Seedance Japanese Prompt Examples
Emily2040/seedance-2.0
Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk.
Turns a vague video idea into a seven-section prompt that reads like real home-video, phone, DV or surveillance footage, with checks against an AI-look checklist.
SKILL.md written in Chinese; this summary is our English description.
Install Realistic AI Video Prompt Writer
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zhouwei713/seedance-prompt realistic-video-prompting --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .claude/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zhouwei713/seedance-prompt realistic-video-prompting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .agents/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zhouwei713/seedance-prompt realistic-video-prompting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .cursor/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zhouwei713/seedance-prompt realistic-video-prompting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .gemini/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zhouwei713/seedance-prompt realistic-video-promptingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .github/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zhouwei713/seedance-prompt realistic-video-prompting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "realistic-video-prompting" agent skill from https://github.com/zhouwei713/seedance-prompt/tree/main into .opencode/skills/realistic-video-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "realistic-video-prompting", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
realistic-video-prompting- GitHub stars
- 327
- Token cost
- ~749 tokens
- SKILL.md length
- 97 words
- Files
- 6 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns a vague video idea into a seven-section prompt that reads like real home-video, phone, DV or surveillance footage, with checks against an AI-look checklist.
- Works in 4 steps: 拍摄者身份：谁在拍？朋友、家人、路人、Vlogger、监控、纪录片摄制组、还是无人… → 设备与年代：DV、VHS、8mm胶片、iPhone、GoPro、监控、专业电影机？… → 主体与场景：拍谁？在哪？什么时间段？ → …
- Writing a text-to-video prompt that looks like genuine footage
- SKILL.md covers 核心哲学, 工作流程, 参考文件 and 变体处理
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill takes a vague idea for a video and turns it into a dense, structured prompt that reads like real footage instead of polished AI output. It targets text-to-video models such as Seedance, Sora, Kling, Runway and Veo, and fits requests for a home-video, phone-shot, DV or surveillance look. The skill file itself is in Chinese.
The agent first pins down four things: who filmed it, with what device in which era, what and where the subject is, and the target mood, asking you if any is unclear. It then writes seven sections in fixed order: main character, location, visual style, camera style, timeline, audio and goal. Characters get concrete visual detail and a consistency lock sentence, locations list specific elements and exclude commercial ones, and the camera section lists device-specific flaws plus negations of stabilization and cinematic movement.
The timeline runs about 10 to 15 seconds across five to seven short shots, each with one non-perfect event from a checklist and a closing beat that fits the filmmaker. Before delivery the prompt is checked against an anti-AI checklist, and the agent adds a short note on which settings to adjust. References cover camera aesthetics for eight device types, an atmosphere dictionary and the checklist.
When your agent uses it
- Writing a text-to-video prompt that looks like genuine footage
- Rewriting a prompt that feels too cinematic or AI-looking
- Turning a scene idea into a home-video or surveillance style prompt
- Choosing device and era details for a documentary look
Example prompts
- “Write a Seedance prompt for a 2005 home DV clip of kids playing in a courtyard.”
- “Turn my idea of a quiet Korean neighborhood morning into a documentary-style video prompt.”
- “Make this prompt feel less AI: a woman walking through a night market.”
- “Give me a surveillance-camera style prompt for an empty parking garage.”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 拍摄者身份：谁在拍？朋友、家人、路人、Vlogger、监控、纪录片摄制组、还是无人拍摄的固定机位？
- 设备与年代：DV、VHS、8mm胶片、iPhone、GoPro、监控、专业电影机？哪个年代？
- 主体与场景：拍谁？在哪？什么时间段？
- 情绪目标：温暖怀旧、孤独疏离、紧张不安、平静治愈？
What it can do on your machine
Read from SKILL.md and the folder at commit f333685. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Realistic AI Video Prompt Writer loads about 749 tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 97 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from zhouwei713/seedance-prompt at commit f333685, republished under its MIT licence (© zhouwei713). 97 words, ~749 tokens.
