CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-2-5

Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section order, multi-shot "Hard cut" breakdown, named locks for continuity across cuts, the asset and character-sheet method, voice conditioning, and iteration discipline.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body delivers specialized, actionable guidance with concrete tool calls, field names, templates, and a real verification-and-iteration loop. It is held back from full marks by minor discursiveness, worked examples living in an external reference, a distributed rather than unified workflow, and a referenced file that is missing from the bundle.

Suggestions

Include the referenced reference/techniques.md in the bundle (or inline one or two worked example prompts) so the disclosure path resolves and actionability reaches full coverage.

Add a single short numbered "Generation workflow" sequence (choose route → set references → prompt with locks → generate → review → iterate one change) that consolidates the checkpoints currently spread across sections.

Tighten a few discursive passages such as the resolution note and the chaining prose to recover tokens without losing the operational specifics.

DimensionReasoningScore

Conciseness

The body is dense and information-rich, conveying vendor-specific operational knowledge Claude does not already know rather than padding with basics; only minor discursive passages (e.g. the resolution note) could be trimmed, so it sits at efficient-with-minor-over-explanation rather than fully lean.

4 / 5

Actionability

Concrete, copy-paste-ready elements are present — the route table with exact tool calls and parameter values, per-provider field names, and the edit-vs-regenerate correction template — but worked end-to-end example prompts are offloaded to the external reference rather than shown inline, leaving a minor gap versus fully executable coverage.

4 / 5

Workflow Clarity

A clear sequence with checkpoints is present: pre-flight "Confirm the exact provider/model before calling", post-generation review for identity continuity, cuts, lip sync, and audio artifacts, plus a one-change-per-iteration correction loop; the gap is that the workflow is distributed across sections rather than one unified numbered sequence.

4 / 5

Progressive Disclosure

Structure is good: well-organized sections plus a clearly signaled one-level-deep reference (a dedicated Reference section linking reference/techniques.md with a description of its contents); the gap is that the referenced file is not present in the bundle, so navigation is only partially fulfilled.

4 / 5

Total

16

/

20

Passed

Description

92%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.

The description is specific, complete, and distinct: it states concrete capabilities, gives an explicit "Use for..." trigger clause, and carves out a clear niche. Its only weak spot is trigger-term coverage that relies on proper nouns without synonyms or variations.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Generate 4-30 second cinematic video", routing through four named providers, and covering the prompt contract, locks, asset/character-sheet method, voice conditioning, and iteration discipline — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers what (generate video + the 2.5 prompt contract) and when ("Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips)") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms a user would say are present ("cinematic video", "Seedance 2.5", "fal.ai", "Runway", "synchronized audio"), but coverage leans on proper nouns and lacks common synonyms or variations, stopping just short of the comprehensive-with-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

A clear, narrow niche — Seedance 2.5 via four specific named providers with explicit reference limits and prompt-contract coverage — making it highly distinct with minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
calesthio/OpenMontage
Reviewed

Table of Contents

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.