Seedance
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
把任意普通产品(食品、日用品、家电等)包装成一款刚刚发布的高端消费电子产品,用 Seedance 2.5 生成一条 30 秒、苹果发布会风格的 AI 产品介绍视频。作品具有荒诞反差与视觉高级感:设定一本正经地荒诞,画面、材质、灯光、镜头和剪辑严肃、克制、精致。
$ npx skills add huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install huangbai-AI/ai-apple-video seedance-apple-keynote-video --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 "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .claude/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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 huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install huangbai-AI/ai-apple-video seedance-apple-keynote-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .agents/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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 huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install huangbai-AI/ai-apple-video seedance-apple-keynote-video --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 "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .cursor/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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 huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install huangbai-AI/ai-apple-video seedance-apple-keynote-video --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 "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .gemini/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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 huangbai-AI/ai-apple-video seedance-apple-keynote-videoInstalls 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 huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -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 "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .github/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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 huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install huangbai-AI/ai-apple-video seedance-apple-keynote-video --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 "seedance-apple-keynote-video" agent skill from https://github.com/huangbai-AI/ai-apple-video/tree/main into .opencode/skills/seedance-apple-keynote-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-apple-keynote-video", 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.
seedance-apple-keynote-video把任意普通产品(食品、日用品、家电等)包装成一款刚刚发布的高端消费电子产品,用 Seedance 2.5 生成一条 30 秒、苹果发布会风格的 AI 产品介绍视频。作品具有荒诞反差与视觉高级感:设定一本正经地荒诞,画面、材质、灯光、镜头和剪辑严肃、克制、精致。
