ac-qa-reviewer

Quality assurance review for implementations. Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ac-qa-reviewer/SKILL.md

Quality

Content

68%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 well-structured, concise, and points to a real implementation file for detail, with an executable quick-start example. Its main weakness is workflow clarity: a batch/destructive QA workflow lacks explicit validation checkpoints and feedback loops, which caps that dimension.

Suggestions

Insert explicit validation checkpoints between workflow steps (e.g., after SCAN/ANALYZE: 'verify findings before SECURITY', and after FIX: 're-run lint/type-check/tests before APPROVE') to add fix->retry feedback loops.

Make the Quick Start snippet self-contained by showing how project_dir is obtained or noting it is an input, so the example is copy-paste ready.

Move or trim the bulleted principle lists (DRY, SOLID, etc.) since they restate knowledge Claude already has, or replace them with the specific rules the reviewer actually enforces.

Dimension	Reasoning	Score
Conciseness	The body is efficiently organized into clear sections with no padding of concepts Claude already knows; the only minor trim opportunity is the bulleted dimension lists (DRY, SOLID, etc.) which restate well-known principles.	4 / 5
Actionability	An executable Quick Start snippet and a pointer to the real scripts/qa_reviewer.py give mostly executable guidance, with a minor gap that the example references an undefined project_dir and delegates most detail to the script.	4 / 5
Workflow Clarity	A clear 7-step sequence and quality gates are present, but because the workflow performs batch/destructive actions (auto-fix, approve/request changes) with no explicit validation checkpoints or fix->retry feedback loops woven between steps, the rubric cap of 3 applies.	3 / 5
Progressive Disclosure	Structure is good with well-signaled one-level-deep references to the existing scripts/qa_reviewer.py for the bulk implementation; minor gaps are the inlined dimension lists that are short enough to be acceptable.	4 / 5
	Total	15 / 20 Passed

Description

65%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 clearly pairs a 'what' with a 'when' and uses natural trigger terms, but its capabilities read as generic review verbs rather than distinct concrete actions, limiting specificity. It is solid but could name sharper, more differentiated capabilities.

Suggestions

Replace generic review verbs with concrete, distinct capabilities (e.g., 'runs static analysis, scores each dimension 0-100, auto-fixes missing docstrings and type hints') to lift specificity.

Add common synonyms/file cues users might say (e.g., 'QA pass', 'code review', 'lint and type-check gates') to round out trigger coverage.

Sharpen the 'what' clause to distinguish this skill from a generic code-review skill by naming its gated-approval output.

Dimension	Reasoning	Score
Specificity	The description names the QA-review domain but the actions ('reviewing code quality, checking implementation standards, performing QA cycles, validating feature quality') are minimal and generic variants of 'review/check' rather than distinct concrete capabilities.	2 / 5
Completeness	It explicitly answers both 'what' (quality assurance review for implementations) and 'when' (Use when reviewing code quality...), but the 'what' is somewhat generic so it sits just below the fully concrete anchor.	4 / 5
Trigger Term Quality	It includes several natural phrases users would actually say ('reviewing code quality', 'QA cycles', 'validating feature quality'), giving good keyword coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The QA-review niche is mostly distinct with concrete QA-specific triggers, carrying only minor overlap risk with general code-review skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fernandezbaptiste/Skrillz
Path: skills/ac-qa-reviewer/SKILL.md
Commit: 93ed392

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.