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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-structured, actionable test-design skill with copy-paste templates, a sequenced workflow, validation checkpoints, and clean progressive disclosure via a single one-level reference. Its only weakness is prose verbosity in the Red-Green Discipline section.

Suggestions

Tighten the Red-Green Discipline section from two long prose paragraphs into concise bullet points, keeping the tautological-test and horizontal-slicing insights without the discursive rationale.

The Testing Trophy ASCII diagram plus Dodds quote largely restates a well-known prioritization model; consider compressing it to the priority order and the single confidence quote to save tokens.

Dimension	Reasoning	Score
Conciseness	Most sections are dense tables and checklists that assume competence, but the Red-Green Discipline section is two long prose paragraphs explaining reasoning that could be tightened into bullets, fitting the "mostly efficient but could be tightened" anchor.	2 / 3
Actionability	Copy-paste-ready strategy templates for pure functions, API endpoints, and UI components, a concrete output-format template, and specific when-to-use guidance (e.g. property-based tests for "parsers, serialization roundtrip, sorting").	3 / 3
Workflow Clarity	A clearly sequenced 5-step workflow with explicit validation gates ("If you can't answer these... Fix that first"; the final "Confidence Question" feedback loop) and checklists for boundaries and test evaluation.	3 / 3
Progressive Disclosure	Summary desiderata table inline with one well-signaled one-level reference ("See references/desiderata.md"), verified to exist and free of nested references; per-property detail is appropriately split into the reference file.	3 / 3
	Total	11 / 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 strong description: it names a specific framework, enumerates concrete actions, and provides explicit quoted trigger phrases covering both review and planning scenarios. It cleanly answers what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Design test strategy", "which properties matter", "which tradeoffs to make" — tied to a named framework, matching the multi-action anchor rather than the single-domain anchor below it.	3 / 3
Completeness	Explicitly answers both what ("Design test strategy using Beck's Test Desiderata") and when (explicit "Use when..." clause with concrete triggers), the top anchor.	3 / 3
Trigger Term Quality	Quotes natural phrases users would actually say ("how should I test this", "what tests do I need", "review my test strategy", "is this well-tested") plus "planning tests for a new feature or refactor", giving strong coverage.	3 / 3
Distinctiveness Conflict Risk	Beck's Test Desiderata niche with testing-strategy-specific trigger phrases makes it unlikely to fire for adjacent skills like debugging or generic code review.	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.

Repository: tslateman/duet
Commit: 436824a

Reviewed: 5 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.