github-seedance-directing

github-seedance-directing is a skill for Claude Code, Codex from ageerle/ruoyi-ai. It costs 0 tokens per session (2,147 once invoked), scanned A, original, MIT.

A directing guide for generating connected video scenes with dialogue, emotional changes, continuous actions, camera movement, and sound. It explains how to assign separate jobs to character references, movement references, places, and voice samples.

In plain words
What is it for?
Use it to write shot prompts, direct performances and camera movement, preserve dialogue and sound ownership, plan door crossings, and make small targeted repairs after review.
Why use it?
It reduces continuity errors such as changing poses, reversing object states, mismatching voices, losing dialogue, or cutting from one side of a doorway to an unexplained location.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write shot prompts, direct performances and camera movement, preserve dialogue and sound ownership, plan door crossings, and make small targeted repairs after review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ageerle/ruoyi-ai/github-seedance-directing
About the project

RuoYi AI is a full-stack enterprise platform for building AI assistants and agents that combine language models, knowledge bases, visual workflows, and multiple cooperating agents. Developers and organizations use it to manage model providers, retrieve information from documents, connect tools through MCP, and orchestrate agent workflows. The catalogue includes skills for working with RuoYi AI.

ageerle/ruoyi-ai · 5,773 stars · on GitHub · doc.ruoyiai.chat

Install

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.

Any agent
npx skills add ageerle/ruoyi-ai --skill github-seedance-directing
Clone the repo
git clone --depth 1 https://github.com/ageerle/ruoyi-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for github-seedance-directing

README.md
[![agentmods](https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/github-seedance-directing/github.svg)](https://agentmods.dev/skills/ageerle/ruoyi-ai/github-seedance-directing)
Your own site
<a href="https://agentmods.dev/skills/ageerle/ruoyi-ai/github-seedance-directing"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/github-seedance-directing/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.

agentmods 80×15 button for github-seedance-directing

Your own site · 80×15
<a href="https://agentmods.dev/skills/ageerle/ruoyi-ai/github-seedance-directing"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/github-seedance-directing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02147
Opus 5.5 $0.00000 $0.00859
Sonnet 5.5 $0.00000 $0.00429
Haiku 4.5 $0.00000 $0.00215

Measured 3d ago against content hash 4d99b433419b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-seedance-directing 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 3d 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.

ruoyi-modules/ruoyi-chat/src/main/resources/short-drama/skill-catalog/github-seedance-directing/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seedance · 表演、摄影与声音

适用范围

用于人物对话、情绪转折、连续行动和多段接续。先读实际剧本、角色声音、空间、道具状态及本镜起止构图;观察段和产品展示保留用户指定表达,不硬塞冲突。

导演方法

先明确观众在此段应该发现什么,人物试图得到什么、压住什么,以及哪个可见变化使局面不同。把这些判断落实为视线、手物接触、停顿、距离或声音,不将内部分析术语原样塞进生成正文。 选择一条服务事件的主摄影策略,说明起点、速度、主体关系与落点。动作发生前让空间关系可读;机位改变不能造成角色换姿态或道具回退。短段不叠加相互冲突的升降、绕行、推近和抖动。 光源应属于当前空间,明确亮暗面和必要材质变化。身份参考负责外观,动作视频负责运动,声音参考负责指定角色的音色;参考职责分开,避免连同别人的演员、房间或台词一起继承。 对白逐句保留原话和声源,让听者的回应接住前一句。画外声、旁白与画内说话分开;音色一致、内容正确、声音自然和口型同步分别核对。环境声建立空间,拟音对应接触与受力,音乐服务段落变化。

接续与返修

下一段继承上一段的实际末态和已确认切点,不重新演一遍已完成动作。记录真实画面与计划的差异,先定位失败的镜头、参考职责或声源,再修最小单元。

媒体提示词

从本镜确认的身份、空间、构图与动作状态展开,将主要事件、对手回应、摄影落点、实际光源和原对白声源融成连续描述。听者和画外声保持准确归属,音效与接触先后对应;结尾留下清楚可衔接的动作状态。参考只控制分配给它的身份、运动或音色。

项目接入边界

本技能提供当前阶段的制作方法,沿用项目现有数据、输出结构、模型目录与内容审阅。用户原文、已批准资产和当前项目决定优先;来源示例不是本剧事实。模型参数与参考语法交给本项目实际供应商适配,不从旧手册推定平台能力。 首帧按需使用,不是生成前置条件;不默认补图。视频正文采用连续导演描述,时长预算独立保存为 timing。写作、修订和技能安装不会提交付费图片、视频、配音或音乐任务。附属脚本仅作文本资料。 修订已有分镜保留已批准图片、连续性、素材任务编号和制作版本;当前只处理有问题的阶段。结构检查、任务完成与成片画面、运动和声音验收分别记录。

