mutant-survival-triage@1.2.10 • testland • Registry • Tessl

PluginPublic

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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

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

A thorough, highly actionable triage skill with a clear sequenced workflow and executable guidance. Its weaknesses are a monolithic structure with no progressive disclosure to separate reference files, and some conceptual prose in Step 5 that could be trimmed.

Suggestions

Split the tool-specific normalization tables (Step 1) and per-mutator heuristics (Step 3) into one-level-deep reference files linked from SKILL.md so the main file stays an overview.

Tighten Step 5 by reducing the academic prose on equivalent-mutant undecidability to a brief statement plus citation; Claude already knows the concept is undecidable.

Consider a short Quick-start block at the top summarizing the Step 1-to-5 flow before the detailed tables, so the entry point is scannable.

Dimension	Reasoning	Score
Conciseness	Tool-specific normalization tables, per-mutator heuristics, and executable examples are high-value non-obvious detail, but Step 5's prose on equivalent-mutant undecidability re-explains a concept Claude already knows and could be tightened, so it is mostly efficient rather than lean.	2 / 3
Actionability	Provides fully executable TypeScript interfaces and test blocks, concrete commands like 'mutmut run' / 'mutmut browse' / 'mutmut apply <mutant>', and specific separating inputs (e.g. 'qty === maxQty', 'tax === 0') plus a copy-paste output template - matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Steps 1-5 are explicitly sequenced with an ordered classification table and validation checkpoints ('If you cannot name one, the classification is equivalent-mutant') plus feedback loops ('Stabilize the covering test first, then re-run'), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Well-organized into sections but it is a ~330-line monolith with no internal reference files (references/scripts/assets are absent), and tool-specific normalization tables and per-mutator detail that could be split out sit inline - matching the 'content that should be separate is inline' anchor rather than the one-level-deep-references anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong, specific description in third-person voice that names concrete actions, four tools, five survival classes, and an explicit 'Use when...' trigger. It is distinguishable from other skills and uses natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions - 'Normalizes a surviving-mutant record across StrykerJS, PIT, mutmut, and Mull', 'classifies why it survived (missing case, weak assertion, equivalent mutant, unreachable code, flaky killer)', and 'drafts the specific test that would kill it' - matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers what it does (normalize, classify, apply heuristics, draft tests) and when to use it via the clause 'Use when a mutation run has finished and the report lists surviving mutants that nobody has yet explained or turned into concrete test cases.'	3 / 3
Trigger Term Quality	Covers natural terms a user would say during mutation testing - the tool names 'StrykerJS, PIT, mutmut, and Mull', 'mutation run', 'surviving mutants', and 'report lists surviving mutants' - giving good coverage rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche - triaging surviving mutants from named mutation-testing tools - with distinct triggers unlikely to fire for unrelated skills; not below 2 because the trigger is specific, not above since 3 is the cap.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

3 months ago

testland/mutant-survival-triage

On this page