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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/seedance/SKILL.md

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.

Highly actionable content with an explicit, well-validated async workflow and excellent error-recovery guidance. It is dragged down by verbosity (repetitive example blocks and a generic prompt-writing tutorial) and a monolithic structure that inlines material better kept in separate reference files.

Suggestions

Move the model catalog, prompt best practices, and common-scenario examples into references/ files (e.g. MODELS.md, PROMPTS.md) and keep SKILL.md as a lean overview with clearly signaled one-level-deep links.

Cut the nine near-duplicate bash invocations down to one or two canonical examples plus the parameter table, and drop the prompt-writing tutorial that restates what Claude already knows.

Trim marketing-style padding such as '无需安装任何依赖！' and duplicated setup notes to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (limit tables, error/fix pairs, and parameter tables earn their tokens), but includes nine near-identical bash invocations across the examples and 'common scenarios' sections, a prompt-writing tutorial that mostly teaches what Claude already knows, and marketing padding ('无需安装任何依赖！'). This fits the 'mostly efficient but some unnecessary explanation or could be tightened' anchor rather than anchor 4's 'minor instances'.	3 / 5
Actionability	Every workflow is a fully executable, copy-paste-ready bash command against the real bundled script (scripts/generate-video.sh exists and delegates to generate_video.js), with real model IDs, complete flag tables, status tables, and cause-to-solution error pairs covering the common cases. Matches anchor 5.	5 / 5
Workflow Clarity	The async workflow is explicitly sequenced (submit task → poll status → download video), with a status table mapping each state (queued/running/succeeded/failed) to the action to take and an error-handling section giving recovery guidance per failure mode. These feedback loops for error recovery match anchor 5 rather than anchor 4's 'minor validation gaps'.	5 / 5
Progressive Disclosure	The file is well-sectioned with headers and correctly references the bundled scripts, but it is a ~450-line monolith: the model catalog, prompt best-practices tutorial, and common-scenario examples are all inlined when they belong in separate reference files, and no references/ files exist in the bundle. This matches anchor 3 ('content that should be separate is inline') better than anchor 4.	3 / 5
	Total	16 / 20 Passed

Description

78%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 strong description that states concrete capabilities tied to a specific vendor model and includes an explicit 'Use this skill when...' trigger clause. Its main weakness is a generic when-clause and missing natural synonyms for video creation requests.

Suggestions

Broaden the when-clause with concrete trigger phrases, e.g. 'Use when the user wants to create, generate, or animate videos, turn text or images into video clips, or mentions Seedance/Volcengine.'

Add common natural synonyms such as 'video clip', 'footage', 'animate an image', or 'make a video' to improve trigger term coverage.

Mention distinctive capabilities like first/last-frame transition and multi-reference-image fusion to raise capability specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('AI videos using Volcengine Seedance model') and three concrete modes ('text-to-video (T2V), image-to-video (I2V), and audio-synced video generation'), matching the 'several specific actions with minor gaps' anchor rather than the comprehensive 5 (first/last-frame, multi-reference, and watermark options are not surfaced).	4 / 5
Completeness	Both parts are explicit: the what ('Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation') and the when ('Use this skill when the user wants to create or generate videos'). The when-clause is generic and lacks concrete trigger phrases, so it matches anchor 4 rather than anchor 5.	4 / 5
Trigger Term Quality	Natural phrases like 'create or generate videos' plus the T2V/I2V terms give good keyword coverage, but common user synonyms such as 'video clip', 'footage', 'make a video', or 'video from an image' are missing, fitting anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Naming the specific vendor model ('Volcengine Seedance') with distinct mode triggers carves out a clear niche with minimal overlap risk against generic video or document skills, matching anchor 5.	5 / 5
	Total	17 / 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: netease-youdao/LobsterAI
Path: SKILLs/seedance/SKILL.md
Commit: 791a352

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.