CtrlK
BlogDocsLog inGet started
Tessl Logo

strategic-testing

Decide whether a change warrants new tests and choose proportionate verification. Use before adding tests, when planning validation, or when reviewing whether a proposed test protects meaningful behavior.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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 lean, well-organized decision framework with actionable criteria and an explicit decision gate. Adding a brief worked example would lift actionability and make the implicit workflow sequence explicit.

Suggestions

Add one short worked example (e.g., a mechanical refactor -> no test, vs. a persisted-data invariant -> test) to make the decision concrete and push actionability toward 5.

Render the decision procedure as an explicit numbered sequence (identify failure -> weigh maintenance cost -> decide -> choose smallest level) so the workflow checkpoint is unambiguous rather than implied by prose.

DimensionReasoningScore

Conciseness

The 11-line body is lean with no padding and no explanation of concepts Claude already knows; every line (prioritize/skip criteria, smallest-level rule, decision gate) earns its place, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

As an instruction-only skill the absence of code is not penalized, and the guidance is actionable with explicit prioritize/skip lists and a concrete if-then rule ('If that case is weak, do not add one'); it stops short of a 5 because no worked example illustrates the decision on a concrete change.

4 / 5

Workflow Clarity

A clear decision procedure is present with an explicit gate ('identify the realistic failure it prevents and confirm... maintenance cost is justified. If that case is weak, do not add one'), but it is presented as bulleted criteria plus a closing paragraph rather than an explicit numbered sequence with checkpoints, fitting the 'clear sequence with minor validation gaps' anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; the body is well-organized with a heading, intro, and bulleted criteria, so the simple-skill exception allows a top score with just well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

78%Weight 40%Scale 1-5

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 cleanly answers both what the skill does and when to use it, with natural trigger phrases and a clear niche. Its main weakness is that the named actions are abstract decisions rather than concrete operational verbs.

DimensionReasoningScore

Specificity

Names the domain ('whether a change warrants new tests') and two actions ('Decide whether...', 'choose proportionate verification'), but the actions are high-level decisions rather than concrete operational steps, matching the anchor that lists 1-2 actions without comprehensive coverage.

3 / 5

Completeness

Explicitly states what ('Decide whether a change warrants new tests and choose proportionate verification') and when ('Use before adding tests, when planning validation, or when reviewing...'), with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'before adding tests', 'when planning validation', and 'reviewing whether a proposed test protects meaningful behavior' read as things a user would say; a few common synonyms (test coverage, unit tests, TDD) are missing, fitting the good-but-incomplete anchor.

4 / 5

Distinctiveness Conflict Risk

The strategic-testing-decision niche ('whether a change warrants new tests') is mostly distinct with specific triggers, but carries minor overlap risk with a general test-writing or test-review skill, fitting the 'mostly distinct; minor overlap' anchor.

4 / 5

Total

16

/

20

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.

Repository
FranciscoMoretti/chat-js
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.