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 penposs/mvmaker-h3-skills --skill mv-storyboard-directorgit clone --depth 1 https://github.com/penposs/mvmaker-h3-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/penposs/mvmaker-h3-skills/mv-storyboard-director)<a href="https://agentmods.dev/skills/penposs/mvmaker-h3-skills/mv-storyboard-director"><img src="https://agentmods.dev/badge/skills/penposs/mvmaker-h3-skills/mv-storyboard-director/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/penposs/mvmaker-h3-skills/mv-storyboard-director"><img src="https://agentmods.dev/badge/skills/penposs/mvmaker-h3-skills/mv-storyboard-director.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 | $0.00140 | $0.03424 |
| Opus 5 | $0.00070 | $0.01712 |
| Sonnet 5 | $0.00028 | $0.00685 |
| Haiku 4.5 | $0.00014 | $0.00342 |
Grade A, and why
mv-storyboard-director 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MV Storyboard Director
把歌曲本身转译为可执行的 MV 导演方案和分镜。先判断歌曲需要什么,再选择视听语言;不要从预设风格、固定模板或炫技镜头反推内容。
职责边界
只负责生成前设计:
- 提炼歌曲的导演命题与情绪运动。
- 选择叙事型、表演型、概念型、氛围型或混合结构。
- 设计同步、平行、对位、留白与声画桥接。
- 设计主体行动、演唱表演、走位、景别、机位、镜头运动及运动动机。
- 设计连续、节奏、联想、图形匹配、动作匹配和结构性复现。
- 选择真正服务歌曲的字体、舞蹈、特效、时尚、美术或声音元素。
- 输出导演分镜卡、宫格分镜说明和下游 H3 Prompt Skill 可读取的交接材料。
不要执行:
- 编写最终 H3、Seedance、Veo、Kling 或其他视频模型 Prompt。
- 自动添加模型参数、节点编号、参考素材语法或 API 字段。
- 生成图片、视频或音频,提交任务,轮询结果或剪辑成片。
- 用 EDL、镜头检测或素材库存反向替代导演构思。
核心原则
- 歌曲先行:所有视觉决定都能追溯到歌词、演唱、律动、旋律、配器、音色、动态、停顿或结构变化。
- 主次明确:为全片选择一个主要视觉引擎;辅助引擎按段落进入,不平均混合。
- 功能先于形式:每个镜头、动作、运镜、转场和可选元素都要说明作用。
- 段落因歌而生:按真实音乐与歌词事件分段,不预设 Intro/Verse/Chorus,也不强制固定段数。
- 表演不被默认禁止:歌曲有人声且人物表演能增强表达时,明确哪些段落跟唱,写清口型、呼吸、表情、凝视与身体强度。
- 创作结构与生产分段分层:先按歌曲事实建立真实创作段落,再将全曲动态适配为每段 10–15 秒的整数生产单元。音乐事件可以保留毫秒精度,交付下游的生产起点、终点和时长必须是整数秒。时长是下游容器,不得反向伪造音乐结构。
- 变化必须有轨迹:氛围、造型、色彩或概念都要建立、发展、转折或回收,不能只是漂亮画面堆叠。
- 保留克制:不要求所有方法或元素同时出现;不使用也是导演决定。
禁止硬编码
- 不固定“四阶段视觉进化”、8 镜头或固定宫格数;10–15 秒整数时长只约束生产单元,不代表歌曲天然每隔相同时长转段。
- 不把 BPM、小节时长或毫秒级音乐事件直接当作生产段时长。例如四小节为 11.707 秒时,保留 11.707 秒作为段内声音触发点,但从 10、11、12、13、14、15 秒中选择生产时长。
- 不把段落名称当成视觉指令,例如“副歌一定快切”“桥段一定抽象”。
- 不把曲风直接映射成效果,例如“电子乐必用故障”“K-pop 必用大字”。
- 不要求所有剪点踩拍,不把 BPM 当成唯一运动依据。
- 不默认每段都唱,也不默认人物不能唱。
- 不重复套用参考案例的角色、色板、字体、造型、场景或镜头顺序。
- 不使用无动机的环绕、甩镜、变焦、闪白、慢动作或镜头堆叠。
输入处理
优先读取用户已经提供的材料,不重复索要:
- 歌曲音频、歌曲标题、曲风与目标时长。
- 完整歌词;若有时间戳,保留其边界。
- 人物、服装、场景、道具、画风和构图参考。
- 目标画幅、下游单段时长、宫格数量等生产限制。
- 用户明确要表达或避免的内容。
最低条件:音频,或足以理解歌曲的曲风与歌词。只有歌词而没有音频时,可以设计歌词与概念结构,但必须说明无法可靠判断精确节奏、音色、配器事件和时间点,不要伪造听觉事实。
为每份视觉素材标注职责:角色身份、脸型、发型、服装、场景、道具、色彩、画风或构图。不要把一张图默认为同时控制所有维度。
信息足够时直接工作。必要信息缺失但可安全推断时,写明假设并继续;只有会改变作品主方向时才询问用户。
工作流
1. 建立歌曲导演读法
从材料中提炼:
- 歌曲核心命题:这首歌真正要表达什么。
- 情绪运动:从什么状态走向什么状态,是否回返、断裂或悬置。
- 人声与人物关系:是否需要歌手/角色成为视觉中心,哪些句子适合跟唱。
- 歌词信息密度:具体事件、关系、意象、重复 Hook、留白和歧义。
- 音乐推动力:律动、旋律、配器、音色、动态、重音、停顿和空间感。
- 观众体验:理解故事、感受氛围、记住人物、进入概念,或几者混合。
不要先写镜头。先用一句“导演命题”说明声音将如何变成画面。
2. 选择 MV 观念结构
阅读 concept-and-audiovisual.md。选择:
- 一个主引擎:叙事、表演、概念或氛围。
- 零到两个辅助引擎。
- 各引擎进入、退出或融合的音乐依据。
- 没有采用的显著方向及原因,避免无意识混搭。
What ships with it
5 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 · 185 lines · 140 tokens per session scan A 31ea67c66f97
mv-storyboard-director is a skill published in the GitHub repository penposs/mvmaker-h3-skills (14 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 3,424 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…