CtrlK
BlogDocsLog inGet started
Tessl Logo

refine-tests

Critically review and refine tests generated during a coding session. Use this skill when the user asks to review tests, clean up tests, refine tests, prune tests, improve test quality, or remove useless/low-value tests. Also use when the user says 'review my tests', 'clean up tests', or mentions test quality after a coding session.

80

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The body is concise, actionable, and well-structured with a clear five-step workflow that includes a validation feedback loop. It assumes Claude's competence and every section earns its place.

DimensionReasoningScore

Conciseness

Lean and focused; avoids explaining concepts Claude already knows and every line is actionable decision criteria rather than filler.

3 / 3

Actionability

Provides a concrete executable command ('php artisan test --compact <test-file>'), specific assertion guidance, and a concrete test-naming example, making the instruction-only guidance directly actionable.

3 / 3

Workflow Clarity

Steps 1–5 are clearly sequenced and Step 5 includes an explicit validation checkpoint with a feedback loop ('Run the refined tests... If any test fails, fix it') covering the batch pruning operation.

3 / 3

Progressive Disclosure

A single-purpose, well-organized skill with labeled sections and no nested references; appropriately self-contained without needing external bundle files.

3 / 3

Total

12

/

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 well-crafted description that concisely states the skill's purpose and provides rich, natural trigger terms including verbatim user phrasings. It clearly answers both 'what' and 'when' in third person without fluff.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions ('review and refine tests, clean up tests, refine tests, prune tests, improve test quality, or remove useless/low-value tests') rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Critically review and refine tests generated during a coding session') and when ('Use this skill when the user asks... Also use when the user says...') with explicit triggers.

3 / 3

Trigger Term Quality

Covers natural user phrasings including verbatim quoted triggers like "'review my tests', 'clean up tests'" alongside variations (prune, refine, improve test quality).

3 / 3

Distinctiveness Conflict Risk

Clear niche of post-session test refinement with distinct triggers that are unlikely to collide with other skills.

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.

Repository
figlabhq/agent-skills
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.