CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-browser-ui

Test web UI across Chromium, Firefox, WebKit, mobile viewports, and real iOS Safari, capturing console errors, failed requests, layout overflow, broken images, and visual defects with screenshots and traces. Use for any UI, smoke, cross-browser, mobile, or visual testing.

71

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 tight, checklist-driven testing skill with explicit flakiness handling, INCONCLUSIVE gating, and exit criteria that make the workflow easy to follow end to end. Its weaknesses are the undefined 'pattern D1–D5' and 'Round 1' references and the absence of a minimal executable Playwright example. These are minor gaps in an otherwise actionable and efficient body.

Suggestions

Define or remove the 'pattern D1/D2/D4/D5' labels — either point them at a real patterns reference file in the bundle or inline the one-line pattern descriptions so the pointers resolve.

Drop or contextualize '(found in Round 1)', since 'Round 1' is undefined in this skill and adds confusion without adding guidance.

Add a minimal copy-paste Playwright config snippet (projects + trace/video/HAR settings) to make the Setup section fully executable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (e.g., 'Playwright projects: desktop chromium/firefox/webkit at 1280... plus video and HAR', 'Console: zero errors, and every warning reviewed'), but tokens like '(pattern D1)', '(pattern D5)', and '(found in Round 1)' reference things undefined anywhere in the bundle and could be trimmed.

4 / 5

Actionability

Guidance is mostly executable with exact expressions ('document.documentElement.scrollWidth <= document.documentElement.clientWidth', 'img.complete && img.naturalWidth > 0', 'toMatchAriaSnapshot') and concrete configs, but there is no complete copy-paste test example and the 'pattern D1/D2/D4/D5' pointers lead to no actual definitions.

4 / 5

Workflow Clarity

A clear sequence (Setup → numbered per-route checks → interaction checks → Evidence → Exit criteria) with explicit validation and feedback loops: 'reload up to 3 times and record the flaky count', 'mark that route's content checks INCONCLUSIVE', and downstream INCONCLUSIVE marking until rerun on isolated state.

5 / 5

Progressive Disclosure

With no bundle files and a ~32-line body of well-organized sections, structure is good, but the dangling 'pattern D1/D5/D4/D2' references imply a patterns catalog that does not exist in the bundle, leaving navigation slightly incomplete.

4 / 5

Total

17

/

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 that states concrete capabilities in third person and pairs them with an explicit, trigger-phrase-driven 'Use when' clause. Its only weakness is trigger-term coverage that omits several natural synonyms users might say. It is clearly distinct from generic testing skills.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions and artifacts ('capturing console errors, failed requests, layout overflow, broken images, and visual defects with screenshots and traces') across named engines (Chromium, Firefox, WebKit, mobile viewports, real iOS Safari), giving comprehensive capability coverage in third-person voice.

5 / 5

Completeness

Both what and when are explicitly stated: the first sentence concretely describes capabilities and the second gives an explicit 'Use for...' clause with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

'Use for any UI, smoke, cross-browser, mobile, or visual testing' provides good natural trigger phrases, but common variations users would say are missing (e.g., 'browser testing', 'end-to-end/e2e', 'regression', 'Playwright', 'Safari testing').

4 / 5

Distinctiveness Conflict Risk

The niche (cross-browser/mobile UI testing with named engines and defect types) is clear with distinct triggers like 'cross-browser', 'mobile', and 'visual testing', minimizing conflict with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

itsablabla/qa-bug-agent-skills

Path

skills/qa-browser-ui/SKILL.md

Reviewed

Table of Contents

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.