CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

motion-showreel

用代码制作图形、文字或界面动画视频,输出 MP4 和可编辑源码,最长 20 分钟。适用于动效作品集、产品片、UI 动效、动态排版、Logo 片头、生成艺术与讲解视频;支持独立选择 BGM/音效来源、用户口播,以及用用户提供的口播稿通过 TTS 合成语音。不用于实拍制作、写实人物生成或一般视频剪辑。

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 highly actionable, well-sequenced complex workflow skill with excellent bundle navigation and executable commands at every step. Its main weakness is token efficiency: the preview/confirmation policy and proxy-rendering rules are repeated across several sections and could be consolidated.

Suggestions

Consolidate the preview-before-export and confirmation-gating rules (currently restated in the intro, 第 1 步, 放手模式, 第 3 步, 第 6 步, and 底线 1) into one canonical section, leaving step-specific sections with only a short pointer.

Deduplicate the proxy-MP4 guidance: 「不默认生成代理 MP4 或整片样片」 and 「不默认渲染低清代理或 MP4 小样」 appear in 第 4 步 and 第 6 步 — state the rule once and reference it.

Tighten the long prose paragraphs in 第 1 步 and 第 3 步 into the existing table/bullet format used elsewhere; several sentences restate the 'confirm before proceeding' principle with only slight variation.

DimensionReasoningScore

Conciseness

The body is dense and mostly operational, but the preview/confirmation gating is restated repeatedly — 「停下来等用户确认,再写 brief」(第 1 步), 「真的等用户回复」(第 3 步), 「只有用户点击『导出视频』…才进入下一步」(第 6 步), and again in 底线 1 — and 「不默认渲染低清代理或 MP4 小样」 appears in both 第 4 步 and 第 6 步. Consolidating these into one canonical confirmation section would trim meaningful tokens without losing clarity. Not 4: the repetition goes beyond minor instances that could be trimmed; not 2 because the text never explains generic concepts and nearly every paragraph carries skill-specific decisions.

3 / 5

Actionability

Fully executable commands cover every stage: 「sh <skill>/scripts/scaffold.sh <slug> [--audio synth|tone|layer|file|none]」, 「node <skill>/scripts/inspect.mjs qa <slug>/out/final.mp4 --out <slug>/qa/final --expect-size 1920x1080 --expect-fps 30 --expect-duration 16 --audio required」, plus a concrete YAML brief template, an audio-engine selection table, and hard rules with real syntax like 「revealOn(拍点, 转场时长, 揭开点)」 and 「[[b(36), DUR]]」. Copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

An 8-step workflow with explicit user-confirmation checkpoints (🛑 等用户确认 at steps 1, 3, and 6), programmatic validation gates — 「跑确定性检查 render.mjs <slug> --determinism,不通过就先修」 and 「只要有一项 FAIL,退出码就是 1,必须修好」 — and feedback loops (「修完只重渲有问题的那一段,再出整片」). Sequencing, checkpoints, and error recovery are all explicit.

5 / 5

Progressive Disclosure

The 「参考文件(按需读)」 table maps each of the 12 reference files to exactly when to read it, with targeted guidance like 「只读对应的那一节」 and 「先看 references/styles/INDEX.md,再只读选中的 1–2 个风格文件」. Every referenced path (including styles/INDEX.md, _template.md, and all 43 style files) exists in the bundle, references are one level deep and clearly signaled, and the SKILL.md body stays an operational overview while detail lives in the bundle.

5 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: concrete actions, explicit positive and negative triggers, natural terminology, and a clear niche — all in third person and without padding. It answers both what the skill does and when to use it unambiguously.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 「用代码制作图形、文字或界面动画视频,输出 MP4 和可编辑源码,最长 20 分钟」 plus 「支持独立选择 BGM/音效来源、用户口播,以及…TTS 合成语音」 — covering rendering, output format, duration, audio sourcing, and narration modes comprehensively. Not 4: there are no coverage gaps; the action list spans the full pipeline from creation to delivery.

5 / 5

Completeness

Both what and when are explicit: what = 「输出 MP4 和可编辑源码,最长 20 分钟」 with concrete capabilities; when = 「适用于…」 listing seven trigger scenarios plus explicit negative triggers 「不用于实拍制作、写实人物生成或一般视频剪辑」. Written in third person with no fluff.

5 / 5

Trigger Term Quality

Natural user vocabulary is comprehensive: 「动效作品集、产品片、UI 动效、动态排版、Logo 片头、生成艺术与讲解视频」 plus 「BGM」「音效」「口播」「TTS」. These are the phrases a user would naturally say when requesting this skill; no common synonyms for the domain are missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (code-driven motion graphics up to 20 minutes) with explicit exclusions that separate it from live-action, realistic-character generation, and general video-editing skills. Triggers like 「Logo 片头」「动态排版」「TTS 合成语音」 are distinct to this skill with minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

ConardLi/garden-skills

Path

skills/motion-showreel/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.