'surviving mutants', 'test coverage', 'run mutation tests'. These cover the key phrases a user would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Mutation testing is a very specific niche within software testing. The trigger terms like 'mutation score', 'surviving mutants', and 'mutation testing' are highly distinctive and 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 reads like a marketing description of mutation testing rather than actionable instructions for Claude. It lacks any concrete implementation details—no specific tools (e.g., mutmut, cosmic-ray), no executable code, no commands, and no real workflow. The content explains concepts Claude already understands while failing to provide the specific, executable guidance needed to actually perform mutation testing.
Suggestions
Add concrete tool references and executable commands (e.g., `mutmut run --paths-to-mutate=src/validator/`, `mutmut results`) instead of abstract descriptions of what the skill 'will do'.
Replace the conceptual 'How It Works' section with a concrete workflow including specific commands, validation steps, and error handling (e.g., how to handle when mutmut fails to run, how to parse output).
Remove the 'When to Use This Skill' and 'Integration' sections entirely—these waste tokens on information Claude can infer and provide no actionable value.
Add a concrete code example showing how to analyze surviving mutants and generate specific test improvement suggestions, including example output formats.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows (what mutation testing is, how it works conceptually). Sections like 'How It Works', 'When to Use This Skill', and 'Integration' add no actionable value and waste tokens on general knowledge. | 1 / 3 |
Actionability | There is no concrete code, no executable commands, no specific tools or libraries mentioned, and no actual implementation guidance. The examples describe what the skill 'will do' in abstract terms rather than providing executable steps, commands, or code snippets for performing mutation testing. | 1 / 3 |
Workflow Clarity | The workflow described is purely conceptual ('mutation generation → test execution → result analysis → reporting') with no concrete steps, no specific commands, no validation checkpoints, and no error recovery. The examples describe outcomes rather than actionable sequences. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections with headers, which provides some structure. However, there are no references to external files, no bundle files to support deeper content, and inline content that is mostly filler rather than substantive material that could benefit from being split. | 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.