门口与空间转换

涉及进出门时,分别确定摄影机所在一侧、人物起点、门扇开合与铰链侧、跨门路线和抵达位置。门可内开或外开,按当前资产与剧情确定;门扇运动不代表人的行进方向。有锁或门闩时先解除,再移动门扇,钥匙和锁的去向延续到下一镜。 让观众看见人物从起始一侧经过门口到目标一侧,或在能核对位置的动作匹配点切镜;不能只写“推门”就切到人物已在房间深处。入场完成后再取物、检查或交谈;后续离场单独保留它的触发与路线。

进出动作审片

入场和离场对照前镜末态、开锁、门扇运动、跨门和抵达的完整运动及后镜起点。判断依据是人从哪一侧走到哪一侧,不能只凭门向内或向外开判断。抽一帧或结构检查只支持局部结论;重要跨门动作需连续播放或密集帧核查,记录未核查的运动与声音范围。返修保留其他通过素材,剪辑验证切口没有截断原对白或提前插入离场。

固定的可读导演稿格式

新生成和用户要求重写的 video_prompt 使用以下三部分,部分之间及各编号镜头之间空一行。它是可阅读的导演稿,不是逐秒表格;不要套用参考例子的人物、事件、画风或镜头数量。

【起始构图】写本段开始时实际空间、可见人物的身份与必要衣装、相对位置、朝向、姿态、持物和已经发生的动作状态。只有本次确实采用并审阅了首帧,才改用【首帧实况】并以实图为准。角色/场景母图不是已审阅首帧;不能虚构首帧已批准。

镜头1:从起始状态连续展开本段事件,写清景别、机位和一条主要运镜;按动作发起、接触或受阻、可见结果、对手反应推进。原对白逐句注明谁说、对谁说及画内/画外/内心声,安排在真实动作之间。需要有动机的内部切镜时另起镜头2、镜头3;单镜也保留镜头1,不为了格式硬添切镜。同一段只发生同一时空内的连续事件,跨时空另建生成段并记录接点。

当前空间为……。收束段交代此刻的光向、必要材质、环境声与动作声、说话者口型和画外声规则,以及最后确实留在画面中的姿势、位置、手中物和切出点。已经在编号镜头写清的内容不再抄写;只补保证声音与末态可执行的要求。下一段剧情放在 continuity,不提前演出。每部分都应是本段具体内容,不能用通用摄影前缀或几句摘要代替。

原剧情与原对白不因格式调整而删改;时长估算独立存入 timing,正文不列0—2秒等清单。旧人工稿只读、复制或展示时不自动改写;新稿保留真实换行,编辑器不靠视觉折行代替持久段落。

资产版本与原文角色核对

分镜前读取本版制作要求并列出实际允许的角色形象索引与场景名。按当前原文时点选择衣装,不从形象的排序、新旧、名称相似或视觉精美程度推定已获批准。标为候选、重设计或待确认的版本只有本版明确选用才绑定;主角衣装改变须有原文依据,不能提前选到后期受伤形象。

Read the full file on GitHub · 65 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 65 lines · 0 tokens per session scan A 4d99b433419b

Subscribe to this mod's changes

github-seedance-directing is a skill published in the GitHub repository ageerle/ruoyi-ai (5,773 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,147 tokens. 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 2026-10-21.

Related

Other skills, from other repositories

wegent-knowledge

Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.

wecode-ai/Wegent · 51 tokens

surfsense-documents

Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.

MODSetter/SurfSense · 80 tokens

surfsense-data

Work out numbers from spreadsheet and CSV sources (.xlsx, .csv, .tsv) by writing a pandas script that surfsenseanalyzedata runs: totals, averages, trends, rankings, comparisons, cleaning, and charts that can go into a document. Load it whenever the user asks for figures from a table, or a chart of one.

MODSetter/SurfSense · 0 tokens

video

Create polished narrated MP4 videos with Remotion in the sandbox.

MODSetter/SurfSense · 15 tokens

memory-rag-poisoning-detection

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing. Use when the agent has long-term memory, a user/preference store, or writes to a retrievable knowledge base.

Tencent/AI-Infra-Guard · 48 tokens

pdf

Create polished PDF files for requests such as PDFs, resumes, CVs, reports, letters, one-pagers, and printable documents.

MODSetter/SurfSense · 29 tokens