CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ac-qa-reviewer

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

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is ac-qa-reviewer in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well structured with concrete quick-start code, a realistic result example, and explicit quality gates, and its single reference is real and one level deep. Weaknesses are the generic dimension checklists that restate what Claude already knows and a workflow presented as step labels without commands or explicit validation checkpoints.

Suggestions

Compress the Review Dimensions checklists to a single line per dimension (or move the detailed checks into qa_reviewer.py config), since items like DRY, SOLID, and SQL injection need no explanation.

Add concrete commands or API calls to each QA Workflow step, and make validation explicit (e.g. '3. SECURITY → run security checks; if blocking issues found, stop and report before FIX').

Complete the Quick Start example by showing how project_dir is obtained so the snippet runs as-is.

DimensionReasoningScore

Conciseness

The body is mostly efficient with short sections, but the Review Dimensions checklists ('Clean code principles', 'DRY (Don't Repeat Yourself)', 'SOLID principles', 'SQL injection prevention') restate concepts Claude already knows and could be tightened to a one-line dimension list or moved to configuration.

3 / 5

Actionability

Concrete executable Quick Start code ('from scripts.qa_reviewer import QAReviewer', 'result = await reviewer.review_feature("auth-001")'), a realistic result JSON example, and specific quality-gate YAML give mostly copy-paste-ready guidance; minor gaps remain such as the undefined 'project_dir' and only one worked example.

4 / 5

Workflow Clarity

The 'SCAN → ANALYZE → SECURITY → REVIEW → REPORT → FIX → APPROVE' sequence is present, but steps are terse labels with no commands or per-step validation checkpoints; the quality gates exist as config yet workflow checkpoints are implicit, matching the anchor for steps listed with validation gaps.

3 / 5

Progressive Disclosure

Sections are well organized (Quick Start, Dimensions, Result, Workflow, Gates, Integration) and the body points one level deep to a real file ('See scripts/qa_reviewer.py for full implementation' — verified present); minor gaps remain since the dimension checklists are inlined rather than split into reference files.

4 / 5

Total

14

/

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 has an explicit and well-formed 'Use when...' clause with several natural trigger phrases, and is written in third-person fragment style. Its main weakness is a vague 'what' — 'Quality assurance review for implementations' states no concrete capabilities, so it reads closer to a domain label than a capability list.

Suggestions

Replace 'Quality assurance review for implementations' with 2-3 concrete capabilities, e.g. 'Runs static analysis, security checks, and quality-gate scoring on completed features'.

Add common trigger synonyms users would naturally say, such as 'code review', 'linting', or 'QA pass/fail', to broaden keyword coverage.

Tie the description to the artifact it produces (a scored review report with blocking issues and auto-fixes) to sharpen distinctiveness from generic code-review skills.

DimensionReasoningScore

Specificity

'Quality assurance review for implementations' names the domain but offers only one generic action ('review'); no concrete capabilities such as static analysis, security scanning, or gate scoring are explicitly stated, matching the anchor where the domain is named but actions are minimal.

2 / 5

Completeness

Both halves are present: 'Quality assurance review for implementations' answers what, and 'Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality' answers when with concrete triggers; the 'what' is generic, so it falls short of the explicit both-anchors example.

4 / 5

Trigger Term Quality

'reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality' gives good natural-phrase coverage, though common variations like 'code review', 'linting', or 'testing' are missing, keeping it short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Triggers like 'performing QA cycles', 'implementation standards', and 'validating feature quality' carve a fairly distinct niche with only minor overlap risk against generic code-review skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

.claude/skills/ac-qa-reviewer/SKILL.md

Revision

93ed392

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill