CtrlK
BlogDocsLog inGet started
Tessl Logo

product-video-creator

多智能体协同的商品视频创作流水线,支持从商品信息到成视频的全流程创作:文案生成、故事策划、脚本创作、分镜设计、图片生成、字幕创作、音效推荐及视频合成;适用于电商商品宣传、品牌推广、社交媒体营销等场景

63

Quality

75%

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/product-video-creator/product-video-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured multi-agent pipeline with clear sequencing, a real executable synthesis step, and excellent progressive disclosure via annotated references. Main weaknesses are redundancy from three restated examples and the absence of an explicit error-recovery feedback loop around video synthesis.

Suggestions

Collapse the three worked examples into one compact example plus a short table of variants (duration/audience/style), cutting significant redundant length.

Add an explicit validate→fix→retry loop to step 8 (e.g., 'If validation fails, review the error, fix the offending asset/JSON, and re-run composer before delivering').

Surface the expected subtitles.json schema inline or via the subtitle_format.md reference so the synthesis step is fully executable without inference.

DimensionReasoningScore

Conciseness

It avoids over-explaining concepts Claude already knows and is well structured, but the three worked examples (示例1–3) largely restate the eight steps with minor variations, adding noticeable length that could be trimmed. Not a 4 because the redundancy is more than minor; not a 2 because the prose itself is not padded with background explanation.

3 / 5

Actionability

Provides a copy-paste-ready video_composer.py invocation with full flags plus concrete specs (1920x1080, 24fps, scene_001.jpg naming, 字幕≤20字, 画面下方1/3处). Not a 5 because the creative steps rely on directional guidance rather than fully executable instructions for every common case.

4 / 5

Workflow Clarity

Eight clearly sequenced steps each with 职责/执行要点/输出, a final '验证视频质量' checkpoint, and a self-evaluation note. Not a 5 because there is no explicit validate→fix→retry error-recovery feedback loop for the synthesis step; not a 3 because validation is present rather than absent.

4 / 5

Progressive Disclosure

SKILL.md is an overview with a 资源索引 pointing to real one-level-deep bundle files (storyboard_format.md, subtitle_format.md, video_specs.md, video_composer.py), each annotated with its purpose and a 何时读取 trigger — easy to navigate and appropriately split.

5 / 5

Total

16

/

20

Passed

Description

80%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.

A strong, specific description that names the full multi-agent pipeline and concrete use-case scenarios. It would reach the top band by recasting the applicability clause as an explicit 'Use when the user asks for…' trigger with natural phrasing variations.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks for a product promo video, e-commerce video, or social-media marketing video' to lift completeness and trigger-term quality.

Include natural phrasing variations and synonyms (e.g., '商品宣传视频、短视频、广告视频、带货视频') so it matches how users actually phrase the request.

Clarify the output artifact (final MP4) in the description itself so the 'what' is unambiguous at a glance.

DimensionReasoningScore

Specificity

Lists eight concrete pipeline actions (文案生成、故事策划、脚本创作、分镜设计、图片生成、字幕创作、音效推荐、视频合成), giving comprehensive coverage of the full creation flow.

5 / 5

Completeness

Clearly states what the skill does (multi-agent product-video pipeline) and when (适用于…场景 with concrete scenarios), but the 'when' is framed as applicability rather than an explicit 'Use when the user says…' trigger phrase, so it stops short of the top anchor.

4 / 5

Trigger Term Quality

Provides concrete scenario terms (电商商品宣传、品牌推广、社交媒体营销) users would naturally reference, but omits common phrasing variations and synonyms. Not a 3 because coverage is genuinely good; not a 5 because it lacks the natural variations and file-extension-style triggers of the top anchor.

4 / 5

Distinctiveness Conflict Risk

The product-video creation pipeline is a clear niche with distinct triggers, with only minor overlap risk against generic image-generation or copywriting skills. Not a 5 because that breadth still invites some overlap.

4 / 5

Total

17

/

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.