video-creation-collaborator

内容创作者与自媒体创作者在制作短视频时，若遇生图畸形、合成瑕疵或协同混乱，当需规范化多智能体流程时必用此技能。一键调度11个AI智能体，自动完成文案、分镜、音视频到视频合成的5阶段闭环，前置质检拦截瑕疵，高效产出统一可控的高质量短视频。

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

77%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 content is highly actionable with a clear, validated multi-stage workflow, but loses points on conciseness (repetition) and progressive disclosure (broken references and inlined detail that belongs in the reference files).

Suggestions

Fix or remove the missing references: create references/data-analysis.md, scripts/music_generator.py, and scripts/audio_quality_checker.py, or remove their links from the body.

Deduplicate the quality-check instructions (merge '质量检测工具使用' and '质量检测流程' into one section) to reduce token overhead.

Move the full 11-agent responsibility breakdown into references/agent-prompts.md and keep only a concise role/trigger summary inline, so the SKILL.md body stays an overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient and free of basic-concept padding, but ~500 lines with notable repetition (quality-check usage appears in both '质量检测工具使用' and '质量检测流程', and JSON configs are repeated), so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash and python commands with real paths, arguments, and full JSON config examples covering the common cases (image/audio/subtitle generation, video compositing, quality checks).	5 / 5
Workflow Clarity	Clear 5-stage sequence with explicit trigger nodes, per-agent '下一级触发' handoffs, and explicit validation/feedback loops ('前置质检拦截', '不合格驳回', detect anomaly -> regenerate -> recheck), so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	Has a clear '资源索引' and inline '参考:' links to one-level-deep references, but three referenced paths do not exist in the bundle (references/data-analysis.md, scripts/music_generator.py, scripts/audio_quality_checker.py) and substantial 11-agent detail is inlined rather than delegated.	3 / 5
	Total	16 / 20 Passed

Description

87%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 is strong: it states concrete capabilities, gives explicit 'use when' triggers tied to recognizable creator pain points, and occupies a distinct niche. Minor weakness is trigger-term jargon density that could include more everyday synonyms.

Suggestions

Add a few plain-language trigger synonyms alongside the jargon (e.g. '做短视频/拍短视频', 'AI生成图片出错', '多智能体协作') so users phrase it more naturally.

Trim domain-internal terms like '多智能体协同流程' in favor of user-facing phrasing to improve naturalness of the trigger clause.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('一键调度11个AI智能体', '自动完成文案、分镜、音视频到视频合成', '前置质检拦截瑕疵', '5阶段闭环'), with only minor coverage gaps; not a comprehensive 5-level list.	4 / 5
Completeness	Explicitly answers both what ('一键调度11个AI智能体...5阶段闭环...前置质检拦截瑕疵') and when ('制作短视频时，若遇生图畸形、合成瑕疵或协同混乱，当需规范化多智能体流程时必用') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a creator might say ('制作短视频', '生图畸形', '合成瑕疵', '协同混乱') alongside jargon ('多智能体'), with good keyword coverage but a few common synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-agent short-video creation pipeline keyed to specific defect types like 生图畸形/合成瑕疵) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (507 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 6 missing, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: anbeime/skill
Path: skills/video-creation-collaborator/video-creation-collaborator/SKILL.md
Commit: d9e888d

Reviewed: 2 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.