影策 is an open-source workspace for AI film and short-video production, using a freeform canvas and structured workflows to organize scripts, characters, scenes, storyboards, media assets, and generated text, images, video, and audio. It is for creators who manage audiovisual projects through local or trusted deployments, with features for task tracking, asset management, timelines, and AI-agent workflows.
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 ddcat-ai/open-ai-canvas --skill 06git clone --depth 1 https://github.com/ddcat-ai/open-ai-canvasWrote 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/ddcat-ai/open-ai-canvas/06)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/06"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/06/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/ddcat-ai/open-ai-canvas/06"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/06.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 | $0.00100 | $0.03451 |
| Opus 5.5 | $0.00040 | $0.01380 |
| Sonnet 5.5 | $0.00020 | $0.00690 |
| Haiku 4.5 | $0.00010 | $0.00345 |
Grade A, and why
影视剧作工坊-06-景别构图机位灯光 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
景别、构图、机位与灯光（模块 06）
主链定位：画面坐标系 / 空间约束与构图词汇 / V4 构图引擎 / 物理灯光与夜景语域。
核心原则（四件事各管一层）
- 景别 —— 控制主体在画面中占多大、可见多少环境。按"要表现的是世界、角色还是细节"来选。
- 机位角度 —— 控制摄影机与主体的垂直与空间关系。角度就是情绪解读：仰拍＝力量，俯视＝脆弱，荷兰角＝不安，虫瞰＝超现实。
- 构图 —— 三者的叠加与编排。最强的提示词把景别、角度、运动暗示（静帧）或镜头运动（视频）全部点名，再以光线与风格收尾。
- 灯光 —— 四条纪律：
- 点名光源，不点名情绪 —— "有情绪的""戏剧化的""电影感的"只能被模型近似；被点名的物理机制才能被一致地渲染。单靠"低调布光"不够——它只说了有多暗，没说光从哪里来。
- 光是场景中的物理事件 —— 说明光源位置、它从哪些表面反射、由此形成的阴影几何。
- 相邻镜头没有共同的起点观感 —— 每条生成素材都自带出厂调色，跨镜头的灯光统一靠逐字重复与全局前缀锁定。
- 整合时超出色彩层面 —— 只做色彩匹配是最常见的"像贴上去的"失败；主光方向、环境反光、大气、边缘落地要一起匹配。
术语约定：[img 1] 与 @Image1 均指"第一张参考图"；未使用参考图时替换为角色描述或 @ 元素引用。静帧与视频的差异处已分别标注。
基础引擎
本模块的底层方法论源：engine/E06-景别构图机位灯光.md（本模块目录内，64 条，来自 book01/book02/book04）。
执行本模块前先查阅该引擎，取其判断依据、创作准则与反模式清单；引擎为只读源层，本模块负责执行流程。
镜头语言层（shotlang/）
| 文件 | 管什么 |
|---|---|
shotlang/01-景别.md |
十种景别（画面词汇总表）、三张阶梯总纲、视频侧八级短语表、六级法则尺与十级→六级归档（双重对比判定刻度，与隔级切级差判分工）、FOV 锚点、焦段与光圈、按镜头类型的时长分配 |
shotlang/02-机位与角度.md |
十种机位角度、角度即情绪解读、视频侧补充词汇 |
shotlang/03-构图.md |
三要素叠加公式、静帧提示词公式、画幅比例（输出比例枚举值 vs 变形宽银幕风格语域，两者不可混写）、可测量语言纪律 |
shotlang/04-灯光.md |
四条灯光纪律、18 种灯光方案总表、场景物理灯光四要素、夜景寄存、频闪、六大灯光预设、题材默认布光、灯光教义、光效整合四层配方、色温与量化单位、灯光瑕疵速查 |
shotlang/07-空间约束.md |
空间约束六层体系——帧坐标系 / 空间布局块 / GEO 场景布局块（每场景一份、只写场所、逐字粘贴）、定场 wide 与角色计数头、坐标走位扩展记法、深度图与走位参考图；含进门走廊穿家具、群像无主肢体、走路的循环物理、打斗接缝四类失败的修复与空间连续性速查 |
shotlang/05-镜头语言标准逻辑引擎.md |
CL 系列：CL-1 景别 / CL-2 角度 / CL-3 运动 / CL-4 衔接四法则 / CL-4a 场面调度 / CL-5 分镜表八要素 / CL-6 摄影机 / CL-7 Filmback |
