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

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-workflow-testing/SKILL.md

Quality

Content

63%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 content is a well-organized, concisely written overview that points into a references/ bundle and lays out clear multi-step workflows with validation checkpoints. Its main weaknesses are limited concrete/executable guidance (more description than instruction) and a Modules section whose referenced files are missing from the bundle.

Suggestions

Add concrete, executable commands or code snippets to the DDD, debugging/refactoring, and performance workflows so the guidance is copy-paste-ready rather than process description.

Restore or remove the Modules section: create the referenced modules/INDEX.md and modules/*.md files, or delete the broken module links to keep navigation intact.

Tighten the few remaining prose restatements (e.g. the 'Workflow Progression' summary line and duplicate capability bullets) to push conciseness toward a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is efficient: tight bullet lists, 'See [reference]' pointers, and TRUST 5 dimension bullets that carry domain meaning rather than padding. It is not a 5 because a few prose passages (e.g. the 'Workflow Progression' line and some capability restatements) could be trimmed.	4 / 5
Actionability	Most sections describe processes ('Apply TRUST 5 validation post-refactor', 'Apply refactoring with continuous test execution') rather than giving concrete executable commands or code; the PR-review pipeline has concrete numeric thresholds but largely abstract steps. It is above a 2 because the PR-review and quality-gate sections do give some specific, actionable detail, but below a 4 because key workflows lack copy-paste-ready commands.	3 / 5
Workflow Clarity	Multi-step sequences are clearly enumerated (DDD PRESERVE 6-step list, PR review 5-step pipeline, debug/refactor/perf 6-step pattern) with validation checkpoints ('Verify baseline: all characterization tests PASS before any change', 'Run TRUST 5 validation post-refactor'). It is not a 5 because some checkpoints are implicit rather than framed as explicit validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	The body is a well-signaled overview pointing one level deep to real files in references/ (trust5-framework.md, workflow-processes.md, pr-review-multi-agent.md, etc.), but the Modules section references modules/INDEX.md and four modules/*.md files that do not exist in the bundle, creating broken navigation. The broken links cap this at 3 rather than 4.	3 / 5
	Total	14 / 20 Passed

Description

83%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 is well-constructed: it pairs a concrete 'Use when...' trigger with a clear enumeration of capabilities, covering what and when explicitly. It is specific and largely distinguishable, with only minor gaps in keyword synonyms and coverage breadth.

Dimension	Reasoning	Score
Specificity	Names the testing/QA domain and lists several concrete actions ('writing tests, measuring coverage, characterization, performance, PR-review QA', 'DDD testing, characterization tests, performance profiling, TRUST 5'). It falls short of a 5 because the action list, while specific, has minor coverage gaps rather than being exhaustively comprehensive.	4 / 5
Completeness	Explicitly answers both: 'what' (comprehensive specialist combining DDD testing, characterization tests, performance profiling, TRUST 5 QA) and 'when' ('Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA'). Concrete trigger phrases anchor both halves.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('writing tests', 'measuring coverage', 'characterization', 'performance', 'PR-review QA') that users would plausibly say. It is not a 5 because common synonyms and file/extension variants are missing.	4 / 5
Distinctiveness Conflict Risk	Distinct niche via 'characterization tests', 'TRUST 5', 'DDD testing', and 'PR-review QA' triggers that are unlikely to fire for unrelated skills. It is not a 5 because broad testing/QA framing could still overlap with general testing skills.	4 / 5
	Total	17 / 20 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: 4100d87

Reviewed: 2 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.