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 jis60224/ai-comic-skills --skill ai-comic-video-promptsgit clone --depth 1 https://github.com/jis60224/ai-comic-skillsWrote 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/jis60224/ai-comic-skills/ai-comic-video-prompts)<a href="https://agentmods.dev/skills/jis60224/ai-comic-skills/ai-comic-video-prompts"><img src="https://agentmods.dev/badge/skills/jis60224/ai-comic-skills/ai-comic-video-prompts/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/jis60224/ai-comic-skills/ai-comic-video-prompts"><img src="https://agentmods.dev/badge/skills/jis60224/ai-comic-skills/ai-comic-video-prompts.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 | $0.00301 | $0.03095 |
| Opus 5 | $0.00151 | $0.01548 |
| Sonnet 5 | $0.00060 | $0.00619 |
| Haiku 4.5 | $0.00030 | $0.00310 |
Grade A, and why
ai-comic-video-prompts 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 漫剧单镜头视频提示词转换技能
本技能接在 ai-comic-storyboard 之后：分镜表已经写好，现在把每个镜头改写成 AI 视频工具更容易理解的完整单镜头提示词，方便逐条复制到 Vidu 等工具生成视频素材。
核心目标：镜头能看懂，角色不变脸，场景不跳变，动作能接上，台词和音效写进提示词。
核心原则
- 所有回复使用中文。
- 一镜一提示词：每个镜号只输出一条完整提示词。台词、画外音、音效必须写进"完整提示词"里，不要拆成独立列。
- 忠于分镜表：不改变镜头顺序、不新增剧情、不改原台词。必要时可把分镜里的抽象情绪翻译成可见动作。
- 保持参考一致性：提示词开头必须说明人物五官、发型、服装、年龄感、气质、场景结构、画风与参考图保持一致。
- 动作写完整过程：写清动作起始、动作变化、动作结果，不要只写"紧张/害怕/震惊"。
- 场景必须有动态：补充光线变化、雨水、风声、屏幕光、灯光闪烁、背景空间等环境状态，避免静态硬照感。
- 限制项必带：每条提示词末尾都要有稳定性限制，尤其是人物不变脸、不换发型、不换服装、场景不跳变。
- 所有产出落盘：单镜头提示词、素材生成记录、筛选补镜记录和质检清单都写入项目文件夹。
工作流程
阶段零：定位分镜和素材来源
- 扫描当前目录，查找 AI 漫剧项目文件夹。优先识别：
00_剧本概览.md07_视觉资产/08_分镜脚本/
- 读取目标集分镜表：
- 默认读取
08_分镜脚本/01_第01集_完整分镜表.md - 用户指定第X集时，读取
08_分镜脚本/01_第XX集_完整分镜表.md - 如果用户只给片段分镜，读取对应
01_第XX集_片段名_分镜表.md
- 默认读取
- 读取素材索引：
07_视觉资产/00_视觉资产总览.md07_视觉资产/01_人物提示词.md07_视觉资产/02_场景提示词.md07_视觉资产/03_道具提示词.md- 分镜表中的"使用素材"列
- 没有分镜表时，不要从剧本直接生成视频提示词；提示用户先用 ai-comic-storyboard 生成分镜表，或让用户粘贴包含镜号、景别、运镜、画面内容、台词音效、时长、使用素材的分镜片段。
- 检查是否已有提示词产物：
- 如果已有
09_视频提示词/，先读取总览和目标集提示词文件。 - 生成第2集及后续集数时，禁止覆盖已有提示词、生成记录或筛选记录；目标文件存在时，除非用户明确要求修改，否则另存为
_v2或先询问。
- 如果已有
阶段一：检查分镜是否能直接转提示词
逐镜检查分镜表。每个镜头至少要有：
- 镜号
- 景别
- 运镜
- 画面内容
- 人物动作 / 表情
- 台词 / 画外音 / 音效
- 预估时长
- 使用素材
如果某个镜头只有抽象表达，如"女主很害怕"，先补成可见动作：后退半步、瞳孔微缩、手指发紧、呼吸变轻、眼神闪烁等。
阶段二：生成单镜头 Vidu 提示词
每条提示词必须包含以下信息：
| 模块 | 写法要求 |
|---|---|
| 参考图一致性 | 保持同一角色/场景/道具参考图：五官、发型、服装、年龄感、气质、画风、场景结构不变 |
| 素材调用 | 写清调用哪些人物主体、场景母版、道具图或关键帧；缺素材则标 待补素材_名称_用途 |
| 镜头语言 | 景别 + 运镜 + 节奏，如 近景，缓慢推镜头 |
| 动作过程 | 动作起始、动作变化、动作结果 |
| 情绪可视化 | 把紧张、震惊、压抑等翻译成眼神、手部、呼吸、身体姿态 |
| 场景氛围 | 光线、色调、天气、空间、环境动态、悬疑/甜宠/压迫等氛围 |
| 台词与音效 | 原台词不改；画外音要标注；环境音、动作音、情绪音写进提示词 |
| 画质描述 | 电影级光影、超写实、高细节、4K画质、画面稳定、质感细腻 |
| 限制项 | 无画面畸变、无模糊、无结构错误、无多余肢体、无重复人脸、人物不变脸、不换发型、不换服装、场景不跳变 |
提示词模板
保持参考图中的【角色/场景/道具】一致：【人物五官、发型、服装、年龄感、气质】保持不变，【场景结构、光线、色调、画风】保持一致。镜头语言为【景别 + 运镜 + 节奏】。画面中【人物/主体】位于【空间位置】，动作从【起始动作】开始，随后【动作变化】，最后【动作结果】。人物表情与情绪表现为【可见表情/眼神/手部/身体反应】。场景为【具体环境】，包含【光线/天气/背景动态/关键道具】，整体氛围【情绪关键词】。台词/画外音：【保留原台词】。音效：【环境音】；【动作音】；【情绪音】。电影级光影，超写实，高细节，4K画质，画面稳定，质感细腻。无画面畸变、无模糊、无结构错误、无多余肢体、无重复人脸、人物不变脸、不换发型、不换服装、场景不跳变。
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.
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 · 183 lines · 301 tokens per session scan A 7a32fa8121e6
ai-comic-video-prompts is a skill published in the GitHub repository jis60224/ai-comic-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 301 tokens to every session and 3,095 once invoked, about $0.0015 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 2026-08-31.
Other skills, from other repositories
comic-mv-director
A production planner for animated stories, short dramas, music videos, and other AI video projects. It first decides whether the project is music-led or story-led, then plans storyboards, images, video, music, and editing.
shot-optimizer
A Chinese-language assistant for developing shots in films, animated stories, short videos, and music videos. It helps turn a rough shot idea into several prompt variations and tracks versions such as V1, V2, and V3.
story-director
A story-planning assistant that turns a rough idea into a structured storyline and a shot list. A shot list breaks a story into individual camera views, each with a purpose and visual direction.
seedance-2-guide
A reference guide to Seedance 2.0, an AI tool for generating videos from text and reference material. It explains the model's work modes, reference controls, prompt structure, and suitable video-making situations.
ai-tech-wechat-writer
A tool for turning supplied content into styled HTML articles for WeChat Official Accounts, a Chinese publishing platform. It follows a fixed five-part structure for AI news posts and supports publishing workflows.
shaka-design-system
A shared design rulebook for Shaka content, covering themes, fonts, components, and visual principles. Other content-making tools read it as their common source of design rules.