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 Supreme-Ultimate/novel-to-script-team --skill director-skillgit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote 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/supreme-ultimate/novel-to-script-team/director-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/director-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/director-skill/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/supreme-ultimate/novel-to-script-team/director-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/director-skill.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 | $0.00041 | $0.03492 |
| Opus 5 | $0.00020 | $0.01746 |
| Sonnet 5 | $0.00008 | $0.00698 |
| Haiku 4.5 | $0.00004 | $0.00349 |
Grade A, and why
director-skill 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 10d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
导演执行技能
必读
../../references/00-first-principles.md../../references/08-camera-and-cinematography.md../../references/09-storyboard-methodology.md../../references/10a-action-dialogue-scenes.md../../references/10b-atmosphere-fantasy.md../../references/19-micro-drama-storyboard-system.md— 微短剧分镜两阶段系统（第一阶段：视觉词典）- 使用时机：AI微短剧项目，参考视觉词典系统建立人物清单和场景清单标准
- 核心价值：角色词条（外貌锁定、表演基线、服装档案）、场景词条（空间锁定、光照状态）
../../references/20-frame-description-elements.md（帧图描述完整元素表）
进阶参考（按需查阅）
../../references/15-color-psychology.md— 色彩心理学（色彩情绪映射、色彩叙事原则）../../references/17-lighting-narrative.md— 光影叙事（光影情绪映射、明暗对比叙事）../../references/16-dramatic-principles.md— 剧作原理（三幕结构、冲突设计、节奏控制）
技能说明
剧本分析与导演讲戏技能。将剧本/梗概/分场大纲转化为：
- 导演讲戏本（按剧情点分节，每节包含元数据 + 导演阐述）
- 人物清单（用于服化道生成角色参考图）
- 场景清单（用于服化道生成场景参考图）
核心理念：导演像给演员讲戏一样，把脑海中的画面完整描述出来。 一个剧情点 = 一段完整叙事 = 一次 Seedance 2.0 生成任务。 段落内可包含多组镜头（如蒙太奇、快速闪回），但叙事上必须是一个完整段落。
输入
- 剧本/梗概/分场文本
- 视觉风格（用户指定）
- 目标媒介（电影/短剧/漫剧/MV/广告）
输出
outputs/<集数>/01-director-analysis.md— 导演分析（讲戏本 + 人物清单 + 场景清单）
执行流程
第一步：通读剧本
- 读取用户提供的剧本/梗概/分场文本
- 理解核心叙事线、人物关系、情感走向
- 识别关键转折点和高潮
第二步：拆解剧情点
将剧本拆分为若干剧情点（P01、P02、P03...），每个剧情点是一个完整的叙事段落。
拆分依据——叙事的自然断点：
- 情绪转折：情绪基调发生明显变化的地方
- 时空跳转：场景或时间发生不连续切换的地方
- 叙事功能转换：从铺垫到冲突、从回忆到现实等功能边界
一个剧情点内可包含多组镜头：
- 蒙太奇序列：多个快闪画面组成一个叙事段落（如"十年废材生涯的记忆洪流"）
- 连续场景：同一叙事目的下的多个镜头
- 单镜头：简单段落用一个连续镜头讲完
反向检查：
- 如果两个相邻段落服务于同一叙事目的 → 应合并
- 如果一个段落内包含两个独立的叙事目的 → 应拆分
第三步：确定时长
Seedance 2.0 单次生成 4-15 秒。根据段落的叙事密度选择时长。
时长选择参考：
| 时长 | 适用场景 |
|---|---|
| 5s | 单镜头，一个动作或表情变化 |
| 8s | 单镜头，一组连贯动作 |
| 10s | 多镜头，一段包含镜头转换的叙事 |
| 15s | 多镜头，完整的多场景叙事（如蒙太奇、连续切换） |
节拍密度约束（作用于每个连续镜头内，非整段）： 底层规律：AI 视频生成中，每个连续镜头内 1 拍 ≈ 2.5 秒屏幕时间。节拍太密，动作会糊、跳、不自然。
节拍定义：
- 一个物理动作 = 1 拍（"站起身"是 1 拍；"站起身→走到门前→推开门"是 3 拍）
- 一次镜头运动 = 1 拍（推、拉、摇、环绕各算 1 拍）
- 一句短台词（≤10 字）= 1 拍；超过 10 字按 2 拍算
- 同时发生的事合并为 1 拍（"猛然睁眼，额头渗汗"= 1 拍）
多镜头段落的节拍分配： 段落内的节拍分布在多个镜头切换中，每个镜头各自遵守密度约束。 例：15 秒蒙太奇可含 5 个子画面，每个 2-3 秒、1-2 拍，总节拍远超单镜头上限。
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.
- 10d ago First seen · 246 lines · 41 tokens per session scan A 94250d5eb0cd
director-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (163 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 3,492 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.