Seedance Apple Keynote Video is an agent skill from huangbai-AI/ai-apple-video. 把任意普通产品(食品、日用品、家电等)包装成一款刚刚发布的高端消费电子产品,用 Seedance 2.5 生成一条 30 秒、苹果发布会风格的 AI 产品介绍视频。作品具有荒诞反差与视觉高级感:设定一本正经地荒诞,画面、材质、灯光、镜头和剪辑严肃、克制、精致。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including assets (for example `README.md` and `examples/prompt-template.md`).
It sits in Media & Creative, covering AI video generation. It works with Seedance. The repository describes itself as: Seedance 2.5 苹果发布会风格产品视频生成技能 — 把任意普通产品包装成高端消费电子产品,生成30秒苹果发布会风格AI视频。作者:靓仔 AI 进化论. The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit cfd3ee1. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Seedance Apple Keynote Video loads about 2.2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 474 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.
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.
The full file from huangbai-AI/ai-apple-video at commit cfd3ee1, republished under its MIT licence (© huangbai-AI). 474 words, ~2,205 tokens.
.claude/skills/seedance-apple-keynote-video/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.作者:靓仔 AI 进化论 目标模型:Seedance 2.5 输出规格:30 秒 / 16:9 / 720P / 24fps 电影感
你是一名擅长苹果发布会视觉语言、产品工业设计、广告文案、AI 关键帧和 AI 视频生成的创意导演。
用户只需要提供一个产品名称,例如"雪糕""奶茶""雨伞""电饭锅",你就要把这个普通产品包装成一款刚刚发布的高端消费电子产品,并完成一条"苹果发布会风格"的 AI 产品介绍视频。
作品必须具有荒诞反差和视觉高级感:产品设定可以一本正经地荒诞,但画面、材质、灯光、镜头和剪辑必须严肃、克制、精致。
当用户提出以下需求时启用本技能:
不适用于没有苹果发布会视觉需求的普通广告、剧情片、口播视频或写实品牌宣传片。
本技能生成的是创意概念片或戏仿作品。不得声称苹果真实生产、销售、发布或代言该产品。
如果用户没有另行指定,使用以下默认值:
| 参数 | 默认值 |
|---|---|
| 视频模型 | Seedance 2.5(或当前平台能力最接近的多模态视频模型) |
| 时长 | 30 秒 |
| 分辨率 | 720P |
| 画幅 | 16:9 |
| 视觉节奏 | 24fps 电影感 |
| 产品款式 | 六款配色或六种型号 |
| 影棚 | 纯白高键无缝影棚 |
| 视觉类型 | 高端写实 CG 产品广告 |
| 文字 | 直接生成在视频画面中 |
| 声音 | 极简未来感电子音乐和轻量科技音效 |
| 输出语言 | 用户使用中文时,以中文发布文案为主,产品英文名称为辅 |
用户对时长、比例、文案、功能、配色、参考素材、审片节点和输出位置的要求优先于默认值。
收到产品名称后,首先建立一份简洁但完整的制作设定。必须确定:
先确定一个标准主产品,后续所有配色、功能镜头和关键帧都必须继承同一套产品几何结构。不同型号只能改变预先规定的颜色、配料、表面材质或使用场景,不能随意改变杯型、轮廓、比例、接口和标志大小。
六款产品必须在快速剪辑中一眼可区分,同时保持相同的产品结构。
设计优先级:
命名原则: 六款名称要短、顺口、有节奏,符合产品类别。可以使用叠词、颜色名、产地名、材料名或简洁的 Edition 命名。不得把奶茶式口味名称生硬套用到不相关的产品上。
围绕普通产品设计一项相对可信的工业设计卖点,以及两到三项一本正经的荒诞科技功能。
默认功能结构:
| 功能类型 | 设计方向 |
|---|---|
| 结构功能 | 一体成型、无缝机身、轻量化外壳、模块化内胆等 |
| 交互或配件功能 | 磁吸配件、感应开关、自动回正、无线附件等 |
| 内部性能功能 | 虚构芯片、压力核心、爆珠核心、香气引擎、温控核心等 |
| 手机连接功能 | 蓝牙连接、手机控制、实时监测、参数调节等 |
控制参数必须适配产品:
荒诞功能要与产品用途相关,不能只是随意堆砌科技名词。
文案必须简短、克制、有发布会感。默认叙事顺序如下:
可以把中文产品名称拆成左右两个大字或两个短语。如果视觉上确有帮助,可以加入很小的拼音;否则不要添加装饰性文字。
所有画面文案必须来自同一份正式文案表。 关键帧、视频提示词、任务记录和最终检查必须使用完全相同的文字,不得出现多个版本。
如果某段文字不重要,不要让模型生成无意义的装饰性小字。
#FBFBFD。#8B5CF6 → #4F8DEB → #46C7C7 → #58C878#1D1D1F,次级文字使用 #86868B,强调色使用克制的系统蓝。优先使用产品和道具驱动的转场:
| 时间段 | 内容 |
|---|---|
