browser-qa

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

Quality

80%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-qa/SKILL.md

Quality

Content

85%

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

The body is a tight, well-sequenced QA playbook with concrete thresholds, validation checkpoints, and a safety gate; its only real weakness is a couple of time-sensitive and mildly explanatory asides that slightly dilute token efficiency.

Suggestions

Drop or relocate the 'INP replaced FID in March 2024' date — keep just the current thresholds (LCP/CLS/INP) to avoid aging time-sensitive content.

Trim the axe-core percentage aside to the operational rule alone: 'An automated axe-core pass is necessary, not sufficient — still do a manual keyboard/focus/screen-reader check before reporting accessible.'

Dimension	Reasoning	Score
Conciseness	The body is largely lean and operational, but it carries time-sensitive detail ('INP replaced FID in March 2024; thresholds per web.dev') and minor explanatory padding (the axe-core 30-40% note) that could be trimmed without losing actionable value.	2 / 3
Actionability	Guidance is concrete and actionable throughout — exact thresholds (LCP < 2.5s, CLS < 0.1, INP < 200ms), specific breakpoints (375/768/1440px), named tools (axe-core), and a copy-ready QA report template with a verdict rubric.	3 / 3
Workflow Clarity	A clear four-phase sequence (Smoke, Interaction, Visual Regression, Accessibility) with explicit validation checkpoints such as 'no baseline ⇒ report INCONCLUSIVE, never a silent PASS' and a safety-first blast-radius gate for mutating journeys.	3 / 3
Progressive Disclosure	Self-contained SKILL.md with well-organized sections and no nested or dangling references; nothing here needs splitting into bundle files, so the clean section structure earns the top anchor.	3 / 3
	Total	11 / 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 cleanly answers what and when with a distinct post-deploy QA niche, but its action list is abstract and its trigger terms lean technical rather than mirroring how users actually ask for UI QA.

Suggestions

Replace abstract verbs with concrete actions, e.g. 'screenshot key pages, run axe-core accessibility scans, verify form flows, and compare against visual baselines'.

Add natural user phrasings to the trigger clause, e.g. 'Use when the user asks to QA a deployed site, check that UI/frontend changes work, or run visual/accessibility checks after deploy'.

Dimension	Reasoning	Score
Specificity	The phrase 'automate visual testing and UI interaction verification using browser automation' names the domain and a couple of actions, but stays abstract rather than listing multiple concrete actions (e.g., screenshot comparison, form submission, axe scans) the way the score-3 anchor does.	2 / 3
Completeness	It states both what it does ('automate visual testing and UI interaction verification using browser automation') and an explicit when ('after deploying features'), satisfying the explicit-trigger requirement that would otherwise cap this at 2.	3 / 3
Trigger Term Quality	'visual testing', 'UI interaction verification', 'browser automation', and 'after deploying features' are relevant, but common user phrasings like 'test my UI', 'QA my site', or 'check my frontend after deploy' are missing, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The combination of post-deploy visual/UI verification via browser automation carves a clear niche unlikely to collide with general scraping or unit-testing skills.	3 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 4092795

Reviewed: 2 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.