mutation-testing

Validate test effectiveness with mutation testing using Stryker (TypeScript/JavaScript with Vitest or bun test via @hughescr/stryker-bun-runner) and mutmut (Python). Find weak tests that pass despite code mutations. Use to improve test quality.

1.43x

Quality

66%

Does it follow best practices?

Impact

93%

1.43x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/mutation-testing/skills/mutation-testing/SKILL.md

Quality

Content

65%

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

A highly actionable, well-structured skill with executable commands and config, but it carries some inferable padding and lacks explicit validation feedback loops in its workflow; with no bundle files, progressive disclosure rests on single-file sectioning rather than reference splitting.

Suggestions

Tighten the 'Core Concept' and 'Mutation Score Targets' sections or fold the score targets into the existing inline 'aim for 80%+' guidance to reduce inferable tokens.

Add an explicit validation gate in the Workflow, e.g. 'Only proceed to mutation testing once coverage is >= 80%; if below, add tests first.'

Consider moving the Stryker and mutmut deep-dive config blocks into one-level-deep reference files (e.g. references/stryker.md, references/mutmut.md) signaled from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean with concrete config and code blocks and no over-explanation of basics, but the 'Core Concept' definitions and the 'Mutation Score Targets' table restate information Claude can largely infer, so it could be tightened toward the score 3 anchor.	2 / 3
Actionability	Provides fully executable install commands, real stryker.config / stryker.conf files, concrete run invocations, and copy-paste ready before/after test examples, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The numbered Workflow section sequences coverage -> run -> report -> fix -> re-run, but checkpoints are implicit (e.g. 'Target: 80%+ coverage' is a soft gate with no 'only proceed if' validation loop), so it sits at the score 2 anchor rather than the explicit-checkpoint score 3.	2 / 3
Progressive Disclosure	Content is well-organized into clear sections in a single file with no broken or nested references, but at ~230 lines it exceeds the under-50-line simple-skill exception and keeps Stryker and mutmut detail inline rather than splitting into one-level-deep reference files.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific, well-scoped description that clearly states what the skill does and names its tools, but its invocation trigger is generic rather than an explicit 'Use when...' clause, capping completeness at 2. Trigger term coverage is relevant but leans technical over natural.

Suggestions

Replace 'Use to improve test quality' with an explicit trigger clause, e.g. 'Use when the user wants to evaluate test quality, find weak tests, or asks about mutation testing / Stryker / mutmut.'

Add natural-language variations users might say (e.g. 'test effectiveness', 'are my tests good enough', 'mutation score') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Validate test effectiveness', 'Find weak tests that pass despite code mutations') and names specific tools (Stryker, Vitest, bun test, mutmut), matching the 'multiple specific concrete actions' anchor rather than the partial score 2.	3 / 3
Completeness	The 'what' is clear but the 'when' is only the generic 'Use to improve test quality' rather than an explicit 'Use when...' trigger, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant keywords ('mutation testing', 'weak tests', 'Stryker', 'mutmut') but these skew technical and miss common natural variations a user would actually say; not the broad coverage of the score 3 anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (mutation testing with named tooling) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/mutation-testing/skills/mutation-testing/SKILL.md
Commit: c4889f6

Reviewed: about 14 hours 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.