Analyzes surviving mutants from mutation testing to identify why tests failed to detect them. Takes repository code, test suite, and mutation testing results as input. Identifies root causes including insufficient coverage, equivalent mutants, weak assertions, and missed edge cases. Automatically generates actionable test improvements and new test cases. Use when analyzing mutation testing results, improving test suite effectiveness, investigating low mutation scores, generating tests to kill surviving mutants, or enhancing test quality based on mutation analysis.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Root cause classification and targeted test generation
Killed mutant filtered
100%
100%
Weak assertion category
62%
100%
Boundary mutation category
87%
100%
State mutation category
62%
100%
Side effect mutation category
62%
100%
Exact value assertion for #1
100%
100%
Boundary value test for #2
100%
100%
State assertion for #4
100%
100%
Side effect assertion for #5
100%
100%
Mutant-targeting comment
100%
100%
Descriptive test name
100%
100%
pytest framework followed
100%
100%
Structured report generation and equivalent mutant documentation
Killed mutant excluded
50%
100%
Executive summary present
100%
100%
Mutants grouped by category
100%
100%
Equivalent mutant identified
0%
0%
Equivalent mutant config
0%
0%
Security priority
100%
100%
Truth table for logical operator
50%
100%
NoCoverage mutant noted
100%
100%
Concrete test improvements
100%
100%
Recommendations section
100%
100%
Exact equality for #4
100%
100%
No mutation of killed mutant
100%
100%
PIT parsing, test framework matching, and side-effect verification strategy
Killed mutant filtered
100%
100%
7 survivors identified
100%
100%
JUnit 5 style used
100%
100%
Mockito verify for paymentGateway
100%
100%
Mockito verify for auditLogger
100%
100%
VoidMethodCall strategy applied
100%
100%
Exact fee assertion
100%
100%
Boundary value test for isEligible
100%
100%
Logical operator test coverage
50%
100%
List state assertion for index 7
100%
100%
Category labels used
100%
100%
Correct fee arithmetic
100%
100%
0f00a4f
Table of Contents
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.