Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Supreme-Ultimate/novel-to-script-team --skill seedance-prompt-review-skillgit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/seedance-prompt-review-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/seedance-prompt-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/seedance-prompt-review-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/seedance-prompt-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/seedance-prompt-review-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.03179 |
| Opus 5 | $0.00032 | $0.01589 |
| Sonnet 5 | $0.00013 | $0.00636 |
| Haiku 4.5 | $0.00006 | $0.00318 |
Grade A, and why
seedance-prompt-review-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance 2.0 提示词审核技能
必读
../../references/00-first-principles.md../../references/04-review-gates.md../../references/05-compliance-boundaries.md../../references/20-frame-description-elements.md(帧图描述完整元素表)
技能说明
审核分镜师在阶段三的 Seedance 2.0 提示词产出。导演需要以批判性视角审视分镜师的产出,通过逐条比对导演讲戏本、脑内预演 Seedance 生成效果、逐条评分的方式,确保提示词质量真正达标,能通过 Seedance 2.0 生成符合导演意图的视频。
审核对象
outputs/<集数>/02-seedance-prompts.md
审核流程
第一步:建立整体理解
- 读取导演讲戏本(
01-director-analysis.md) - 读取人物提示词(
outputs/{剧本名}/assets/character-prompts.md)和场景道具提示词(outputs/{剧本名}/assets/scene-prompts.md) - 读取待审核的 Seedance 提示词产出
- 明确审核立场:你的任务是找出问题,而非确认通过
第二步:逐条比对
- 对每条提示词,逐句对照导演讲戏本中对应剧情点的导演阐述
- 找出导演阐述中有但提示词中被弱化、遗漏或表达偏离的地方
- 找出分镜师自行添加的、导演阐述中没有的内容,判断是否合理
- 记录所有偏差,无论大小
第三步:脑内预演
- 对每条提示词,想象它被送进 Seedance 2.0 后,生成的视频画面是什么样的
- 判断:生成的视频是否与导演讲戏本中描述的画面一致?
- 判断:是否有描述方式可能导致 Seedance 理解错误(如动作顺序混乱、运镜方向矛盾、多个动作在短时间内无法完成)?
- 判断:@引用的参考图加上提示词的动态描述,生成效果是否会自然?
第四步:逐条评分
按照下方验收清单,对每条提示词评分(1-10)
第五步:输出结果
- 计算所有提示词的平均分
- 平均分 ≥ 8 且无单项低于 6 → PASS
- 平均分 < 8 或任一单项低于 6 → FAIL + 问题清单
验收清单
生成模式选型检查(整体检查,不评分)
- □ 模式合理性:硬切换景别/机位的镜头是否使用了
I2V-首帧或I2V-首帧 + 多参考?连续动作过渡的镜头是否使用了首尾帧?纯氛围/概念镜头是否使用了T2V?逐条检查,列出不合理的模式选择。 - □ 帧图需求完整性:所有
I2V-首帧模式的提示词是否都有对应的首帧图需求?所有首尾帧模式的提示词是否都有首帧图和尾帧图需求?逐条检查,列出遗漏。 - □ 帧图描述质量:帧图描述是否为精确的静态单帧画面(构图、人物姿态、光影、色调)?是否包含动态描述(帧图不应有动作)?逐条检查。
- □ 引用配额检查:叠加模式(如
I2V-首帧 + 多参考)下,帧图 + 参考图总数是否 ≤ 9 张?逐条检查。 - □ 模式标注格式:每条提示词是否都标注了
**生成模式**和**选型理由**?格式是否统一?
素材对应表(整体检查,不评分)
- □ 完整性:是否为所有引用的素材建立了对应关系?逐个检查,列出遗漏。
- □ 准确性:素材描述是否与 character-prompts.md / scene-prompts.md 一致?逐个比对,列出不一致。
- □ 无孤立引用:提示词中的 @引用是否都在对应表中有记录?逐条检查。
- □ 素材边界正确:对应表中是否只包含在 character-prompts.md / scene-prompts.md 中有参考图的素材?不在素材文件中的群演/一次性配角不应出现在对应表中。
- □ 场景独立编号:scene-prompts.md 中的九宫格是生成格式,用户会将每个格子拆成独立的场景参考图。对应表中每个场景是否独立编号为一个 @图片?如果发现整张九宫格被作为一个 @图片(如"@图片5 = ep01 场景宫格"),则为严重错误,必须 FAIL。
- □ 引用用途明确:每个 @引用是否都明确标注了用途(如"参考@图片1的人物形象")?是否存在模糊引用(如只写"参考@视频1"而不说参考什么)?逐个检查。
- □ 平台约束合规(单条维度):每条提示词内的素材引用是否在 Seedance 2.0 单次生成限制内?图片 ≤ 9、视频 ≤ 3、音频 ≤ 3、总文件 ≤ 12。注意:素材对应表是全文档总映射,@图片总数可以超过 9 张。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 177 lines · 64 tokens per session scan A 2a6863a7330e
seedance-prompt-review-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (167 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 3,179 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…