testing

Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

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.

A well-structured, token-efficient body that teaches the Desiderata tradeoff framework and a concrete test-design workflow without re-explaining basics Claude already knows. Its only gap is that the templates are scaffolding rather than executable test code, and the workflow steps lack explicit validation checkpoints.

Suggestions

Add one runnable example test (e.g., a small property-based roundtrip test) alongside the strategy templates so actionability reaches fully copy-paste-ready code.

Insert an explicit validation/checkpoint between workflow steps — e.g., after Articulate the Contract, confirm the contract is answerable before identifying boundaries — to mirror the confidence-question loop.

Consider folding the duplicated 'Tautological test' guidance (which appears in both the Test Smells table and the Red-Green Discipline section) into one location to tighten the body further.

Dimension	Reasoning	Score
Conciseness	Lean throughout: it assumes Claude knows what tests and frameworks are and adds only the Desiderata framework, the trophy priority, and test-smell fixes — every section earns its place with no padding, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides concrete fill-in templates for pure functions, APIs, and UI components plus boundary checklists and a trophy diagram; stops at 4 because the templates are scaffolding rather than copy-paste runnable test code, so they are mostly-executable rather than fully-executable.	4 / 5
Workflow Clarity	A clear five-step sequence (Articulate Contract, Identify Boundaries, Choose Approach, Apply Trophy, Evaluate) with a closing Confidence-Question feedback loop; not 5 because the steps lack explicit validation checkpoints between them, and not a destructive/batch op so no hard cap applies.	4 / 5
Progressive Disclosure	Clear overview body with a single, well-signaled one-level reference ("See references/desiderata.md for application guidance") that resolves to a real file, and the bulk is appropriately split into tables and templates — matching the clear-overview-with-one-level-references anchor.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

A model description: it states concrete capabilities, names the governing framework, and lists multiple natural trigger phrases that a user would actually say. It uses third-person voice throughout and clearly separates the 'what' from the 'when'.

Dimension	Reasoning	Score
Specificity	Names the concrete actions ("Design test strategy", "which properties matter, which tradeoffs to make") plus the governing framework, giving comprehensive coverage of what the skill does — not vague abstraction like "Helps with documents".	5 / 5
Completeness	Explicitly answers both what ("Design test strategy using Beck's Test Desiderata") and when ("Use when the user asks...") with concrete trigger phrases, exactly matching the score-5 anchor; not 4 because the when-clause is fully explicit and specific.	5 / 5
Trigger Term Quality	Quotes several natural phrases users actually say ("how should I test this", "what tests do I need", "review my test strategy", "is this well-tested") plus synonyms (planning tests, refactor), matching the comprehensive-synonym anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (test-strategy design via Desiderata tradeoffs) with distinct triggers unlikely to fire for code-writing or debugging skills; minimal conflict risk, matching the clear-niche anchor.	5 / 5
	Total	20 / 20 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.

Repository: tslateman/duet
Path: skills/testing/SKILL.md
Commit: 5647baf

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.