Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs. Use when the user mentions mewt, muton, mutation testing, or wants to configure or optimize a mutation testing campaign.
.claude/skills/kunanonj-mutation-testing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -33% | 0% |
> Note: muton and mewt share identical interfaces but target different languages — mewt for general-purpose languages (Rust, Solidity, Go, TypeScript, JavaScript), muton for TON smart contracts (Tact, Tolk, FunC). All examples use mewt commands, but they work exactly the same with muton. File names change accordingly: mewt.toml → muton.toml, mewt.sqlite → muton.sqlite.
Use this skill when the user:
mewt run and needs help getting set up firstDo not use this skill when the user:
Load workflows/configuration.md — a 5-phase guide from mewt init to a validated, ready-to-run campaign.
General question or unfamiliar command? Run mewt --help or mewt <subcommand> --help, then assist.
| File | Content | |------|---------| | workflows/configuration.md | 5-phase guide: init, scope, optimize, validate, run | | references/optimization-strategies.md | Per-file targeting, two-phase campaigns, mutation type filtering |
bash# Initialize and mutate mewt init # Create mewt.toml and mewt.sqlite mewt mutate [paths] # Generate mutants without running tests mewt run [paths] # Run the full campaign # Inspect configuration and scope mewt print config # View effective configuration mewt print targets # Table of all targeted files mewt print mutations --language [lang] # Available mutation types mewt status # Mutant count and per-file breakdown # Investigate specific mutants mewt print mutants --target [path] # All mutants for a file mewt print mutants --severity high # Filter by severity mewt print mutant --id [id] # View mutated code diff mewt test --ids [ids] # Re-test specific mutants
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,048 | 6,719 | -26% | 1 | 1 | 0% | 1,801 | 2,010 | +12% | 0 | 0 | — |
case-02 | fail→pass | 9,707 | 5,589 | -42% | 1 | 1 | 0% | 1,723 | 1,694 | -2% | 0 | 0 | — |
case-03 | fail→pass | 8,177 | 4,509 | -45% | 1 | 1 | 0% | 1,650 | 1,454 | -12% | 0 | 0 | — |
case-04 | fail→fail | 7,087 | 3,874 | -45% | 1 | 1 | 0% | 1,243 | 1,118 | -10% | 0 | 0 | — |
case-05 | pass→pass | 17,839 | 10,618 | -40% | 1 | 1 | 0% | 3,529 | 2,880 | -18% | 0 | 0 | — |
case-06 | pass→pass | 11,723 | 9,551 | -19% | 1 | 1 | 0% | 2,500 | 2,654 | +6% | 0 | 0 | — |
case-07 | fail→pass | 10,223 | 4,641 | -55% | 1 | 1 | 0% | 1,974 | 1,474 | -25% | 0 | 0 | — |
case-08 | fail→pass | 9,813 | 2,809 | -71% | 1 | 1 | 0% | 1,697 | 1,138 | -33% | 0 | 0 | — |
case-09 | fail→pass | 8,949 | 2,289 | -74% | 1 | 1 | 0% | 1,520 | 1,022 | -33% | 0 | 0 | — |
case-10 | fail→pass | 5,632 | 2,494 | -56% | 1 | 1 | 0% | 1,109 | 1,074 | -3% | 0 | 0 | — |
case-11 | fail→pass | 11,535 | 2,699 | -77% | 1 | 1 | 0% | 2,030 | 1,048 | -48% | 0 | 0 | — |
case-12 | pass→pass | 8,697 | 5,499 | -37% | 1 | 1 | 0% | 1,369 | 1,462 | +7% | 0 | 0 | — |
case-13 | fail→pass | 13,139 | 6,460 | -51% | 1 | 1 | 0% | 2,031 | 1,737 | -14% | 0 | 0 | — |
case-14 | fail→pass | 9,052 | 4,690 | -48% | 1 | 1 | 0% | 1,569 | 1,420 | -9% | 0 | 0 | — |
case-15 | pass→pass | 9,536 | 6,285 | -34% | 1 | 1 | 0% | 1,680 | 1,684 | +0% | 0 | 0 | — |
case-16 | fail→pass | 6,987 | 2,734 | -61% | 1 | 1 | 0% | 1,294 | 1,138 | -12% | 0 | 0 | — |
case-17 | fail→pass | 6,350 | 2,446 | -61% | 1 | 1 | 0% | 1,067 | 1,062 | -0% | 0 | 0 | — |
case-18 | fail→pass | 13,440 | 1,717 | -87% | 1 | 1 | 0% | 2,575 | 940 | -63% | 0 | 0 | — |
case-19 | fail→pass | 4,003 | 3,023 | -24% | 1 | 1 | 0% | 672 | 1,204 | +79% | 0 | 0 | — |
case-20 | fail→pass | 27,893 | 3,098 | -89% | 1 | 1 | 0% | 5,521 | 1,277 | -77% | 0 | 0 | — |
case-21 | pass→pass | 6,950 | 3,380 | -51% | 1 | 1 | 0% | 1,166 | 1,201 | +3% | 0 | 0 | — |
case-22 | fail→pass | 5,872 | 2,412 | -59% | 1 | 1 | 0% | 1,025 | 1,072 | +5% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +73 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.