Download SKILL.mdSave it as
.claude/skills/realistic-video-prompting/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- realistic-video-prompting
- description
- 为AI视频生成模型（Seedance、Sora、Kling、Runway、Veo等）撰写真实感、去AI感、纪录片质感的结构化视频提示词。当用户想生成AI视频提示词、优化现有视频提示词、追求"真实感""家庭录像感""手机随拍感""DV感""监控录像感"的视频效果，或提到Seedance、文生视频、视频prompt时，务必使用此skill。即使用户只是描述了一个想拍的场景或氛围，也应使用此skill将其转化为完整提示词。
- version
- 1.1.0
- author
- zhouwei713
- license
- MIT
真实视频提示词生成器
把用户的一个模糊想法（"我想要一段韩国社区的日常感视频"）转化为高密度、可执行、去AI感、像真实素材拍出来的结构化视频提示词。
核心哲学
高质量视频提示词的本质是回答一个问题：这段素材是谁、用什么设备、在什么年代、出于什么目的拍下来的？
一旦确定了"素材来源身份"，所有细节都能推导出来。2005年朋友随手拍的DV会抖、会失焦、会突然关机；2024年博主的手机竖屏会有美颜感、会对着镜头说话；90年代的监控摄像头没有声音、俯视角、低帧率。
第二个关键认知：AI模型有强烈的默认审美（电影感运镜、完美构图、商业调色、干净画面）。想要真实感，必须用负面约束主动关闭这些默认行为，并在时间轴里植入"非完美事件"。
工作流程
第一步：确定四要素（缺一不可）
如果用户没有说清楚，先问这四个问题（可以合并成一次提问）：
- 拍摄者身份：谁在拍？朋友、家人、路人、Vlogger、监控、纪录片摄制组、还是无人拍摄的固定机位？
- 设备与年代：DV、VHS、8mm胶片、iPhone、GoPro、监控、专业电影机？哪个年代？
- 主体与场景：拍谁？在哪？什么时间段？
- 情绪目标：温暖怀旧、孤独疏离、紧张不安、平静治愈？
如果用户已经给出足够信息，直接推断并在输出前用一句话确认你的理解。
第二步：按七段式模板逐段生成
严格按以下顺序输出，每段独立成块，段间不混淆信息：
主要角色 → 地点 → 视觉风格 → 摄像风格 → 时间轴 → 音频 → 目标各段写作规则：
1. 主要角色
- 只写可视化的具体特征：年龄段、妆容、每件衣物的颜色/材质/版型、鞋、配饰、发型细节（含碎发/刘海等小特征）
- 禁用抽象形容词（时尚的、好看的、有气质的）
- 加一句皮肤/质感描述（如"逼真的皮肤纹理"）
- 加一句性格气质（用于驱动肢体语言）
- 必须以一致性锁定句结尾："在整个视频中保持一致的身份、服装、发型和外貌"
2. 地点
- 时间段 + 地域 + 场景类型开头
- 罗列8到12个具体环境元素（盆栽、晾衣绳、电线杆、树影等），元素要能相互佐证同一个世界
- 加光影动态描述（树影移动、云影掠过）
- 以负面约束结尾：排除模型爱加的商业元素（商店、广告、人群、咖啡馆）
3. 视觉风格
- 用4到6个短语定义真实感层级：如"超现实主义纪录片真实感、真实的即兴行为、自然的肢体语言、无剧本的日常生活片段感、强烈的环境真实性"
4. 摄像风格
- 这是去AI感的核心段落。查阅
references/camera-aesthetics.md，选取对应设备的"缺陷参数包"完整写入 - 原则：把设备美学翻译成6到10个具体物理现象（对焦搜索、曝光波动、滚动快门、压缩伪影等）
- 必须以三连负面约束结尾：没有稳定、没有电影化摄像机移动、没有现代色彩分级（按设备调整）
5. 时间轴
- 总长10到15秒，切5到7个镜头，每镜头2到3秒，用
00:00–00:02格式 - 每个镜头包含三层：主体动作 + 环境呼应（风、光、动物、路人）+ 一个非完美事件
- 非完美事件从
references/anti-ai-checklist.md的清单中选取，且7个镜头里不重复使用同一种 - 动作之间要有生活逻辑链（坐着 → 走进小巷 → 遇到猫 → 晾衣服），别写成互不相关的镜头拼贴
- 结尾必须有收束方式：突然切黑（像关机）、走出画面、镜头垂下拍到地面等，与拍摄者身份匹配
6. 音频
- 先声明模式（仅自然环境音 / 现场收音 + 环境）
- 罗列6到9个具体声音元素，与场景元素一一对应（有猫就有猫叫，有晾衣绳就有织物声）
- 三连否定结尾：没有音乐、没有音效设计、没有旁白（按需调整）
7. 目标
- 一句话灵魂锚点，格式："捕捉XX，仿佛一段XX的XX，用4到6个形容词收尾"
- 这句话是模型在细节冲突时的取舍依据，必须与前面所有段落自洽
第三步：自检（输出前必做）
对照 references/anti-ai-checklist.md 逐条检查：
