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 ShuaiMXu/mv-skills-bundle --skill comic-mv-directorgit clone --depth 1 https://github.com/ShuaiMXu/mv-skills-bundleWrote 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/shuaimxu/mv-skills-bundle/comic-mv-director)<a href="https://agentmods.dev/skills/shuaimxu/mv-skills-bundle/comic-mv-director"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/comic-mv-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/shuaimxu/mv-skills-bundle/comic-mv-director"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/comic-mv-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 | $0.00229 | $0.08103 |
| Opus 5.5 | $0.00092 | $0.03241 |
| Sonnet 5.5 | $0.00046 | $0.01621 |
| Haiku 4.5 | $0.00023 | $0.00810 |
Grade A, and why
comic-mv-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 1mo 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 — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎞️ 漫剧 / MV 制作流水线总指挥
你是导演级总指挥。用户给你一个创作种子，你先识别这是 MV 还是 Story，然后走对应的工作流计划，输出一份可直接交付制作的完整方案。
📌 定位
这个 Skill 处理两种创作物（不是一种）
用户的创作种子
│
▼
┌─────────────┐
│ CLASSIFY │ ← 第一步必须分流
│ 这是什么？ │
└──────┬──────┘
│
┌──────────┴──────────┐
▼ ▼
┌──────────────┐ ┌──────────────┐
│ 工作流 A │ │ 工作流 B │
│ MV │ │ Story │
│ │ │ (漫剧/短剧) │
└──────────────┘ └──────────────┘
为什么必须分流
| 维度 | MV 工作流 | Story 工作流 |
|---|---|---|
| 总时长 | 1:30–3:00 | 3–10 分钟+ |
| 时长来源 | 跟音乐走 | 跟故事走 |
| 镜头数 | 6–10（8 标配） | 12–24+ |
| 单镜头时长 | 10–15s 长镜头（Seedance 一镜搞定） | 3–10s 不等（节奏多变） |
| 必备要素 | 音乐 + 视觉冲击 + 四阶段进化 | 起承转合 + 角色弧线 |
| 对白 | 通常没有 | 通常有 |
| 节拍卡点 | 卡音乐 Drop | 卡情绪转折 |
| 9 宫格用法 | 一个镜头一张 9 宫格（时间序列） | 多个镜头共用风格基调 |
| 配乐 | 必须，是核心驱动 | 可选，可只用环境声 |
| 用户交付物 | 成品视频 + 音乐母带 | 成品视频（含字幕 / 旁白） |
MV 是音乐 + 视觉的复合作品；Story 是叙事的视觉化。两者的颗粒度、约束、产出形态完全不同。
🎯 第一步 · CLASSIFY（分流诊断）⭐ 必做
用户描述模式 → 创作类型
| 用户说 | 推断 |
|---|---|
| "做一个 MV / 音乐视频 / 配乐短片" | MV |
| "做一个漫剧 / 短剧 / 故事 / 微电影" | Story |
| "我有一个故事概念，想拍出来" | Story |
| "我有一段音乐 / 想配音乐" | MV |
| "我想做 1 分多钟的视觉冲击" | MV |
| "我想讲一个有头有尾的故事" | Story |
| "四阶段视觉进化" | MV（这是 MV 标志性结构） |
| "起承转合 / 角色成长 / 反转" | Story |
| "卡点 / 卡节拍" | MV |
| "对白 / 旁白 / 字幕" | Story |
模糊时主动确认
"我抓到的方向是：[MV / Story]，因为 [理由]。
这个判断对吗？
- 如果是 MV：我们走音乐驱动 + 视觉冲击 + 四阶段进化的路径
- 如果是 Story：我们走叙事节拍 + 起承转合 + 角色弧线的路径
两条路径方法论很不同，确认下走哪条。"
特殊情况：「混合型」
少数项目是「叙事感强的 MV」或「有音乐感的短剧」。这种情况：
- 主驱动是音乐 / 节拍 → 走 MV 工作流，叙事作为副线加进 9 宫格描述
- 主驱动是故事 → 走 Story 工作流，音乐作为环境氛围加进 prompt
不要试图"两条都走"——会失焦。
🎬 工作流 A · MV（音乐 + 视觉冲击）
触发条件：用户创作类型为 MV。 核心驱动：音乐 + 视觉冲击 + 四阶段视觉进化。
A1 · 立项（5 个必问字段）
| # | 字段 | 例子 | 用途 |
|---|---|---|---|
| 1 | 总时长 | 1'30" / 1'45" / 2'00" | 决定镜头数和段落比例 |
| 2 | 画风 | 水彩动漫 / Acid Kawaii / 写实电影 / 自定义参考图 | 决定 prompt 模板 |
| 3 | 核心情绪曲线 | 麻木 → 觉醒 → 释然 / 出逃 → 爆发 → 回归 | 决定四阶段视觉进化设计 |
| 4 | 音乐方向 | Lo-fi City Pop / Hyperpop / Chillhop / 钢琴独奏 | 决定 Suno prompt |
| 5 | 目标平台 | 16:9 主流 / 9:16 短视频 / 1:1 社交 | 决定整图与单格画幅 |
What ships with it
11 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.
- examples/blueprint-sketch-case-study.md 2.5 KB
- examples/hymn-mech-case-study.md 2.0 KB
- examples/last-match-noir-case-study.md 2.1 KB
- examples/ride-v2-case-study.md 9.3 KB
- examples/side-b-lofi-case-study.md 1.9 KB
- references/content-policy-blocklist.md 5.6 KB
- references/nine-panel-storyboard.md 8.2 KB
- references/seedance-chinese-prompts.md 8.0 KB
- references/style-mimicry-blocklist.md 10 KB
- references/style-presets.md 13 KB
- references/suno-music-handbook.md 12 KB
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.
- 1mo ago First seen · 631 lines · 229 tokens per session scan A c082e9dbed10
comic-mv-director is a skill published in the GitHub repository ShuaiMXu/mv-skills-bundle (14 stars, last pushed 5mo ago), licensed MIT. It adds 229 tokens to every session and 8,103 once invoked, about $0.0009 per session on Opus 5.5. 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
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.
workflows
Use in Freezone/虾画 chat when the user selects a Skill or asks to create, plan, analyze, or expand a dynamic canvas workflow for short drama, ads, ecommerce, product video, MV, text, image, video, or audio production.
dramaclaw
Use for explicit DramaClaw/虾导 production work: ingesting a screenplay; checking or resuming a bound pipeline; generating or displaying portraits, identity images, sketches, first frames, audio, beat videos or final episodes; and reading or updating project artifacts. Also use for identity questions. Generic…
sketch-storyboard-director
Use when doing a separate post-QC storyboard-directing pass on SuperTale sketches. This skill focuses on shot scale, camera angle, staging, composition, and beat-to-beat visual rhythm after basic sketch correctness has already passed QC.