CtrlK
BlogDocsLog inGet started
Tessl Logo

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...

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced agent definition with strong feedback loops and concrete CLI guidance. Its weaknesses are token efficiency from duplicated command/greeting definitions and a monolithic inline YAML block that should be a one-level-deep reference.

Suggestions

De-duplicate the command listing: keep either the markdown Star Commands table or the YAML commands block, not both, to cut substantial tokens.

Move the full agent-definition YAML block into a referenced file (e.g. references/agent-definition.yaml) and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure and conciseness simultaneously.

Consolidate the three greeting definitions (Activation Greeting section + greeting_levels minimal/named/archetypal) into a single canonical source.

DimensionReasoningScore

Conciseness

The body is mostly operational config but carries clear redundancy — the command set appears twice (markdown Star Commands table and full YAML commands list), the greeting is defined in three places, and repeated ALL-CAPS CRITICAL/MANDATORY directives pad the activation steps; not 1 because it avoids explaining concepts Claude already knows, not 3 because the duplication is substantial.

2 / 3

Actionability

Provides concrete commands with explicit args and executable CLI invocations like '~/.local/bin/coderabbit --prompt-only -t committed --base ${DEFAULT_BRANCH:-main}' plus specific error-handling and timeout guidance, matching the copy-paste-ready anchor.

3 / 3

Workflow Clarity

Sequenced activation protocol and a Typical Workflow with explicit validation checkpoints, and the CodeRabbit self-healing loop is a full feedback loop (parse output, check CRITICAL/HIGH, retry, FAIL after max iterations); not 2 because validation is explicit rather than implicit.

3 / 3

Progressive Disclosure

Sections are organized and external task/template dependencies are signaled via the dependencies list, but the complete agent-definition YAML block is inlined monolithically instead of being split into a reference file; with no bundle files present, the inline monolith keeps this below 3.

2 / 3

Total

10

/

12

Passed

Description

85%

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, complete description that names concrete capabilities and provides explicit activation triggers in third-person imperative voice. Its main weakness is trigger-term breadth — the triggers lean on activation commands rather than the fuller range of natural language a user might say.

Suggestions

Broaden trigger terms to include natural-language variations such as 'quality review', 'test review', 'review my tests', or 'run quality checks' alongside the activation commands.

Consider trimming 'code improvement' or scoping it ('advisory code improvement') since it is the broadest phrase and the most likely source of overlap with general code-review skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'test architecture review, quality gate decisions, and code improvement' plus 'requirements traceability, risk assessment, and test strategy' — matching the multi-action anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly states what the agent does and includes an explicit 'Trigger when user asks to qa...' clause, satisfying both what and when; not 2 because the when is explicit rather than implied.

3 / 3

Trigger Term Quality

Triggers ('activate qa', 'switch to qa', '@qa') are activation-command style and miss common natural variations like 'quality review', 'test review', or 'run QA', fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

Clear QA/test-architecture niche with distinct activation triggers ('@qa', 'activate qa') unlikely to fire for unrelated skills; not 2 because the scope is narrowly scoped rather than broadly overlapping.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.