moai-workflow-testing

Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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-structured overview with clear sequenced workflows and validation checkpoints, and it pushes detail into one-level-deep references. The main gap is the Modules section: all five module links and the modules index are broken (the modules/ directory is absent from the bundle).

Suggestions

Either create the referenced modules/ files (ai-debugging.md, smart-refactoring.md, performance-optimization.md, automated-code-review.md, INDEX.md) or remove the Modules section and fold any essential content inline or into existing references.

Add at least one concrete executable example per workflow (e.g., a real pytest characterization-test snippet or a TRUST 5 scoring command) to lift actionability from conceptual guidance to copy-paste-ready.

Run a link audit so every ${CLAUDE_SKILL_DIR}/... path resolves to a real bundled file, preventing broken-navigation regressions.

Dimension	Reasoning	Score
Conciseness	The body is dense and scannable: bullet summaries, terse step lists, and one-line per-topic overviews, with detail offloaded to references — every token earns its place and it does not re-explain concepts Claude already knows.	3 / 3
Actionability	Guidance is mostly conceptual ('Apply TRUST 5 framework per file', 'organize tests by aggregates') rather than executable; concrete commands/tooling appear only as brief references and per-language lists, with little copy-paste-ready code.	2 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (DDD PRESERVE 1-6, code review 1-6, PR multi-agent 1-5) with explicit validation checkpoints ('Verify baseline: all characterization tests PASS before any change', 'drop issues <80 confidence').	3 / 3
Progressive Disclosure	Overview is well-signaled and reference links resolve, but the 'Modules' section points to modules/INDEX.md and four modules/*.md files that do not exist in the bundle, leaving broken navigation and incomplete disclosure.	2 / 3
	Total	10 / 12 Passed

Description

92%

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 is strong: it leads with an explicit 'Use when' trigger, names many concrete capabilities, and uses natural vocabulary. Its main weakness is a broad testing/QA scope that could overlap with general testing skills.

Suggestions

Tighten distinctiveness by leading with the differentiating capabilities (e.g., 'characterization tests for legacy refactors', 'TRUST 5 quality scoring', 'multi-agent PR review') so it is less likely to fire for generic 'write me a test' requests.

Add a 'do not use for' or scope-narrowing phrase to reduce overlap with plain unit-testing or coverage skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'writing tests, measuring coverage... characterization, performance, or PR-review QA' plus 'DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation', matching the multiple-specific-actions anchor.	3 / 3
Completeness	Opens with an explicit 'Use when...' trigger clause and follows with a clear statement of what the skill combines, satisfying both the what and the when with explicit triggers.	3 / 3
Trigger Term Quality	Natural user phrases appear ('writing tests', 'measuring coverage', 'PR-review QA') alongside recognizable terms ('characterization tests', 'performance profiling'), giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The combination (DDD testing + TRUST 5 + PR-review) is fairly niche, but 'writing tests, measuring coverage, performance' overlaps broadly with generic testing/QA skills, so it could still trigger for the wrong skill.	2 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 11 missing, 11 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-workflow-testing/SKILL.md
Commit: 05117b6

Reviewed: 1 day 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.