ui-demo

录制精美的产品 UI demo 视频。当用户需要录制演示视频、功能演示、操作教程或利益相关方展示视频时使用。输出带可见鼠标、自然节奏和专业字幕的 WebM 视频。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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

Highly actionable content with executable code and an explicit, validated three-phase workflow. Its weaknesses are length/duplication (two full script templates) and a monolithic structure with no external references for the sizable Screencast material.

Suggestions

Collapse the two full script templates into one canonical template and describe the Screencast alternative as a delta (call swaps) to cut duplication and tokens.

Move the Screencast API comparison table and its template into a references/ file (e.g. SCREENCAST.md) referenced one level deep, improving progressive disclosure for this large skill.

Tighten 'Browser Operation Best Practices' by merging the items that restate 'Common Pitfalls' (e.g. fill() on rich-text editors) to a single authoritative section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (patchright, CDP, no basic-concept padding), but ~479 lines include two near-complete script templates (manual injection and Screencast) plus helper functions whose duplication could be tightened. Not a level-1 wall of concept-explanation, but not the lean 'every token earns its place' of level 3 either.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code — complete injectCursor/injectSubtitleBar/showSubtitle/moveAndClick/typeSlowly helpers, full script templates, and a concrete run command (`node demo-script.cjs`). No pseudocode gaps.	3 / 3
Workflow Clarity	A clearly sequenced Discover→Rehearse→Record three-phase process with an explicit '禁止跳过直接录制' rule, a pre-recording Checklist, and validation/feedback loops (Phase 2 '修正字段映射再重试', the 30s→60s browser-timeout retry ladder).	3 / 3
Progressive Disclosure	Well-organized into headed sections, but no bundle files exist and the whole skill is one ~479-line monolith; full script templates and the Screencast API alternative are inline content that could be split into one-level-deep references. Structure is present but content that should be separate is inline, matching the level-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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: third-person voice ("录制"/"输出"), concrete capabilities, and an explicit 'Use when' trigger covering several natural phrasings. It clearly distinguishes the skill and answers both what and when.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "录制精美的产品 UI demo 视频" and "输出带可见鼠标、自然节奏和专业字幕的 WebM 视频" — matching the anchor that lists several specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (record UI demo videos, output WebM with mouse/pacing/subtitles) and when via the "当用户需要…时使用" clause, which is an explicit trigger equivalent to 'Use when...'.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — "演示视频、功能演示、操作教程或利益相关方展示视频" — giving good breadth of trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	A clear niche — UI demo video recording with visible cursor, pacing and subtitles in WebM — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/content-producer/skills/ui-demo/SKILL.md
Commit: bcef823

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.