Name: 1k-ui-verify
Rating: 64.8 (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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-ui-verify/SKILL.md

Quality

Content

90%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.

This is a strong, dense operational skill: executable commands for both platforms, real gotchas that could only come from experience, and clean push-down of detail into two rule files. The only notable gaps are an implicit validation loop in the workflow and a regression-runner path that does not resolve inside the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is entirely operational — a decision table, exact commands, and hard-won gotchas (perf-overlay swallowing taps, testID vs snapshot) with zero padding or explanation of concepts Claude already knows. Lean throughout; matches anchor 5 rather than 4 because there is nothing to trim.	5 / 5
Actionability	Copy-paste ready commands cover both backends and common cases: `node .skillshare/skills/1k-ui-verify/scripts/cdp-shot.mjs --testid header-gift-action --click --out ...`, `agent-device click 'id="home-more-button"'`, and `REGRESSION=1 node scenarios/regression.mjs gift-storm-desktop`. Fully executable guidance matching anchor 5.	5 / 5
Workflow Clarity	The 6-step checkbox workflow is clearly sequenced with BEFORE/AFTER screenshots and an evidence requirement ("do not claim 'fixed' without it"), and the RN section covers error recovery. Not 5 because there is no explicit validate→fix→retry loop in the workflow itself; checkpoints are present but partly implicit.	4 / 5
Progressive Disclosure	Good structure: an overview with a backend decision table, well-signaled one-level-deep references (references/rules/electron-cdp.md and references/rules/agent-device-rn.md both exist, as does scripts/cdp-shot.mjs). Not 5 because scenarios/regression.mjs is referenced with a whole section but is not present in the bundle, and /1k-dev-commands points outside the skill.	4 / 5
	Total	18 / 20 Passed

Description

67%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 clearly states what the skill does with concrete, tool-specific actions and an explicit use-when clause. Its main weakness is trigger coverage: only two narrow trigger phrases, one of which is Chinese, leaving common English phrasings uncovered.

Suggestions

Broaden the trigger clause to include English phrasings users would naturally say, e.g. "Use for UI verification, visual checks, or screenshot confirmation of the OneKey app".

Mention the regression-scenario capability (reproducible freeze/regression checks) in the description so that use case triggers the skill.

Add a boundary cue (e.g., desktop/iOS/Android only, web out of scope) to further reduce overlap with generic screenshot/verify skills.

Dimension	Reasoning	Score
Specificity	"Drive OneKey desktop or mobile apps to verify real visual and interactive behavior using CDP/Playwright or agent-device" names several concrete actions with specific tooling, matching anchor 4. Not 5 because coverage has minor gaps (e.g., regression scenarios and reporting are not mentioned).	4 / 5
Completeness	It has a clear "what" (drive OneKey apps to verify visual/interactive behavior) and an explicit "Use for..." when-clause with concrete trigger phrases. Not 5 because the when-clause is thin — only two triggers and no English equivalent.	4 / 5
Trigger Term Quality	Trigger phrases are limited to "UI 验证" and "screenshot confirmation" — some relevant keywords but missing common variations like English "UI verification", "visual check", or "screenshot the app". Anchor 3 fits better than 4 because keyword coverage is thin rather than good.	3 / 5
Distinctiveness Conflict Risk	"OneKey desktop or mobile apps" pins a clear niche with distinct tooling, but "screenshot confirmation" risks overlap with closely related generic skills (e.g., a generic launch/screenshot or verify-the-change skill). Mostly distinct with minor overlap risk — anchor 4, not 5.	4 / 5
	Total	15 / 20 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: 356c24e

Reviewed: 6 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.