seedance

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

Quality

88%

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 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, highly actionable prompt-engineering skill with concrete templates, examples, and a clear interaction workflow. Its main weaknesses are verbosity (repeated examples) and a monolithic structure with no progressive disclosure via reference files.

Suggestions

Move the 镜头语言词汇库 and 风格词汇库 tables and the per-capability example banks into separate reference files (e.g. references/vocabulary.md, references/examples.md) and link to them from SKILL.md to reduce the inline footprint.

Trim each of the ten capability sections to a single representative example prompt instead of 2-3, keeping the prompt-pattern template as the primary guidance.

Consider splitting the 超长视频分段拼接策略 and 输出格式 details into a reference file, leaving SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The content is domain-specific and actionable rather than explaining generic concepts Claude knows, but the ~580-line body repeats 2-3 full example prompts per capability and could be tightened; vocabulary tables and example banks pad the token budget.	2 / 3
Actionability	Provides concrete prompt-pattern templates, copy-paste-ready full example prompts, exact @-reference naming conventions (@图片1, @视频1), and specific parameter specs — directly executable guidance.	3 / 3
Workflow Clarity	Clear sequenced interaction flow (第一步获取输入 through 第四步微调优化) plus the超长视频分段策略 with explicit衔接点 checkpoints and a 注意事项 verification checklist covering @-reference labeling.	3 / 3
Progressive Disclosure	Well-organized into thematic sections, but entirely monolithic (~580 lines, no bundle files present); vocabulary libraries and per-capability example banks that could live in separate reference files are inline, so it does not qualify for the simple-skill exception.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, well-constructed description that explicitly states both what the skill does and when to use it, with rich bilingual trigger terms and a clear niche. No significant weaknesses; written in third person about the skill, incurring no voice penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'generate video prompts', 'create Seedance prompts', 'write video descriptions' — matching the anchor for several specific concrete actions rather than vague language.	3 / 3
Completeness	The explicit 'This skill should be used when the user asks to...' clause supplies the 'when', while the quoted actions supply the 'what', answering both clearly with explicit triggers.	3 / 3
Trigger Term Quality	Broad coverage of natural user terms in both English and Chinese ('Seedance', '即梦', '视频提示词', 'AI视频', '短剧', '视频延长'), terms a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Niche, product-specific triggers (Seedance 2.0, 即梦平台) give it a clear, narrow domain unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (581 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: songguoxs/seedance-prompt-skill
Path: .claude/skills/seedance/SKILL.md
Commit: 57d1e2f

Reviewed: 2 months 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.