aiox-qa

Activate Quinn (qa) for Test Architect & Quality Advisor. Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and...

1.59x

Quality

65%

Does it follow best practices?

Impact

86%

1.59x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/AIOX/agents/qa/SKILL.md

Quality

Content

56%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 body is actionable and reasonably workflow-clear, with concrete commands and validation checkpoints. Its weaknesses are token inefficiency from persona decoration and a monolithic structure that inlines a large config block instead of splitting it into referenced files.

Suggestions

Remove skill-irrelevant persona padding (zodiac, Portuguese vocabulary, archetypal greeting levels, Portuguese signature closing) to reclaim token budget — it does not help Claude perform QA tasks.

Move the large YAML agent-definition block into a referenced file and keep SKILL.md as a concise overview with clearly signaled one-level-deep links to the dependency task files already listed.

Either detail the 10-phase review-build workflow inline or explicitly link to it so the headline '10-phase structured QA review' workflow is navigable rather than only named.

Dimension	Reasoning	Score
Conciseness	The ~460-line body is noticeably verbose and padded with skill-irrelevant persona decoration — 'zodiac: ♍ Virgo', a Portuguese vocabulary list ('validar, verificar, garantir...'), archetypal greeting levels, and a Portuguese signature closing — that does not earn its token budget.	2 / 5
Actionability	Concrete executable guidance is present throughout — prefixed commands with args ('review {story}', 'gate {story}'), real CodeRabbit CLI invocations with platform variants, and an explicit error-handling table — with only minor gaps in the pseudocode self-healing loop.	4 / 5
Workflow Clarity	The Typical Workflow is a clear 6-step sequence with validation checkpoints (CodeRabbit scan before manual review, PASS/CONCERNS/FAIL gate) and the self-healing loop provides a feedback loop for error recovery, but it falls short of a 5 because the 10-phase review-build is only referenced, not detailed.	4 / 5
Progressive Disclosure	Section headers provide some structure, but the massive inlined YAML agent-definition block is content that arguably belongs in separate files, and the dependency files (qa-gate.md, qa-review-story.md, etc.) are listed as names rather than clearly signaled one-level-deep navigation links.	3 / 5
	Total	13 / 20 Passed

Description

75%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 specific, trigger-aware, and clearly niche-scoped to QA, scoring solidly above the midpoint on every dimension. Its main flaw is the literal 'and...' truncation, which leaves the capability list and trigger guidance slightly incomplete.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'test architecture review, quality gate decisions, and code improvement' plus 'requirements traceability, risk assessment' — but the literal 'and...' truncation leaves coverage with minor gaps, so it stops short of a comprehensive 5.	4 / 5
Completeness	Both 'what' (Test Architect & Quality Advisor capabilities) and 'when' ('Use for comprehensive test architecture review...') are present, but the 'when' is not tied to concrete user trigger phrases and the description is cut off mid-sentence with 'and...', keeping it below a 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('test architecture review', 'quality gate decisions', 'code improvement'), though the terms lean formal/jargony and miss common synonyms a user might actually say ('review my code', 'check quality').	4 / 5
Distinctiveness Conflict Risk	The QA/testing niche ('Test Architect & Quality Advisor', 'quality gate decisions') is mostly distinct with only minor overlap risk against general code-review skills, fitting above the midpoint but not a fully conflict-free 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .claude/skills/AIOX/agents/qa/SKILL.md
Commit: 4ef6530

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.