aiox-qa

Activate the AIOX Test Architect & Quality Advisor agent (Quinn). Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and test strategy. Advisory only - teams choose their quality bar. Trigger when user asks to qa, or says 'activate qa', 'switch to qa', '@qa'.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.kimi/skills/aiox-qa/SKILL.md

Quality

Content

52%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 delivers actionable CodeRabbit and gate workflows with real feedback loops, but is heavily padded with triplicated command listings and persona metadata, and inlines a large config block that should be split into bundled reference files.

Suggestions

Eliminate the duplicated command listings: keep a single canonical command table and remove the redundant YAML commands block and Quick Commands section to cut tokens substantially.

Move the large inlined YAML agent-definition block into a bundled reference file (e.g. references/agent-definition.yaml) and reference it one level deep from SKILL.md.

Trim persona decoration (zodiac, vocabulary list, archetypal greeting variants) and meta-instructional padding ('Read it ENTIRELY', 'DO NOT load any external agent files') that Claude does not need.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the command list is duplicated three times (Star Commands table, YAML commands block, and Quick Commands), and persona fluff (zodiac, vocabulary, archetypal greetings) plus meta-instructions ('Read it ENTIRELY', 'DO NOT load any external agent files') pad the body well past what is needed.	2 / 5
Actionability	Mostly executable guidance: the CodeRabbit section gives concrete native and WSL commands, explicit error-handling recipes, and a self-healing loop; many other sections are descriptive rather than instructional, leaving minor gaps.	4 / 5
Workflow Clarity	The Typical Workflow and CodeRabbit self-healing loop provide a clear sequence with explicit validation checkpoints (scan → analyze → gate) and a validate→fix→retry feedback loop capped at 3 iterations with a halt-on-failure fallback; minor gaps in linking gate verdicts to follow-up actions.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the body is monolithic: a large inlined YAML agent-config block that should live in a separate file, with dependencies pointing to external .aiox-core/ paths rather than bundled, discoverable references.	2 / 5
	Total	12 / 20 Passed

Description

92%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 strong, concrete description that clearly states both capabilities and explicit trigger conditions. Trigger terms are command-oriented and could include more natural-language synonyms, but overall it is comprehensive and distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the domain — 'test architecture review, quality gate decisions, and code improvement' plus 'requirements traceability, risk assessment, and test strategy' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Activate the AIOX Test Architect & Quality Advisor agent... comprehensive test architecture review...') and when ('Use for...', 'Trigger when user asks to qa...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural command-style triggers a user would say ('qa', 'activate qa', 'switch to qa', '@qa'), but misses common natural-language synonyms like 'test review' or 'quality review'.	4 / 5
Distinctiveness Conflict Risk	Clear QA/test-architecture niche with distinct '@qa' trigger and advisory framing; minimal overlap risk with adjacent dev or PM skills.	5 / 5
	Total	19 / 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
skill_md_line_count	SKILL.md is long (523 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

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.