| 0.00—4.45 秒 | 产品在远景出现,手与产品发生短暂且自然的接触。产品由远到近进入主视觉,随后产品本体撤离画面,并同步露出"Apple + 英文产品名"。产品完全离场后,标题独立停留在纯白背景中。不得使用手捏不存在的附件。手的动作必须符合产品结构,例如握住杯身、触碰边缘、按压按钮或拿起把手。 |
| 4.45—7.25 秒 | 依次出现"这一次,我们""重新定义了"。随后把中文产品名称拆成一个或两个大字、短词进行展示。 |
| 7.25—9.20 秒 | 出现"六款全新配色"。六款产品通过与产品相关的液体、粉末、雾气、原料或材料云显现,组成克制的放射构图或整齐阵列。 |
| 9.20—13.70 秒 | 六款产品分别进行约 0.75 秒的节奏硬切。每一款必须同时展示对应产品、真实环境元素和准确名称。颜色和原料必须清楚区分。 |
| 13.70—16.70 秒 | 展示产品结构微距和结构文案。通过产品局部放大擦过镜头,进入交互或配件功能特写。配件尺寸、方向和连接关系必须合理。 |
| 16.70—19.60 秒 | 展示内部性能文案和产品切面。选择一个核心内部元素进行明显的微距动作,例如一粒爆珠爆汁、一个核心元件启动或一滴液体释放。内部元素必须比例合理、分布自然,不能整齐排成一行。 |
| 19.60—24.25 秒 | 产品连接手机,出现准确的蓝牙或连接文案。手机向镜头推进完成遮挡转场,进入全屏控制卡片。展示两项与产品相关的控制参数及明确数值。 |
| 24.25—27.00 秒 | 出现"小孩子才做选择"。两款产品对角交叉擦过镜头。左侧出现"成年人",右侧出现与产品相关的成人结论文案。丰富的原料、配件或材料进入画面。 |
| 27.00—30.00 秒 | 六款产品按固定顺序形成最终阵列,稳定保持。随后淡入纯白场,中央保留一个极小的渐变产品图标直到结束。 |
在生成正式视频前,建议先生成 14 至 16 张 16:9 横版关键帧。关键帧最低分辨率为 1280×720。
推荐关键帧:
流程要求:
可以自动进行一次免费修正的问题:
不要进入没有止境的关键帧重生成循环。
生成正式提示词时,必须把所有方括号内容替换为当前产品的真实设定,禁止提交未填写的占位符。
制作一条30秒、16:9、720P、24fps观感的高端写实CG产品发布广告,主题是"假如苹果做[中文产品]:[Apple英文产品名]"。
整体采用纯白高键无缝影棚、巨大留白、柔和顶侧光、苹果发布会式镜头语言、克制的剪辑节奏、纤细渐变字体动画和产品驱动转场。主体必须是当前设计的[产品名称],禁止出现其他品类产品和无关文案。
固定产品设定:
[写明产品轮廓、比例、材质、标志、接缝、盖子、把手、接口、配件位置以及必须保持一致的部分。]
六款产品固定为:
[依次写明每一款的名称、颜色、材料或食材、环境元素。]
文字最高优先级:
以下文字必须逐字逐标点原样生成,禁止改写、错字、漏字、增字、乱码和额外文案。文字出现后逐帧锁定。
英文字体接近SF Pro Display Light或Thin,中文字体接近PingFang SC Light或Thin。叙事标题使用#8B5CF6到#58C878的紫蓝青绿渐变,无描边、无阴影、无底板。标准入场为0.25至0.40秒横向遮罩显现,并从下方轻微上移。文字优先由产品或道具遮挡擦除。
0.00—4.45秒:
[写明手与产品的自然接触、产品从远景推进到近景、产品撤走,以及准确的英文产品名如何显现。产品完全离场后标题单独保持。]
4.45—7.25秒:
依次出现准确文字"这一次,我们""重新定义了"。随后展示拆分后的中文产品名称。
7.25—9.20秒:
出现准确文字"六款全新配色"。六款产品通过相关液体、粉末、薄雾、材料云或原料揭晓,形成放射构图或阵列。
9.20—13.70秒:
[逐项写出六个时间段、六款产品、环境元素和准确名称。每款约0.75秒,使用节奏硬切。]
13.70—16.70秒:
[写出准确结构文案、结构微距、擦镜动作、准确交互或配件文案,以及真实物理动作。]
16.70—19.60秒:
[写出准确内部性能文案、产品切面、一个核心内部元素的微距动作和准确收益文案。]
19.60—24.25秒:
[写明连接手机、准确蓝牙文案、手机遮挡转场、全屏控制卡片、两项产品相关设置及准确数值。]
24.25—27.00秒:
出现准确文字"小孩子才做选择"。两款产品交叉擦镜。左侧出现"成年人",右侧出现[准确成人结论文案]。丰富配料、附件或材料进入画面。
27.00—30.00秒:
六款产品按固定顺序形成最终阵列并稳定保持。随后淡入纯白场,极小的渐变产品图标保持到最后。
转场总则:
使用产品推进、产品撤离露字、前景物擦镜、六款硬切、结构微距遮挡、手机遮挡和结尾白场。禁止无意义的模板转场。
音乐与音效:
极简未来感电子氛围音乐。产品移动使用轻柔whoosh,款式硬切使用轻微click,配件连接使用克制snap,内部元素使用清脆pop,手机连接使用短促系统提示音。
绝对禁止:
错字、乱码、额外文字、额外品牌、水印、二维码、黑色边框、肮脏灰背景、产品结构漂移、产品融化、穿模、重复配件、巨大内部颗粒、配料整齐排列以及与当前产品无关的旧文案。正式生成前必须检查:
检查以下项目:
如果平台支持媒体分析,验证:
抽查时间点: 约 1 秒、3.8 秒、5.5 秒、8.3 秒、六款产品切换点、14.5 秒、16 秒、18 秒、20 秒、22.5 秒、25.5 秒、28 秒和 29.5 秒附近的画面。
重点检查:
生成成功不等于质量完全合格。必须如实报告肉眼可见的错误。
只有满足以下任一条件,任务才算结束:
最终向用户交付:
本技能为创意概念与戏仿作品生成工具,与 Apple Inc. 无任何关联、授权或代言关系。生成内容中出现的"Apple"字样仅为风格化戏仿,不得用于误导消费者、虚假宣传或任何商业侵权用途。使用者需自行承担因使用本技能生成内容而产生的一切法律责任。
© huangbai-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (assets) in the repository root of huangbai-AI/ai-apple-video.
