seedance

Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.

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

65%

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 complete executable commands and a clear async workflow, but it is verbose (redundant example/scenario blocks and generic prompt tips) and monolithic rather than progressively split into reference files. Verification of generated output is also missing for a batch operation.

Suggestions

Consolidate the five '使用示例' and four '常见使用场景' sections to remove redundant near-identical command invocations, or move scenarios into a separate reference file.

Add an explicit output-verification step to the workflow (e.g., confirm the downloaded MP4 is non-empty and a valid media file) so the batch generation loop closes with a real checkpoint.

Move the detailed model catalog, error catalog, and prompt best-practices into one-level-deep reference files (e.g., MODELS.md, TROUBLESHOOTING.md) referenced from a leaner SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly domain-specific and useful, but it is padded: 5 '使用示例' plus 4 '常见使用场景' repeat the same bash invocation pattern, and the '提示词最佳实践' section restates fairly generic guidance, so it could be tightened.	2 / 3
Actionability	Provides fully executable bash commands with real flags, model IDs, URLs, and a parameter table with defaults and valid ranges — copy-paste ready, matching the top anchor.	3 / 3
Workflow Clarity	The submit→poll→download sequence is clear with a status table and an error-recovery section, but for this batch/async generation there is no explicit verification of the downloaded output (e.g., check the MP4 is non-empty/valid), and the rubric caps batch-operation workflows at 2 when verification is missing.	2 / 3
Progressive Disclosure	Bundle scripts are correctly referenced one level deep via a consistent $SKILLS_ROOT path, but SKILL.md itself is a ~450-line monolith with the model catalog, error catalog, and prompt tips kept inline rather than split into well-signaled reference files.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 concise, third-person, names concrete capabilities, and includes an explicit 'Use this skill when' trigger. It cleanly satisfies all four dimensions at the top of the scale.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'text-to-video (T2V), image-to-video (I2V), and audio-synced video generation' — matching the anchor that lists several specific capabilities rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Generate AI videos... Supports...') and when via an explicit 'Use this skill when the user wants to create or generate videos' trigger clause, matching the top anchor.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('create or generate videos', 'AI videos') alongside the model name; not merely technical jargon, matching the good natural-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'Volcengine Seedance model' AI video generation with distinct triggers, a clear niche unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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: netease-youdao/LobsterAI
Path: SKILLs/seedance/SKILL.md
Commit: 2921c1e

Reviewed: about 11 hours 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.