CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/mutant-survival-triage

Normalizes a surviving-mutant record across StrykerJS, PIT, mutmut, and Mull into one shape, classifies why it survived (missing case, weak assertion, equivalent mutant, unreachable code, flaky killer), applies per-mutator heuristics for conditional-boundary, arithmetic-operator, statement-removal, and constant mutations, and drafts the specific test that would kill it. Treats equivalence as a judgment call, because deciding whether a mutant is equivalent to the original is undecidable in general, so a residual survivor rate is expected rather than a defect. Use when a mutation run has finished and the report lists surviving mutants that nobody has yet explained or turned into concrete test cases.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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

Highly actionable and well-structured with a clear sequenced workflow and correct one-level-deep reference usage. The main weakness is conciseness: the equivalent-mutant undecidability theme is repeated across several sections and Step 5's prose could be tightened.

Suggestions

State the undecidability of equivalent mutants once in Step 5 and reference it from Step 2 and Limitations, rather than restating the full argument in each place.

Condense the score-convention subsection in Step 5 to the two named conventions and the one-line rule ('state the convention every time; never compare scores across conventions'), dropping the surrounding explanatory prose.

Trim the Limitations section to points not already covered inline (e.g., remove the reiterated heuristic-classification and undecidability bullets).

DimensionReasoningScore

Conciseness

Specialized and mostly tight, but the undecidability-of-equivalent-mutants point is restated across the description, Step 2, Step 5, and Limitations, and Step 5's citation-heavy prose could be trimmed.

2 / 3

Actionability

Provides a TypeScript interface, concrete original/mutant code pairs per mutator family, a named separating input, and a copy-paste-ready Step 4 test block, matching fully executable guidance.

3 / 3

Workflow Clarity

Clear five-step sequence with Step 2 ordering the classes, a four-point Step 4 completeness checklist, re-run feedback loops, and a spec-confirmation checkpoint before changing either side.

3 / 3

Progressive Disclosure

Verified references/tool-normalization.md exists and is one level deep, holding the bulky per-tool field and operator tables while the core triage logic stays inline with two clearly signaled links.

3 / 3

Total

11

/

12

Passed

Description

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.

A specific, well-scoped description that names concrete actions, includes natural trigger terms and an explicit 'Use when...' clause, and carves out a distinctive niche. The discursive equivalence caveat adds length but does not weaken any dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (normalize, classify into five named reasons, apply per-mutator heuristics, draft the killing test), matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly states what it does and includes an explicit 'Use when a mutation run has finished and the report lists surviving mutants...' trigger, satisfying both the what and the when.

3 / 3

Trigger Term Quality

Uses natural terms a mutation-testing user would actually say ('mutation run', 'surviving mutants', 'report') plus the four tool names, giving good coverage rather than jargon-only language.

3 / 3

Distinctiveness Conflict Risk

Occupies a narrow, clearly defined niche (survivor triage across four named mutation-testing tools) with a distinct trigger, making conflict with other skills unlikely.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents