CtrlK
BlogDocsLog inGet started
Tessl Logo

mutation-testing

Use when evaluating test quality on modules containing business logic, calculation utilities, or state machines to determine whether the tests provide genuine defect detection.

55

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/mutation-testing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The body is a well-organized overview that correctly offloads detail to one real reference file, but it stays at a high level with no executable commands or validation checkpoints in the overview itself.

Suggestions

Add one minimal executable snippet to the body (e.g. `pnpm stryker run`) so the overview is actionable on its own.

Surface a brief validation checkpoint inline, such as "re-run Stryker and confirm the score improved," rather than leaving it only in the reference.

Trim the motivational intro paragraph to reduce conceptual padding Claude already knows.

DimensionReasoningScore

Conciseness

Mostly efficient with brief sections and compact Quick Reference bullets, but the opening editorializing ("the standard that actually matters in production") explains motivation Claude already knows and could be tightened.

2 / 3

Actionability

Names concrete actions ("Set up Stryker", "run an initial mutation report", "kill surviving mutants") but the body itself contains no executable commands or code — all concrete detail is deferred to references/rule.md, leaving key specifics missing in the overview.

2 / 3

Workflow Clarity

The Check/Fix sequence and Fix sub-steps provide a clear order, but the body omits validation checkpoints; the validate→fix→re-run loop only exists in the reference's Verification section, so checkpoints are missing from the overview.

2 / 3

Progressive Disclosure

A concise overview is clearly split from a single, well-signaled one-level-deep reference ("see `references/rule.md`"), which exists as a real bundle file, giving easy navigation without nested references.

3 / 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.

The description has a strong explicit trigger and answers both what and when, but relies on abstract phrasing and omits the obvious keyword "mutation testing," weakening trigger quality and distinctiveness.

Suggestions

Add the concrete term "mutation testing" (and optionally "Stryker") to the description so the most natural user trigger is present.

Replace abstract phrasing like "evaluating test quality" with concrete actions, e.g. "Run Stryker mutation testing on... to measure defect detection."

Sharpen distinctiveness by framing the trigger around mutation score specifically rather than generic test-quality evaluation.

DimensionReasoningScore

Specificity

Names the domain ("business logic, calculation utilities, or state machines") and an action ("evaluating test quality" / "determine whether the tests provide genuine defect detection"), but the actions are abstract goals rather than multiple concrete operations, so it is not comprehensive enough for a 3.

2 / 3

Completeness

An explicit "Use when..." clause states the trigger conditions and the purpose ("to determine whether the tests provide genuine defect detection"), clearly answering both what it does and when to use it; third-person voice is maintained.

3 / 3

Trigger Term Quality

Includes relevant terms ("test quality", "business logic", "defect detection") but omits the most natural trigger a user would say — "mutation testing" / "Stryker" — which never appears in the description, leaving common variations missing.

2 / 3

Distinctiveness Conflict Risk

The narrowing to business logic / calculation / state-machine modules helps, but the broad "evaluating test quality" trigger could still overlap with general coverage or testing skills, so it is not a clearly conflict-free niche.

2 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
Reviewed

Table of Contents

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.