three-body-video-creator

影片与视频编辑和内容创作者必备！当需要制作《三体》主题视频时，自动化完成选题策划、视觉设计、音频生成到成片合成，多智能体协作流程，3小时搞定72小时工作量。

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 body is a well-structured, actionable multi-agent workflow with strong sequencing, validation gates, feedback loops, and clean progressive disclosure to real bundle files. Its weak point is conciseness — repeated character-voice descriptions and a 使用示例 section that re-lists the 15 steps add padding.

Suggestions

De-duplicate the character-voice descriptions: keep them once in 步骤10 (配音指导) and reference rather than re-stating them in 步骤3.

Trim the 使用示例 section so it shows genuinely distinct invocations (e.g. end-to-end CLI call, the quality_checker snippet) instead of re-listing steps 1-15 already covered in 操作步骤.

Replace placeholder inputs like '<旁白数据JSON>' with a concrete example file path or a one-line schema note to close the minor actionability gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific detail (三体 settings, character voices, color codes) earns its place, but character-voice descriptions are repeated across 步骤3 and 步骤10 and the 使用示例 section re-treads the already-listed 15 steps, so it could be tightened; not a 4 because the redundancy is noticeable rather than minor.	3 / 5
Actionability	Provides concrete executable script invocations with real flags ('scripts/voice_generator.py --input <旁白数据JSON> --output ./output/audio/voice', 'scripts/video_compositor.py --images ... --audio ... --subtitles ... --output ...') and a runnable Python example, with only minor gaps (placeholder input JSON paths, some purely descriptive creative steps).	4 / 5
Workflow Clarity	15 steps are sequenced across 3 timed phases with three explicit validation gates (步骤12 合规检测, 步骤13 技术指标检测, 步骤15 五维评审 with ≥80分 threshold) plus an 可选分支 feedback-loop section for error recovery, matching the 5-anchor; the destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Clear overview body points via well-signaled one-level-deep links to real references/, assets/, and scripts/ bundles, and the 资源索引 even annotates '何时读取' for each reference, giving easy navigation that matches the 5-anchor.	5 / 5
	Total	17 / 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 cleanly states both capability and trigger for a well-scoped niche, with concrete pipeline actions and a natural trigger phrase. Its main weakness is marketing padding ('创作者必备', '3小时搞定72小时工作量') that dilutes specificity and adds over-claim.

Suggestions

Drop the marketing clause '影片与视频编辑和内容创作者必备！3小时搞定72小时工作量' to remove over-claim and tighten specificity.

Add a few natural synonyms/format terms (e.g. '三体短片, 动画, 视频成片, .mp4') to lift trigger-term coverage toward comprehensive.

Lead with the concrete action list ('选题策划、视觉设计、音频生成、成片合成') before the trigger clause so capabilities read as standalone verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('选题策划、视觉设计、音频生成到成片合成') covering the pipeline, but they are framed inside marketing fluff ('创作者必备', '3小时搞定72小时工作量') rather than presented as clean standalone capabilities, leaving minor gaps versus the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('自动化完成选题策划、视觉设计、音频生成到成片合成') and 'when' ('当需要制作《三体》主题视频时') with a concrete trigger phrase, matching the 5-anchor; not downgraded because neither component is vague.	5 / 5
Trigger Term Quality	Natural trigger phrasing is present ('当需要制作《三体》主题视频时', '视频编辑', '内容创作者') with good keyword coverage, but synonyms and format extensions (e.g. 短片, 动画, .mp4) are missing, so it falls just below the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly bounded niche ('《三体》主题视频') with a distinct trigger unlikely to fire for unrelated skills, matching the 5-anchor for minimal conflict risk.	5 / 5
	Total	18 / 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/three-body-video-creator/three-body-video-creator/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.