CtrlK
BlogDocsLog inGet started
Tessl Logo

web-design-guidelines

前端 UI 审查清单:可读性、视觉密度、间距、响应式、空状态、加载态和可访问性。

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/web-design-guidelines/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The content is a compact, well-organized instruction-only checklist with concrete criteria and a defined output format; its only real weakness is minor non-functional padding (the migration note) and a few subjective checklist items.

DimensionReasoningScore

Conciseness

The body is lean with concise one-line checklist items and a brief output spec, but the 'PilotDeck Migration Note' section and the slightly redundant intro line ('helps the agent review whether the interface is usable, readable, responsive, and polished') are tokens that could be trimmed, so it stops short of the 5 'every token earns its place' anchor.

4 / 5

Actionability

For an instruction-only skill, the checklist gives concrete checkable criteria (e.g. 'keyboard focus, labels, alt text, contrast, reduced motion') and a defined output format, but a few items remain subjective ('feel consistent', 'no random palette mixing'), leaving minor gaps below the fully executable 5 anchor.

4 / 5

Workflow Clarity

The single review-then-report action is largely unambiguous with a specified output, and since this is a non-destructive read-only review the destructive/batch validation cap does not apply; it falls just short of 5 because there is no suggested ordering or prioritization for working through the eight checklist areas.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (none provided), and is organized into clear, well-signaled sections (Checklist, Output, Migration Note), meeting the rubric's simple-skill exception for a top progressive_disclosure score.

5 / 5

Total

17

/

20

Passed

Description

66%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 is specific and well-scoped to a frontend UI review checklist with natural Chinese trigger terms, but it lacks an explicit 'when to use' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause, e.g. '前端 UI 构建或修改后用于界面审查' to satisfy the completeness 'when' requirement.

Include a few common synonyms/variants (e.g. UI 检查、界面审查) and mention error state alongside empty/loading states for fuller trigger coverage.

Use third-person voice consistently and ensure the description states the concrete action (审查/检查) plus the trigger context in one sentence.

DimensionReasoningScore

Specificity

The description names a concrete domain (前端 UI 审查) and enumerates several specific review dimensions (可读性、视觉密度、间距、响应式、空状态、加载态、可访问性), giving comprehensive coverage with only a minor gap (no error state named), so it sits above the 1-2 action anchor at 3 but does not fully reach the multiple-distinct-actions bar of 5.

4 / 5

Completeness

It has a clear 'what' (a UI review checklist across named dimensions) but no explicit 'when'/'Use when' clause; per the rubric a missing explicit trigger clause caps completeness at 3, and it is not vague enough to fall to 2.

3 / 5

Trigger Term Quality

It contains natural terms a user would say (前端 UI、响应式、可访问性、空状态、加载态), but is missing common synonyms/variants (e.g. UI 检查、界面审查) and a 'Use when' trigger phrase, placing it just below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The niche (frontend UI design QA) is clearly scoped with distinct triggers and minimal overlap risk with adjacent review skills, but it could still lightly overlap generic accessibility or code-review skills, keeping it below the 5 anchor.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenBMB/PilotDeck
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.