Open the folder on GitHubat commit cfd3ee1
Seedance Apple Keynote Video 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 |
|---|---|---|---|---|---|---|
| Seedance Apple Keynote Video this skillhuangbai-AI/ai-apple-video | 135 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Seedancesongguoxs/seedance-prompt-skill | 2.9k | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| SN Motion HTMLOpenSenseNova/SenseNova-Skills | 5.7k | — | ~2.2k | Automated safety check: Notes | MIT | |
| Seedance Prompt Endexhunter/seedance2-skill | 4.2k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Seedance Japanese Prompt ExamplesEmily2040/seedance-2.0 | 7.6k | 1 repos | ~898 | Automated safety check: Pass | MIT | |
| Seedance 2 5 Video Directorliyue-aigc/seedance-2-5-video-director | 599 | — | ~3.5k | Automated safety check: Pass | MIT |
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
OpenSenseNova/SenseNova-Skills
Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.
dexhunter/seedance2-skill
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation.
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.
liyue-aigc/seedance-2-5-video-director
Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5.
dexhunter/seedance2-skill
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。
Works with
Categories
把任意普通产品(食品、日用品、家电等)包装成一款刚刚发布的高端消费电子产品,用 Seedance 2.5 生成一条 30 秒、苹果发布会风格的 AI 产品介绍视频。作品具有荒诞反差与视觉高级感:设定一本正经地荒诞,画面、材质、灯光、镜头和剪辑严肃、克制、精致。. Seedance Apple Keynote Video is an agent skill from huangbai-AI/ai-apple-video.
Seedance Apple Keynote Video fits situations like: tasks that involve AI video generation.
Run `npx skills add huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a claude-code`. Or copy the skill folder (the huangbai-AI/ai-apple-video repository) into .claude/skills/seedance-apple-keynote-video in your project. Claude Code loads it when a task matches its description.
Run `npx skills add huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a codex`. Or copy the skill folder (the huangbai-AI/ai-apple-video repository) into .agents/skills/seedance-apple-keynote-video in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huangbai-AI/ai-apple-video --skill seedance-apple-keynote-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedance-apple-keynote-video, .gemini/skills/seedance-apple-keynote-video, .github/skills/seedance-apple-keynote-video and .opencode/skills/seedance-apple-keynote-video in your project.
SKILL.md names no scripts, command-line tools or credentials: Seedance Apple Keynote Video is instructions for the agent only.
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.
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.
Seedance Apple Keynote Video is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Seedance Apple Keynote Video: Seedance (songguoxs/seedance-prompt-skill, 2.9k stars), SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars), Seedance Prompt En (dexhunter/seedance2-skill, 4.2k stars) and Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
huangbai-AI (a GitHub user) maintains it in huangbai-AI/ai-apple-video, which has 135 GitHub stars. The repository was last updated on September 7, 2026.
Source: huangbai-AI/ai-apple-video on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.