qa-expert

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./qa-expert/SKILL.md

Quality

Content

70%

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

The content is highly actionable and well-organized with a clean progressive-disclosure structure that points to real bundle files, but it is verbose with promotional repetition and lacks explicit validation checkpoints for its batch CSV-tracking operations.

Suggestions

Collapse the repeated capability descriptions across 'When to Use', 'Quick Start', 'Core Capabilities', and 'Autonomous Execution' into a single source of truth to reduce token cost.

Add explicit validation/feedback-loop steps for batch operations, e.g. verify CSV row matches the executed test before moving on and re-check on mismatch, to raise workflow clarity.

Remove marketing language ('world-class', '100x faster', 'Innovation', '⭐ Recommended') that adds tokens without actionable value.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured with concrete commands, but it repeats capabilities across 'When to Use', 'Quick Start', 'Core Capabilities', 'Autonomous Execution', and 'Common Patterns' sections and includes promotional language ('100x faster', 'Innovation', 'world-class') that pads tokens beyond what Claude needs.	2 / 3
Actionability	It provides fully executable commands (python scripts/init_qa_project.py, calculate_metrics.py), specific file paths for templates and references, concrete bug-severity classifications, and copy-paste-ready workflow patterns, matching the level-3 anchor.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced (Common Patterns, manual/autonomous execution), but destructive/batch operations like CSV updates and bug filing lack explicit validate-then-retry checkpoints; the 'Ground Truth Principle' is stated but no validation gate guards doc/CSV sync, capping this at 2 per the rubric's batch-operations rule.	2 / 3
Progressive Disclosure	The body is a concise overview that points one level deep to real, present bundle files (references/day1_onboarding.md, master_qa_prompt.md, google_testing_standards.md, ground_truth_principle.md, llm_prompts_library.md; scripts/init_qa_project.py, calculate_metrics.py; assets/templates/TEST-CASE-TEMPLATE.md), all of which exist, with clear navigation sections.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 comprehensive and explicitly covers both capabilities and trigger conditions, but it is overlong and padded with self-promotional over-claims ('100x speedup', '90% coverage targets') that blur its trigger quality and inflate distinctiveness risk.

Suggestions

Trim over-claims and self-referential meta-language (e.g. 'Includes autonomous execution capability', 'Implements OWASP security testing and achieves 90% coverage targets') so the description states what Claude does, not what the skill contains.

Convert trigger phrasing into natural user language (e.g. 'Use when the user needs to set up QA testing, write test cases, or track bugs') and drop marketing terms like '100x speedup'.

Tighten scope so the description signals a single coherent niche (QA process setup and test execution) rather than spanning testing, security, metrics, reporting, and autonomous execution.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports', matching the level-3 anchor.	3 / 3
Completeness	It explicitly answers both what it does and when to use it via the 'Use when creating test strategies, writing test cases...' clause, satisfying the level-3 anchor for explicit what-and-when triggers.	3 / 3
Trigger Term Quality	It includes relevant terms users would say (test strategies, test cases, bug tracking, coverage, QA reports) but mixes in self-referential language ('This skill should be used', 'Includes autonomous execution capability', 'Implements OWASP') and over-claims ('100x speedup', '90% coverage targets') rather than natural trigger phrasing, so it falls short of full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The QA-testing niche is reasonably distinct, but the breadth of capabilities (testing, security, metrics, reporting, autonomous LLM execution) plus generic phrasing ('any software project') leaves overlap risk with general testing or security skills, so it is not a fully clear niche.	2 / 3
	Total	10 / 12 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
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: daymade/claude-code-skills
Path: qa-expert/SKILL.md
Commit: b3b4af8

Reviewed: 8 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.