seedance-prompt-en

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

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 1-3

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

The body is highly actionable with concrete syntax, templates, and worked examples, and the workflow includes an explicit constraint-checking step. Its main weaknesses are length/verbosity (restating known concepts) and a monolithic structure with no progressive disclosure into separate reference files.

Suggestions

Move the camera-language, style-modifier, and example-template reference material into separate files under references/ and link to them from SKILL.md to improve progressive disclosure and reduce inline length.

Trim the restated "Description" section and the definitions of basic camera terms (pan, tilt, close-up) that Claude already knows, keeping only Seedance-specific syntax and constraints.

Consider adding a brief validation/feedback note in the workflow for cases where a drafted prompt violates constraints (e.g., real-face upload blocked), mirroring the destructive-operation checkpoint pattern.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference tables and examples, but it re-states the description in a "Description" section and defines basic cinematography terms Claude already knows (e.g. "Pan left/right — Camera rotates horizontally"), and the body runs ~370 lines that could be tightened.	2 / 3
Actionability	Provides fully concrete, copy-paste-ready prompt templates, an explicit @-reference syntax table, a prompt-structure formula, and ten capability-specific worked examples — directly executable guidance rather than abstraction.	3 / 3
Workflow Clarity	The "Workflow: Step-by-Step Prompt Creation" gives a clear 6-step sequence with an explicit validation checkpoint (step 5: verify total files ≤ 12, no real human faces, durations within limits), and the "Common Mistakes" section reinforces error avoidance.	3 / 3
Progressive Disclosure	Well-organized into sections, but it is a single monolithic ~370-line file with no bundle files (references/scripts/assets absent) and no one-level-deep references — the camera language reference, capability patterns, and templates could each be split into separate referenced files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, specific, and uses third-person imperative voice while clearly answering both what the skill does and when to use it. Trigger terms are natural and the Seedance 2.0 / @-reference scoping makes it highly distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — "camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content" — alongside the core action of writing prompts for a named model.	3 / 3
Completeness	Explicitly states both what ("Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation") and when ("Use when users want to create video prompts using text, images, videos, and audio inputs"), satisfying the what-and-when requirement.	3 / 3
Trigger Term Quality	Covers natural terms users would say ("video prompts", "images, videos, and audio inputs", "video extension", "editing", "e-commerce ads", "short dramas") plus the model's distinctive "@ reference system" trigger.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to "Jimeng Seedance 2.0" with its proprietary "@ reference system", giving it a clear niche unlikely to trigger for other video or prompting skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dexhunter/seedance2-skill
Path: SKILL.md
Commit: e06c7c6

Reviewed: ~1 month 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.