CtrlK
BlogDocsLog inGet started
Tessl Logo

video-creation-pro

10大智能体协同的商品视频创作系统,全流程质量闭环(创作→质检→反馈迭代),强制使用COZE视频大模型API进行视频合成,彻底移除本地依赖包逻辑,适用于智能硬件、美妆护肤、家居家电等多品类商品视频创作

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/video-creation-pro/video-creation-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 body is a well-sequenced, validation-rich orchestration workflow with good reference structure, but it is heavily padded by repeated constraints and lacks the concrete COZE API call detail needed to make the core synthesis step fully executable.

Suggestions

State the 'no local dependency packages / COZE API only' constraint once in 前置准备 and remove its repetition from each of the ten agent sections to recover significant tokens.

Add a concrete COZE video API invocation example in 步骤8 (endpoint, request payload with the listed params, and response handling) so the synthesis step is copy-paste executable.

Reconcile the bundled scripts/ (video_composer.py, image_quality_checker.py) with the body — either reference and use them or remove them, since the body states '必要脚本:无'.

DimensionReasoningScore

Conciseness

The same mantras ('强制使用COZE视频大模型API', '无本地依赖包调用', '彻底移除本地依赖包逻辑') are restated in nearly every agent's 角色定位/输出标准/协同规则/核心禁忌, producing noticeably verbose, padded sections that assume Claude needs the same constraint repeated ten times.

2 / 5

Actionability

Specific numerical specs are present (1080P, 25fps, transitions 0.3-0.5s, audio offset ≤0.1s, retry ≤3/timeout 10s, JPG/PNG/MP3/MP4), but the actual COZE API invocation is never shown (no endpoint, request format, or parameter payload), and the bundled scripts/ files are unreferenced while the body claims '必要脚本:无'.

3 / 5

Workflow Clarity

A clearly sequenced 10-step pipeline with a flow diagram, a dedicated 质检智能体 step, defect grading, interception/remediation, an API retry mechanism, and redraw feedback loops provide explicit validation checkpoints and error-recovery loops.

5 / 5

Progressive Disclosure

The 资源索引 section signals six one-level-deep references (all verified to exist) with clear markdown links, but the ~340-line body inlines full per-agent detail that overlaps with the separate references/agent_specs.md, leaving a minor organization gap.

4 / 5

Total

14

/

20

Passed

Description

53%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 conveys a clear niche and several specific facets but reads as a system description rather than an action list, lacks an explicit 'Use when' trigger, and leans heavily on internal jargon over natural user phrases.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to create product/commerce short videos (商品视频、带货视频、电商短视频) for smart hardware, beauty, or home appliances.'

Lead with concrete actions the skill performs (e.g. '提炼卖点、生成分镜图片、合成视频、质检迭代') instead of leading with system/architecture phrasing.

Replace internal jargon ('质量闭环', '本地依赖包逻辑') in the description with user-facing terms, or move implementation constraints into the body.

DimensionReasoningScore

Specificity

Names the domain ('商品视频创作系统') and several facets ('创作→质检→反馈迭代', 'COZE视频大模型API进行视频合成', '多品类'), but presents a system description rather than a discrete list of concrete actions like 'extract/fill/merge'.

3 / 5

Completeness

The 'what' is reasonably clear, but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied via '适用于...多品类商品视频创作', which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes some natural terms ('商品视频创作', '视频合成', category names like 美妆护肤/家居家电), but is dominated by internal jargon ('COZE视频大模型API', '本地依赖包', '质量闭环') and misses common synonyms users would say (短视频/带货视频/电商视频).

3 / 5

Distinctiveness Conflict Risk

The product/commerce-video niche combined with the COZE-API-only constraint makes it mostly distinct from generic video skills, with only minor overlap risk against closely related video-creation skills.

4 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
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.