mutation-test-suite-optimizer
Uses mutation testing to find weak assertions and missing tests — injects small bugs and checks if the suite catches them, then generates tests targeting the surviving mutants. Use when coverage is high but bugs still ship, when auditing test quality, or when deciding if the suite is good enough.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill mutation-test-suite-optimizer97
Quality
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 explains the mutation testing technique, lists concrete actions, and provides explicit trigger conditions. The description uses domain-appropriate terminology that developers would naturally use while remaining accessible. The three-part 'Use when...' clause effectively captures the scenarios where this skill should be selected.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'injects small bugs', 'checks if the suite catches them', 'generates tests targeting the surviving mutants'. Uses third person voice correctly throughout. | 3 / 3 |
Completeness | Clearly answers both what (mutation testing to find weak assertions, inject bugs, generate tests) AND when with explicit 'Use when...' clause covering three distinct scenarios: high coverage with shipping bugs, auditing test quality, and evaluating suite sufficiency. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'mutation testing', 'weak assertions', 'missing tests', 'coverage', 'bugs', 'test quality', 'suite'. These are terms developers naturally use when discussing test effectiveness. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on mutation testing, which is distinct from general testing skills. The specific terminology ('surviving mutants', 'mutation testing', 'weak assertions') creates a unique trigger profile unlikely to conflict with standard test generation or coverage tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently teaches mutation testing concepts with concrete, actionable guidance. The worked example is particularly strong, showing both the problem and solution with real code. Minor improvement possible in organizing cross-references to related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely efficient use of tokens. No unnecessary explanations of basic concepts. Tables compress information well. Every section adds value Claude wouldn't already know about mutation testing specifics. | 3 / 3 |
Actionability | Provides concrete, executable examples throughout. The worked example with actual Python code, mutation reports, and fixed assertions is copy-paste ready. Tool recommendations are specific with exact commands. | 3 / 3 |
Workflow Clarity | Clear two-step process (run tool → triage survivors) with explicit classification criteria. The triage table provides decision points, and the worked example demonstrates the fix-verify loop. 'Do not' section prevents common errors. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and tables, but references to other skills (`smart-mutation-operator-generator`, `dead-code-eliminator`) are inline without clear signaling. Could benefit from a dedicated 'Related skills' section for navigation. | 2 / 3 |
Total | 11 / 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.
- 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.