product-video-creator

电商运营与内容创作者在制作商品宣传、带货及社媒营销视频时，使用此多智能体协同流水线，一键自动完成卖点文案、故事分镜、场景图片、音效字幕到MP4视频合成的全流程，高效产出专业级营销视频，大幅节省制作成本与时间。

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%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, actionable multi-agent pipeline with concrete parameters and clean progressive disclosure. The main weaknesses are repetitive examples and the absence of an explicit validation feedback loop for the batch video-render step.

Suggestions

Add an explicit validate→fix→retry checkpoint around step 8 (e.g., run the composer, check resolution/fps/audio-sync, and if failing fix inputs and re-run) so the batch render has a real feedback loop.

Collapse the three full example walkthroughs into one detailed example plus a compact table summarizing how 15s/30s/60s variants differ in shot count and style, reducing repetition.

Note in step 5 how to verify generated images (count, resolution, style consistency) before passing them to the composer, giving an intermediate validation checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient task guidance without explaining concepts Claude already knows, but the three near-identical example walkthroughs (each re-listing all 8 steps) add notable repetition that could be tightened.	3 / 5
Actionability	Provides a copy-paste-ready composer invocation with concrete flags (--images, --subtitles, --audio, --fps, --duration) plus specific parameters throughout (1920x1080, scene_001.jpg, subtitles ≤20 chars, bottom 1/3 placement).	5 / 5
Workflow Clarity	Eight steps are clearly sequenced with 职责/执行要点/输出, but this batch render operation lacks an explicit validate→fix→retry feedback loop; verification is only an implicit bullet in step 8, capping the score per the batch-operation rule.	3 / 5
Progressive Disclosure	SKILL.md serves as an orchestration overview with well-signaled one-level-deep references (storyboard_format.md, subtitle_format.md, video_specs.md, video_composer.py — all real files) annotated with 何时读取 navigation cues.	5 / 5
	Total	16 / 20 Passed

Description

92%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 specific, well-targeted description that clearly states what the skill does and when to use it, with natural Chinese e-commerce trigger terms. Only minor gap is the absence of file-extension keywords.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — 卖点文案、故事分镜、场景图片、音效字幕到MP4视频合成 — giving comprehensive coverage of the full workflow rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (multi-agent pipeline completing copy→storyboard→images→audio/subtitles→MP4) and 'when' (电商运营与内容创作者在制作商品宣传、带货及社媒营销视频时) with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural terms users say (商品宣传视频、带货、社媒营销视频、营销视频) with good synonym coverage, but omits file-extension triggers like .mp4 and a few common phrasings.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (e-commerce product/marketing video creation) with distinct triggers (带货, 商品宣传视频) that minimize overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/product-video-creator/product-video-creator/SKILL.md
Commit: 6bd4418

Reviewed: 5 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.