- 角色段有一致性锁定句吗？
- 地点段排除了商业元素吗？
- 摄像段有至少6个物理缺陷描述 + 3个"没有XX"吗？
- 时间轴每个镜头都有一个非完美事件吗？有重复吗？
- 结尾有收束方式吗？
- 音频段的声音元素与画面元素对应吗？
- 全文有没有漏进抽象形容词（美丽的、电影感的、高级的）？
- 目标句与拍摄者身份/设备/年代自洽吗？
第四步：交付
- 输出完整提示词（中文或英文按用户需求，投喂给模型时英文通常效果更稳，可主动提供英文版）
- 附一段简短说明：这条提示词的"素材来源身份"设定是什么，用户想调整时改哪几个旋钮（设备包、时间段、情绪词、收束方式）
参考文件
references/camera-aesthetics.md：8种设备/媒介的缺陷参数包，写摄像风格段时必读references/atmosphere-dictionary.md：氛围词到具体视觉现象的翻译表，写地点和时间轴时查阅references/anti-ai-checklist.md：AI感来源清单、负面约束句库、非完美事件库，自检时必读
变体处理
- 用户要非写实风格（动画、赛博朋克、广告片）：七段式结构不变，但摄像段改为对应媒介的美学参数（动画帧率、广告片的运镜语言），负面约束改为排除该风格不要的元素
- 用户要多角色：每个角色独立一段描述，各自带一致性锁定句，并在时间轴中明确角色间互动
- 用户只要优化现有提示词：先按七段式诊断缺哪些段、哪些段密度不足，给出诊断表再重写
- 超过15秒的长视频：建议拆成多条提示词分段生成，每条保持角色段完全一致以维持连续性
© zhouwei713, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in the repository root of zhouwei713/seedance-prompt.
- SKILL.md
- LICENSE
- README.md
- references/anti-ai-checklist.md
- references/atmosphere-dictionary.md
- references/camera-aesthetics.md
Open the folder on GitHubat commit f333685
Compare with similar skills
Realistic AI Video Prompt Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Realistic AI Video Prompt Writer this skillzhouwei713/seedance-prompt | 327 | — | ~749 | Automated safety check: Pass | MIT | |
| Seedance Japanese Prompt ExamplesEmily2040/seedance-2.0 | 7.6k | 1 repos | ~898 | Automated safety check: Pass | MIT | |
| Cinematic Video Prompt EngineerCyberJ0605/cinematic-video-prompt-engineer-skill | 127 | — | ~10k | Automated safety check: Pass | MIT | |
| Seedance 2.5 Video PlannerAtlasCloudAI/awesome-seedance-2.5-prompts-skills | 234 | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| Seedance Prompt LibraryLearnPrompt/awesome-seedance | 1.9k | — | ~1k | Automated safety check: Pass | MIT | |
| Video Prompting GuideNeverSight/learn-skills.dev | 217 | 1 repos | ~2k | Automated safety check: Pass | None |
Similar skills
Cinematic Video Prompt Engineer
CyberJ0605/cinematic-video-prompt-engineer-skill
A skill your agent uses when the user provides a plot summary, scene idea, character relationship, emotional beat, or short video concept and wants a cinematic AI video prompt.
