Name: 1k-ui-verify
Rating: 73.6 (1 reviews)
Author: OneKeyHQ

1k-ui-verify

Drive OneKey desktop or mobile apps to verify real visual and interactive behavior using CDP/Playwright or agent-device. Use for UI 验证 or screenshot confirmation.

Quality

92%

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

100%

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

A tight, highly actionable skill body: executable recipes on both backends, a sequenced workflow with screenshot-evidence validation, and clean one-level-deep references to the detail files. Little to improve.

Dimension	Reasoning	Score
Conciseness	Lean and command-dense throughout — a backend decision table, quick recipes, and scenario invocations with no padding explaining concepts Claude already knows; every line carries executable guidance or a justified gotcha.	3 / 3
Actionability	Fully executable, copy-paste-ready commands with concrete testIDs and script paths (e.g. 'node .skillshare/skills/1k-ui-verify/scripts/cdp-shot.mjs --testid header-gift-action --click'), not pseudocode or vague direction.	3 / 3
Workflow Clarity	A 6-step sequenced checklist with explicit verification checkpoints — BEFORE/AFTER screenshots, console/log capture, and 'do not claim fixed without it' — plus a CI-gate (REGRESSION=1 exit 1) feedback loop.	3 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real files (electron-cdp.md, agent-device-rn.md) for full patterns/pitfalls, keeping the body a navigable index rather than a monolith.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 concise, specific description that covers both what the skill does and when to use it, scoped tightly to OneKey apps. Trigger-term coverage is the weakest dimension — only a couple of natural phrases with limited variation.

Suggestions

Broaden trigger terms to common English variations a user would naturally say, e.g. 'Use for UI verification, visual regression checks, or screenshot confirmation of a change'.

Add the user-facing noun forms ('screenshot', 'visual check', 'confirm a UI change') alongside 'UI 验证' so the trigger fires regardless of language.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Drive OneKey desktop or mobile apps to verify real visual and interactive behavior' — and names the specific tools (CDP/Playwright, agent-device) rather than staying abstract.	3 / 3
Completeness	Explicitly answers both what ('Drive OneKey... apps to verify real visual and interactive behavior') and when via the explicit 'Use for UI 验证 or screenshot confirmation' trigger clause.	3 / 3
Trigger Term Quality	Includes natural trigger phrases ('UI 验证', 'screenshot confirmation') a user might say, but coverage is narrow with few common variations and the rest is technical jargon (CDP/Playwright, agent-device).	2 / 3
Distinctiveness Conflict Risk	Scoped to OneKey desktop/mobile apps with specific tooling, giving it a clear niche and distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: OneKeyHQ/app-monorepo
Path: .skillshare/skills/1k-ui-verify/SKILL.md
Commit: e0fcee5

Reviewed: about 3 hours 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.