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 09git 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/09)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/09"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/09/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/09"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/09.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 | $0.00080 | $0.02721 |
| Opus 5.5 | $0.00032 | $0.01088 |
| Sonnet 5.5 | $0.00016 | $0.00544 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
影视剧作工坊-09-音效 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
音效（模块 09）
主链定位：背景音 / 对白 / 配乐 / 对白与口型（独立一级模块）。
做什么
把声音当作与画面平等的一等元素来导演，产出可进入提示词的并行音轨，而不是给画面配一个背景垫。
四条纪律贯穿本模块：
- 音频是并行轨道，不是画面附庸——对白、音效、环境音、BGM 四层分开描述，各自点名内容、时机与空间感；混成一团"有氛围的音乐"会让模型随机分配。
- 音乐不铺满——场景音乐过满、无源音乐起止随意会让观众疲劳，并削弱画面自身的判断力；留出安静的时刻让环境声与画面自己说话。
- 只在情绪手段做不到的地方才引入音乐——用音乐去修补、粉饰失败素材是最庸俗也最无效的做法；理想状态是"一两个非常鲜明的音符"。
- 信赖现实本身的音响——自然音响（風声、浪涛、发报机、树叶声）优先于专门谱写的配乐；声音不必与画面形象对应，只需与心理效果对应。
基础引擎
本模块的底层方法论源：engine/E09-音效.md（本模块目录内，20 条，来自 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。
其中几条对本模块最关键：主题音乐重复出现 + 分段变奏（同曲在不同叙事阶段改节奏、唱词与嗓音质地）、组织音响空间而不是谱写音乐（作曲家的任务是构造整片的音响总谱）、用真实声音的变形构造另一个世界（铁轨撞击声→合成器分解→回声）、沉默是结构性的（主动让人物失语，语言缺席本身承担意义）、剪接点配合重音（台词不停顿时转换镜头，剪接点落在重音词上）。
数据层（audio/）
| 文件 | 管什么 |
|---|---|
audio/01-对白.md |
对白轨道——四层音频的定位、内联法（短提示词首选）与专门块法（复杂音频）、按语言的对话同步词预算（15 秒片段：英语约 16–20 词 / 中文普通话同步最强 / 俄语约 10–15 词 / 日韩测试不足）、逐模型音频实践（Kling 3.0 与 3.0 Omni / Seedance 1.5 Pro / Seedance 2.0 / Veo 3 与 3.1 / Grok Imagine Video）、[AUDIO: Xs] 脚本块、Cinema Studio 3.0 音频 |
audio/02-环境音.md |
环境声（Ambient）轨道——背景声景写法、元素最多 2–3 个（再多就浑浊）、用声学描述空间（"混响明显的教堂大厅""局促的车内"）、用声音与寂静的对比制造冲击（"死寂。然后——一声脚步。"）、音频作为提示元素（SCELA） |
audio/03-配乐.md |
BGM 轨道——描述配器·速度·情绪而非流派标签（"紧张的弦乐，逐渐推进"优于"悬疑音乐"）、音乐进出时机、NO BGM 是规格而 no music 只是偏好、枚举与否定词规则的冲突提示、Beat sync（节拍同步）——音频为画面编舞、卡点剪辑（把分开生成的片段组装到一条轨上）、15 秒提取问题（选好窗口，别直接上传整轨）、场景音频生成 Seed Audio 1.0、Standalone Audio 标签页与生成后配音工作流 |
audio/04-口型对白匹配.md |
口型同步轨道——Lip-Sync 该做/不该做、多角色对白的变通办法（分开生成 + 画中画 + 线性遮罩 15% 羽化 / 聆听者用静态图片）、[AUDIO: Xs] 脚本块、常见音频故障与修复、何时可以不加音频 |
audio/05-后期音乐与声音设计.md |
后期音乐与声音设计（script-writing-studio）——后期 BGM / 配乐 / AI 音乐 / 音效 / 静默点 / 声音方案设计 |
audio/06-声音与BGM.md |
声音与 BGM 落地规则——对白 / 配乐 / 音效的落地规则 |
执行流程
- 定声音层档位与分工 —— 先声明输出档位：
- 全量档（默认）：⑧对白 + ⑨背景音 + ⑩BGM 三轨齐全，打开即成品；
- 去配乐档：拿掉 ⑩BGM、保留 ⑧⑨，为后期配乐留出音区——⑩ 写
NO BGM（规格级），不是省略（Seedance 2.0 自带音效/配乐，不声明 ≠ 不生成）；该档不得残留任何音乐类 token（除NO BGM本身）。 再决定这个镜头需要几层，不存在的层显式写"无"（无对白 / 无 BGM），而不是省略。
- 选写法 →
audio/01/audio/03短提示词走内联法；复杂音频（多层 + 时机）走专门块法（视觉内容在前，Audio:块在后分轨罗列）。 - 写对白 →
audio/01对白要短——每个角色每镜头 1–2 句；指明情绪语气（"急切地说""低语""隔着房间喊"）；非英语指明语言与方言（She speaks in Cantonese: "走啦"）。按语言核词预算（15 秒英语约 16–20 词；超预算就把次要台词转成身体行为——保留主导权翻转的那句）。 - 写环境音与 SFX →
audio/02环境声元素 2–3 个封顶；描述空间的声学而不只是元素清单；需要冲击时用"声音—寂静"的落差。音效记法事件@秒。 - 写 BGM →
audio/03描述配器 + 速度 + 情绪，不给流派标签；点名音乐进出时机；明确压制音乐时写NO BGM（规格级），不要只写no music（偏好级）。卡点类内容写"剪切卡在强拍上""运动在 drop 处达到峰值"。 - 过口型同步 →
audio/04对白片段保持 3–8 秒（准确率最佳区间）、用中近景或更近取景、每镜只有一张说话的脸、机位锁locked-off static camera或slow Dolly In；头部/面部运动 token 与对白不能同镜。多于一个角色要说话时走变通办法，不在一条提示里硬塞。 - 防覆盖 —— 上传音频被生成式音频引擎覆盖时，加时间戳锚定（"音频 @Audio1 从 0 秒到结尾严格按上传内容播放"）并删掉所有环境音/音效/音乐 token。
- 交下游 —— 音频纪律的最终校验（口型不同步、BGM 压过对白、填充嘟囔）归 13 交付文件审核（
review/13-失败诊断.md§三音频两症、§4.7 填充嘟囔）；L 切/J 切用声音桥磁化接缝归 10（editing/05-剪辑与连续性词汇.md）。
What ships with it
7 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.
- 11d ago First seen · 76 lines · 80 tokens per session scan A 196e1876019b
影视剧作工坊-09-音效 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 2,721 once invoked, about $0.0003 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.