qa

Autonomous multi-app QA sweep that drives template apps with Playwright MCP. Use only when the user explicitly runs /qa or asks for an end-to-end QA sweep. Do not load it for ordinary feature work, single-page checks, or one-off bug fixes.

Quality

83%

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

77%

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

Highly actionable and clearly sequenced with good validation checkpoints, but it is a monolithic file: the tester prompt and troubleshooting are inlined rather than split into one-level-deep referenced files, and some content restates general QA knowledge.

Suggestions

Move the full Tester Agent Prompt template into a referenced file (e.g. references/tester-prompt.md) and keep only the placeholder list in SKILL.md, so the body stays a lean overview.

Trim the 'What Counts as a Bug' / 'What is NOT a bug' lists to the few app-specific signals; Claude already knows console errors and 4xx/5xx count as bugs.

Optionally extract the Troubleshooting section into references/troubleshooting.md and link to it, keeping the main workflow uncluttered.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational detail with no concept-explanation padding, but the ~115-line tester prompt is inlined verbatim and the bug/no-bug lists restate general QA knowledge Claude already has, so it is not fully lean.	2 / 3
Actionability	Provides exact, copy-paste-ready commands and tool calls (per-app ports, 'cd templates/mail && PORT=9201 pnpm dev', curl polling loop, named Playwright MCP tools, lsof kill command), matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clearly sequenced 7-step orchestrator workflow with explicit validation checkpoints (curl server readiness with 30s skip, 'Maximum 2 full passes', 3-attempt retry cap) and fix-retest feedback loops for a parallel batch operation.	3 / 3
Progressive Disclosure	Sections are well organized but no bundle files exist and content that could be one level deep — notably the full tester prompt template — is inlined in SKILL.md, matching the 'content that should be separate is inline' anchor rather than a clearly referenced split.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, third-person description with explicit use-when triggers and clear conflict avoidance. The only weakness is specificity: it names the domain and mechanism but does not list multiple discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete mechanism ('drives template apps with Playwright MCP', 'multi-app QA sweep') but does not enumerate multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	Explicitly answers both what ('Autonomous multi-app QA sweep that drives template apps with Playwright MCP') and when ('Use only when the user explicitly runs /qa or asks for an end-to-end QA sweep'), matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Includes natural terms a user would actually say ('/qa', 'end-to-end QA sweep', 'QA sweep') with good coverage; not the level below which only has partial keywords.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (template-app QA sweep via Playwright MCP) with a distinct trigger and explicit exclusion of ordinary work, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/qa/SKILL.md
Commit: c1ee18b

Reviewed: 4 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.