qa-expert

Sets up QA testing processes: test strategies, Google Testing Standards test cases, P0-P4 bug tracking, quality metrics, progress reports, autonomous execution via master prompts, and OWASP security testing, with third-party QA handoff docs. Use when establishing QA infrastructure, writing test cases, executing test plans, or tracking bugs. Not for auditing an already-rendered UI (use frontend-visual-qa).

Quality

81%

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

Quality

Content

71%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.

Well-structured, actionable overview with excellent progressive disclosure — every referenced bundle file exists and is one level deep. The main weaknesses are redundancy (autonomous execution covered in four sections, master_qa_prompt.md referenced six times, repeated '100x' marketing claims) and missing explicit validation/feedback loops in the workflows.

Suggestions

Consolidate autonomous execution into a single section (remove the duplicated Quick Start pointer, capability-3 'Innovation' block, and Pattern 2 overlap) and reference 'references/master_qa_prompt.md' once from that section.

Trim unverifiable marketing claims ('world-class', '100x faster', 'zero human error') and replace them with concrete expectations (e.g., what the master prompt actually does).

Add an explicit feedback loop to the execution workflows: after the autonomous run or each batch, re-run calculate_metrics.py and verify quality-gate status before proceeding, with a fix-and-retry step on failure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, numbered lists, commands, no basic-concept explanations), but autonomous execution is described in at least four places (Quick Start, capability 3, a dedicated 'Autonomous Execution' section, Pattern 2), 'references/master_qa_prompt.md' is pointed to six times, and marketing claims ('world-class', '100x faster/speedup') recur. It is not a 4 because this duplication is noticeable rather than minor.	3 / 5
Actionability	Concrete, runnable commands are given ('python scripts/init_qa_project.py <project-name> [output-directory]', 'python scripts/calculate_metrics.py <path/to/TEST-EXECUTION-TRACKING.csv>') plus specific formats (TC-[CATEGORY]-[NUMBER], BUG-001), a severity table, and quality-gate thresholds. Not a 5 because key steps like test-case writing and report generation defer almost entirely to reference files without inline examples of the actual output format.	4 / 5
Workflow Clarity	Sequences are clear for manual execution (read test case → execute → update CSV immediately → file bug), autonomous execution, Day 1 onboarding, and the four common patterns, with checkpoints like the ground-truth principle and P0 auto-escalation. Not a 5 because there is no explicit validate-then-retry loop (e.g., verifying the CSV after the autonomous run or re-running metrics on failure), leaving minor validation gaps.	4 / 5
Progressive Disclosure	The body is an overview with well-signaled, one-level-deep references, and every referenced path exists in the bundle (5 files in references/, 2 scripts, assets/templates/TEST-CASE-TEMPLATE.md), each summarized in the 'Reference Documents', 'Scripts', and 'Assets & Templates' sections. Not a 4 because organization, signaling, and actual bundle structure all align with no nesting or buried references.	5 / 5
	Total	16 / 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 description: specific, third-person, comprehensive on both 'what' and 'when', with an explicit negative boundary that routes the neighboring frontend-visual-qa use case away. The only gap is a few missing natural synonyms (e.g., 'quality assurance', 'bug reporting').

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capabilities in third person ('Sets up QA testing processes: test strategies, Google Testing Standards test cases, P0-P4 bug tracking, quality metrics, progress reports, autonomous execution via master prompts, and OWASP security testing, with third-party QA handoff docs'), matching the multiple-specific-concrete-actions anchor with comprehensive coverage. It is not a 4 because the action list covers the skill fully rather than leaving minor gaps.	5 / 5
Completeness	It explicitly answers both what (the enumerated capability list) and when ('Use when establishing QA infrastructure, writing test cases, executing test plans, or tracking bugs') with concrete trigger phrases, matching the top anchor. Not a 4 because the 'when' clause is already explicit and specific, not merely present.	5 / 5
Trigger Term Quality	'establishing QA infrastructure', 'writing test cases', 'executing test plans', 'tracking bugs' are natural phrases a user would say, giving good keyword coverage. It falls short of a 5 because common variations such as 'quality assurance', 'regression testing', or 'bug reporting' are absent.	4 / 5
Distinctiveness Conflict Risk	The QA-process niche is distinct and it proactively disambiguates a bordering skill ('Not for auditing an already-rendered UI (use frontend-visual-qa)'), minimizing conflict risk. Not a 4 because overlap with generic testing skills is addressed by that explicit boundary.	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
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: bb6ad55

Reviewed: 5 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.