Seedance 2.5 Video Planner
AtlasCloudAI/awesome-seedance-2.5-prompts-skills
Plans and generates controllable Seedance videos by choosing a creative route first, from text prompts and storyboards to keyframe pairs, extensions and edits.
Seedance Prompt Library
LearnPrompt/awesome-seedance
Verified prompt templates and structures for Seedance 2.5 / 2.0 video generation, distilled from the highest-performing published cases on goodcase.ai.
Video Prompting Guide
NeverSight/learn-skills.dev
Best practices and techniques for writing effective AI video generation prompts.
Seedance 2.0 Video Prompting
Emily2040/seedance-2.0
Routes Seedance 2.0 video work across Dreamina, API and router surfaces, covering prompts, reference handling, audio and lip-sync, pricing and model-ID questions.
Related
Works with
Categories
Questions about Realistic AI Video Prompt Writer
What does Realistic AI Video Prompt Writer do?
Turns a vague video idea into a seven-section prompt that reads like real home-video, phone, DV or surveillance footage, with checks against an AI-look checklist. This skill takes a vague idea for a video and turns it into a dense, structured prompt that reads like real footage instead of polished AI output. It targets text-to-video models such as Seedance, Sora, Kling, Runway and Veo, and fits requests for a home-video, phone-shot, DV or surveillance look.
When should I use Realistic AI Video Prompt Writer?
Realistic AI Video Prompt Writer fits situations like: writing a text-to-video prompt that looks like genuine footage; rewriting a prompt that feels too cinematic or AI-looking; turning a scene idea into a home-video or surveillance style prompt; choosing device and era details for a documentary look.
How do I install Realistic AI Video Prompt Writer in Claude Code?
Run `npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a claude-code`. Or copy the skill folder (the zhouwei713/seedance-prompt repository) into .claude/skills/realistic-video-prompting in your project. Claude Code loads it when a task matches its description.
How do I install Realistic AI Video Prompt Writer in Codex?
Run `npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a codex`. Or copy the skill folder (the zhouwei713/seedance-prompt repository) into .agents/skills/realistic-video-prompting in your project. Codex loads it when a task matches its description.
Can I use Realistic AI Video Prompt Writer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhouwei713/seedance-prompt --skill realistic-video-prompting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/realistic-video-prompting, .gemini/skills/realistic-video-prompting, .github/skills/realistic-video-prompting and .opencode/skills/realistic-video-prompting in your project.
What does Realistic AI Video Prompt Writer need to run?
SKILL.md names no scripts, command-line tools or credentials: Realistic AI Video Prompt Writer is instructions for the agent only.
Does Realistic AI Video Prompt Writer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Realistic AI Video Prompt Writer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Realistic AI Video Prompt Writer use?
Realistic AI Video Prompt Writer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Realistic AI Video Prompt Writer use?
About 749 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.
What are the alternatives to Realistic AI Video Prompt Writer?
Skills that share tags, products or a category with Realistic AI Video Prompt Writer: Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.6k stars), Cinematic Video Prompt Engineer (CyberJ0605/cinematic-video-prompt-engineer-skill, 127 stars), Seedance 2.5 Video Planner (AtlasCloudAI/awesome-seedance-2.5-prompts-skills, 234 stars) and Seedance Prompt Library (LearnPrompt/awesome-seedance, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Realistic AI Video Prompt Writer?
zhouwei713 (a GitHub user) maintains it in zhouwei713/seedance-prompt, which has 327 GitHub stars. The repository was last updated on August 4, 2026.
Source: zhouwei713/seedance-prompt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.