muapi-seedance-2

Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.

Quality

73%

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 ./.opencode/skills/muapi-seedance-2/SKILL.md

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 concrete, copy-paste bash commands and detailed parameter tables, but it is verbose with redundancy and basic cinematography padding, lacks validation/feedback loops for expensive generation operations, and is a monolithic file that references a non-existent script. Tightening, adding verification steps, and either providing or removing the script reference would lift the weaker dimensions.

Suggestions

De-duplicate the repeated 'audio is mandatory' and 'single-beat' guidance (Prompts, Protocol, and Common Mistakes) into one canonical statement and cross-reference it.

Add a verification/feedback step to the generation workflow (e.g. check the returned video for watermark, duration, and tier-appropriate aspect ratio before considering the job done), since video generation is a batch/expensive operation.

Provide the referenced 'scripts/generate-seedance.sh' as a bundle file (or remove the broken reference) and consider splitting the Camera Language Reference and Prompt Templates into separate referenced files to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is ~600 lines with redundancy (the audio-is-mandatory and single-beat rules are each repeated several times, e.g. Common Mistakes items 5 and 10 both cover missing audio) and includes a Camera Language Reference explaining basic terms like 'Pan left/right' and 'Close-up' that Claude already knows. Not a 1 because most content is skill-specific and actionable rather than padding; not a 3 because it could be materially tightened.	2 / 3
Actionability	Provides many concrete, copy-paste-ready bash commands with full flag syntax (e.g. 'bash scripts/generate-seedance.sh --mode i2v --tier global --file hero.jpg --subject "..." --duration 8 --view') and specific parameter tables. This matches the fully-executable-instruction anchor rather than the pseudocode anchor.	3 / 3
Workflow Clarity	Steps are listed (Prompt Optimization Protocol, async submit-then-check pattern, per-mode command examples) but there are no validation checkpoints or error-recovery feedback loops for batch/expensive video-generation operations, which per the scoring notes caps workflow_clarity at 2.	2 / 3
Progressive Disclosure	Section headers and tables give it clear internal structure, but the skill is a single monolithic ~600-line file with content (camera reference, prompt templates, 12 capability patterns) that could be split into referenced files. The repeatedly-referenced 'scripts/generate-seedance.sh' does not exist in the bundle, so signaled references point to missing files. Not a 1 because organization is reasonable; not a 3 because there are no real one-level-deep references and content is not appropriately split.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, distinctive, and rich in natural trigger terms, but it omits an explicit 'Use when...' trigger clause, which caps its completeness at 2. Adding a sentence stating when to invoke the skill would raise it to a top score.

Suggestions

Append an explicit trigger clause, e.g. 'Use when generating or editing video with Seedance 2.0, or when the user mentions ByteDance video generation, text-to-video, image-to-video, or watermark removal.'

Consider adding common user variations like 'AI video', 'video from images', or 'animate an image' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions/capabilities — 'text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal' — matching the anchor for enumerating several concrete actions.	3 / 3
Completeness	Strongly answers 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Good coverage of natural terms a user would say — 'video generation', 'text-to-video', 'image-to-video', 'video editing', 'watermark removal', plus the product name 'Seedance 2.0' (ByteDance). Not a 2 because it goes beyond a single keyword with broad natural coverage.	3 / 3
Distinctiveness Conflict Risk	A clear, product-specific niche ('Seedance 2.0 (ByteDance)' with named tiers and modes) unlikely to trigger for other skills, matching the distinct-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (633 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 26 missing	Warning

	Total	13 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: .opencode/skills/muapi-seedance-2/SKILL.md
Commit: 71242e2

Reviewed: about 21 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.