CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-prompt-zh

为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./zh/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 dense, highly actionable prompt-writing guide with excellent concrete examples, clear syntax reference, and a sequenced interaction workflow including a constraint-check checkpoint. Its main weaknesses are redundancy between the scenario and template sections and the lack of progressive disclosure — the bulky reference libraries sit inline in one long file rather than being split into separate bundle files.

Suggestions

De-duplicate overlapping content: the 提示词模版库 repeats 产品广告/短剧/科普 cases already shown in 各场景提示词模式 — merge them or have the template library reference distinct, additional scenarios.

Apply progressive disclosure by moving the bulky camera-language tables, the 12-scenario example library, and the template library into separate reference files (e.g. references/camera-language.md, references/scenarios.md, references/templates.md) with clearly signaled one-level-deep links from SKILL.md.

Strengthen the workflow's feedback loop: after the 检查约束 step, add an explicit 'if a constraint is violated, revise the prompt and re-check before finalizing' retry path.

DimensionReasoningScore

Conciseness

Mostly concrete reference material that earns its place, but the ~430-line body has notable redundancy — e.g. 产品广告/科普/短剧 appear in both the 12-scenario "各场景提示词模式" section and the overlapping "提示词模版库" — that could be tightened.

3 / 5

Actionability

Highly actionable for an instruction-only skill: provides a concrete prompt formula, the exact @引用 syntax with a usage table, copy-paste-ready example prompts, and full 15-second time-segmented templates covering the common cases.

5 / 5

Workflow Clarity

The "交互指引" section gives a clear 6-step sequence with an explicit validation checkpoint ("检查约束:确认总文件数 ≤ 12、无写实人脸、时长在限制范围内") plus a refine step; minor gap is that there is no explicit validate→fix→retry feedback loop after constraint failure.

4 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), so the ~430-line guide is a single monolithic file; section headers are clear and well-organized, but large reference blocks (12-scenario library, template library, camera-language tables) are inlined rather than split into one-level-deep referenced files.

3 / 5

Total

15

/

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 well-crafted description that names the specific model, lists numerous concrete scenario capabilities, and provides an explicit trigger condition. It clearly answers both what and when with low conflict risk, needing only minor refinement in trigger-term synonyms and action granularity to reach the top anchor.

DimensionReasoningScore

Specificity

Lists several concrete capability areas ("@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育"), giving broad scenario coverage rather than vague abstraction, though they are use-case labels rather than discrete granular actions.

4 / 5

Completeness

Explicitly answers both 'what' ("为即梦 Seedance 2.0...撰写高质量提示词") and 'when' ("当用户需要使用...创作视频提示词时触发"), with concrete trigger guidance; the 'when' clause is present and explicit but could be slightly more scenario-specific.

4 / 5

Trigger Term Quality

Includes natural terms users would say ("提示词", "视频", "文本、图片、视频、音频", "创作视频提示词") with a clear trigger phrasing, but lacks common synonyms/file extensions and a few natural variants.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — the specific "即梦 Seedance 2.0 多模态AI视频生成模型" with model-specific @ syntax — making it highly distinct with minimal conflict risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dexhunter/seedance2-skill
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.