browser-qa

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

75%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.

A well-structured, actionable browser-QA skill with explicit safety/blast-radius guidance, concrete metric thresholds, and a clean report template. The main gaps are a missing fix→retry feedback loop and the absence of any concrete MCP tool invocation example.

Suggestions

Add one short executable MCP example (e.g. a claude-in-chrome navigate+screenshot call) to push actionability toward 5.

Add an explicit feedback loop such as 'if smoke test fails, capture the failing request/console error, fix, and re-run before proceeding to Phase 2.'

Move the INP/FID date note into a short 'Deprecated metrics' aside so time-sensitive info does not sit inline in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and almost every line earns its place — concrete thresholds, a compact output template, and a justified safety section; the inline 'INP replaced FID in March 2024' note is time-sensitive but brief and error-preventing rather than padded.	4 / 5
Actionability	Instruction-only but highly actionable: exact Core Web Vitals thresholds, breakpoint pixel widths (375/768/1440), WCAG 2.2 AA level, named MCP tools, and a copy-ready report template with a verdict enum; minor gap is the absence of any concrete MCP invocation example.	4 / 5
Workflow Clarity	Four phases are clearly sequenced with verification checkpoints (console/network checks, INCONCLUSIVE-on-missing-baseline rule, verdict enum, metric pass/fail gates), but there is no explicit fix→retry feedback loop for failed checks.	4 / 5
Progressive Disclosure	Well-sectioned into When/How/Phases/Output/Integration with no nested references and a self-contained body; at ~100 lines it is slightly above the simple-skill 50-line threshold so it stops short of a 5 despite strong organization.	4 / 5
	Total	16 / 20 Passed

Description

57%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 answers both 'what' and 'when' and carves out a distinct niche, but it leans on a single trigger phrase and uses second-person imperative voice ('Use this skill to…') which the rubric penalizes. Tightening voice to third person and adding common synonyms (QA, regression, screenshots) would raise it.

Suggestions

Rewrite in third person (e.g. 'Automates visual testing and UI interaction verification via browser automation…') to avoid the second-person specificity penalty.

Add 1-2 more natural trigger phrases such as 'Use when reviewing frontend PRs, running regression checks, or verifying UI after a deploy.'

Include common synonyms users actually say — 'QA', 'regression testing', 'screenshots', 'e2e' — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('automate visual testing and UI interaction verification using browser automation'), which is a baseline 3, but the imperative 'Use this skill to…' is second-person voice and the rubric penalizes that by -1.	2 / 5
Completeness	Clearly states what it does (automate visual/UI testing via browser automation) and when to use it ('after deploying features'), but the 'when' is a single trigger rather than multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms like 'visual testing', 'UI interaction verification', and 'after deploying features', but misses common synonyms users would say such as QA, regression testing, screenshots, or e2e/frontend testing.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (post-deploy browser QA / visual testing) with distinct triggers and minimal conflict risk, with only minor overlap against general testing skills.	4 / 5
	Total	13 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/browser-qa/SKILL.md
Commit: 06c5e11

Reviewed: 3 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.