seedance-2-0

Generate cinematic clips with ByteDance Seedance 2.0 — the preferred premium video model in OpenMontage when a paid gateway is configured. Use when: (1) producing trailers, teasers, hype edits, or premium cinematic clips, (2) needing native synchronized audio (speech, SFX, ambience) in a single pass, (3) needing multi-shot cuts inside one generation, (4) needing director-level camera control, (5) needing lip-sync from quoted dialogue in the prompt, (6) needing reference-conditioned generation with up to 9 images + 3 video clips + 3 audio clips, (7) wanting consistent character identity across shots. Accessible via fal.ai (`seedance_video` tool), HeyGen (Video Agent / Avatar Shots), Replicate, Runway (Enterprise, non-US), Freepik, BytePlus ModelArk, Higgsfield, Pollo, and other aggregators.

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 1-5

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

A highly actionable, well-sequenced body with strong feedback loops, dragged down by inlined content that belongs in reference files and by time-sensitive detail left in the main flow rather than a deprecated section. Conciseness is the weakest dimension.

Suggestions

Move the provider surface table, fal.ai model IDs, and verbatim Higgsfield opener templates into a references/ file (e.g. PROVIDERS.md and PROMPT_TEMPLATES.md) and link to them one level deep, keeping SKILL.md as an overview.

Relocate time-sensitive facts (release dates, Elo ranking, per-second pricing) into a clearly labeled 'Pricing & release notes (verify before use)' or deprecated-style section so the operational guidance stays lean.

Trim the opening OpenMontage routing paragraph, which restates the gateway list and dedup-by-provider behavior already covered in 'Provider surfaces'.

Dimension	Reasoning	Score
Conciseness	Mostly dense and operational with little basic-concept padding, but time-sensitive claims ('released Feb 2026', 'Elo 1269 as of Feb 2026', fal.ai pricing) sit in the main body rather than a deprecated/old-patterns section, and the OpenMontage routing prose in the intro repeats detail covered later — could be tightened.	3 / 5
Actionability	Fully executable: copy-paste `video_selector` and direct `seedance_video` Python calls, exact fal.ai model IDs, verbatim opener templates, and parameter tables covering the common T2V/I2V/reference cases.	5 / 5
Workflow Clarity	Clear sequenced 'Iteration strategy' (block out shape → lock seed → upgrade to standard → extend → keep README) plus an explicit 'Verification checklist for every Seedance shot' and an anti-drift feedback loop ('If face morphs... drop to a shorter duration, tighten identity-lock language').	5 / 5
Progressive Disclosure	Well-sectioned with clear headers, but no bundle files exist (references/scripts/assets all absent) and everything — provider surface table, Higgsfield opener templates, legacy template, parameter guidance — is inlined in one ~280-line file with no one-level-deep references to split out the bulk.	3 / 5
	Total	16 / 20 Passed

Description

100%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 high-quality description: third-person imperative voice, concrete capability list, explicit seven-part 'Use when' trigger guidance, and a distinctive niche that minimizes conflict risk. No first/second-person voice to penalize.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'producing trailers, teasers, hype edits, or premium cinematic clips', 'native synchronized audio', 'multi-shot cuts', 'lip-sync from quoted dialogue', 'reference-conditioned generation with up to 9 images + 3 video clips + 3 audio clips' — giving comprehensive coverage of the model's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Generate cinematic clips with ByteDance Seedance 2.0') and 'when' via a numbered 'Use when: (1)...(7)' clause with seven concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms users would actually say — 'trailers, teasers, hype edits', 'cinematic clips', 'speech, SFX, ambience', 'multi-shot cuts', 'camera control', 'lip-sync' — with no jargon-only phrasing.	5 / 5
Distinctiveness Conflict Risk	Clear niche — ByteDance Seedance 2.0 cinematic video with distinctive triggers (synced audio, multi-shot, lip-sync, reference conditioning) unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/seedance-2-0/SKILL.md
Commit: 08e2151

Reviewed: 6 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.