shotlang/06-焦距库.md |
35mm 全画幅：10mm–200mm 逐焦段视场角、透视特性、叙事用途；9 格分镜焦距分配；焦距负面过滤词 |
shotlang/08-静帧构图.md |
静帧侧构图权威表（Higgsfield higgsfield-image-shots v3.0.0）——距离与大小景别 10 档（EWS / WS / Full / MLS / Cowboy / MS / MCU / CU / ECU / Macro，各含画面范围·用途·AI 提示词关键词·提示词示例）、机位角度（平视 / 仰拍 / 俯视 / 顶摄鸟瞰 / 虫瞰 / 荷兰角 / 过肩 / 主观视角 / 自拍角 / 贴地）、静帧五段图像提示词公式、与视频镜头控制的关键区别 |
shotlang/09-景别总清单.md |
景别总索引——视频版 10 个（higgsfield-camera）+ 静帧版 10 个（higgsfield-image-shots），含缩写与画面范围，用于快速点数与选择 |
shotlang/10-构图总清单.md |
构图总索引——视频机位角度 13 个 + 静帧机位角度 10 个 + 构图工具 5 组（构图词汇：空间分区/负空间/越轴规则/坐标记法；帧坐标系：定性锚 + 百分比坐标；空间布局块；三层叠加公式；俯视平面图与演出参考模板） |
shotlang/11-灯光总清单.md |
灯光总索引——9 种灯光类型 + 13 种经典布光技法（伦勃朗光/蝴蝶光/分割光/轮廓光/动机光/实用光源/明暗对照/高调/低调/黄金时刻/蓝调时刻/正午烈日/阴天漫射）+ Cinema Studio 3.5 灯光 6 预设 + 场景物理光·夜景寄存·频闪补充 |
shotlang/12-全镜头转换-景别-机位-焦距.md |
《全镜头类型精准转换总规范》第 2/3/5 章——景别体系全转换（八级定义、情绪阶梯、与焦距强制匹配、与时长匹配、全局负面约束、模型可执行句库）、机位角度全转换（平视/微仰/微俯/侧45/过肩/鸟瞰/荷兰角、情绪权力映射表、与景别组合、与情绪曲线绑定）、焦距体系全转换（13 档逐档转换句） |
shotlang/13-全镜头转换-构图-调度-竖屏-物理构图.md |
同规范第 18/20/26 章——场面调度体系全转换（三大空间体系 + 五种走位）、竖屏 9:16 构图转换全法则、物理构图引擎全转换 |
shotlang/14-灯光调色画幅（手册第四章）.md |
灯光、调色与画幅（AI 图像与影视提示词技术手册·第四章）——灯光词汇、场景物理灯光、夜景语域、频闪、调色语言、配色规则、胶片型号模拟、画幅比例：输出规格 vs 风格语域。注：手册的第三/五/六/十/十一 章经归位说明判定为同源重复，未收录 |
shotlang/15-镜头光学决策（cinedance）.md |
cinedance 镜头光学决策——镜头决策树、六段 FOV 语言块（8°–107°）、长焦/广角结果栈、光学反模式 |
shotlang/16-摄影机-动作速查表.md |
摄影机-动作速查表（script-writing-studio）——按动作类型反查机位与运动 |
shotlang/17-生成前空间预检.md |
生成前空间预检——站位校验卡，生成前先过空间一致性 |
shotlang/18-物理与灯光（cinedance）.md |
cinedance 物理与灯光——光线保持与灯光约束（物理真实性校验的灯光侧） |
What ships with it
19 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.
- engine/E06-景别构图机位灯光.md 22 KB
- shotlang/01-景别.md 10 KB
- shotlang/02-机位与角度.md 2.9 KB
- shotlang/03-构图.md 3.6 KB
- shotlang/04-灯光.md 14 KB
- shotlang/05-镜头语言标准逻辑引擎.md 33 KB
- shotlang/06-焦距库.md 10 KB
- shotlang/07-空间约束.md 15 KB
- shotlang/08-静帧构图.md 23 KB
- shotlang/09-景别总清单.md 1.6 KB
- shotlang/10-构图总清单.md 2.3 KB
- shotlang/11-灯光总清单.md 2.2 KB
- shotlang/12-全镜头转换-景别-机位-焦距.md 37 KB
- shotlang/13-全镜头转换-构图-调度-竖屏-物理构图.md 37 KB
- shotlang/14-灯光调色画幅(手册第四章).md 7.4 KB
- shotlang/15-镜头光学决策(cinedance).md 8.0 KB
- shotlang/16-摄影机-动作速查表.md 16 KB
- shotlang/17-生成前空间预检.md 9.0 KB
- shotlang/18-物理与灯光(cinedance).md 6.9 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.
- 11d ago First seen · 80 lines · 100 tokens per session scan A 22a70fc770ae
影视剧作工坊-06-景别构图机位灯光 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 3,451 once invoked, about $0.0004 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 2026-10-14.
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.