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 13git 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/13)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/13"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/13/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/13"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/13.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 | $0.00149 | $0.03744 |
| Opus 5.5 | $0.00060 | $0.01498 |
| Sonnet 5.5 | $0.00030 | $0.00749 |
| Haiku 4.5 | $0.00015 | $0.00374 |
Grade A, and why
影视剧作工坊-13-交付文件审核 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交付文件审核（模块 13）
主链定位：PV 校验 + TD 放行 + T2V/I2V 交付规格 + 负面约束总库。
做什么
本模块是 13 级主链的最后一道闸门，也是整条链的质量闭环。它做三件事：
- 放行 —— 交付文件能不能出（PV 校验 + TD 放行）。
- 定规格 —— 交付按 T2V 还是 I2V 出、字段与形态怎么钉死。
- 兜底与复盘 —— 负面约束总库集中取用；生成之后失败时，走失败诊断层定位、裁定、记录。
本模块无 engine/：四本导演学专著不覆盖交付审核与失败诊断，本模块的知识源是数据层而非方法论引擎。
数据层
⚠️ 本模块只判不合，不持有拼装规则。 交付文件的制造（三模式顺序、即梦形态、负面三法）全部归 12—— 顺序见
12/SKILL.md§按模式的拼装顺序；即梦形态见12/platform/09-即梦交付拼装规格.md（负面三法的规则归属地）。 本模块拿它们当尺子判合规。同一份交付文件里，12 出的规则与 13 判的判据不得混写。
| 目录/文件 | 管什么 |
|---|---|
review/13-失败诊断.md |
失败分层（<10 秒 = 过滤器 / >30 秒 = 渲染）· 常见问题速修表 · 动作迁移失败速查 · 失败模式图谱（逐帧审查 / 失败抢救 / NSFW 误判 / 关键帧发明 / 物理状态锚 / 动作回摆 / 填充嘟囔）· 诊断树与预检清单 · 镜头五种裁定 · 视觉锚定诊断 · 记录纪律 |
review/14-交付规格与合规判据.md |
按模式的交付合规判据——通用判据 G1–G10 · 文生视频 T1–T5 · 首帧 F1–F6 · 首尾帧 L1–L7；每条可一眼判定，FAIL 即阻断放行，并给出按判据编号的退回路由（退 12 / 04 / 08 / 09）。分工：12 制造（怎么拼），本文件判合规（拼出来必须满足什么）。其中 G10「即梦负面三法」拿 12/platform/09 §三 当尺子 |
review/15-负面词全量（导演plus5.0）.md |
负面提示词全量提取（导演plus 5.0.0）——核心词表总表 + 按类分表，各条目标注原始出处文件。⚠️ §四「即梦负面词三法」为提取归档，规则归属地已迁 12/platform/09 §三 |
review/16-负面约束总集.md |
负面约束总集（漫剧导演全流程工作台）——五层级组织：全局层（每条 prompt 必附的底座负面词与注入机制）/ 引擎层 / 模块层 / 场景层 / 特例层；收录「禁止出现 / 反向规避 / 黑名单 / 禁忌 / 绝对禁止 / 负面词 / 禁止继承 / 互斥禁令」全部成体系条款 |
失败诊断闭环（review/）
第一步永远是分层，不是修复
总纲：诊断先于修复。绝不在诊断之前原样重发——同样的文本会绊响同一个分类器、踩中同一处渲染边界；重发不是诊断。
| 失败时机 | 含义 | 该做什么 |
|---|---|---|
| < 10 秒（即时） | 内容过滤器拒稿——提示词根本没到渲染层 | 按语气重写 + 移除风险词。绝不绝不绝不原样重新生成 |
| > 30 秒（延迟） | 基础设施、超时或复杂度——提示词过了过滤器但渲染失败 | 简化动作密度、缩短时长、再试 |
循环出现的即时失败是过滤器问题，绝不是渲染能力问题——在重写完成之前，先拦住重新生成的手。
先分岔——系统性还是随机性
在约 1.5% 的视频通过率门槛下，大多数失败是方差，不是提示词坏了。
- 失败都是同一种失败 → 系统性：提示词错了，走单变量迭代。
- 失败方式五花八门、偶尔接近命中 → 随机性：锁定提示词，批量开火，然后淘汰。
防线：一个保留者、其余全部记账（保留 + 真实的淘汰原因），分母保持诚实。整批都过不了硬性闸门 → 失败终究是系统性的，停止收割，回去迭代。
镜头裁定——交付镜头的五种裁定
修复处理的是彻底失败；大多数真实交付落在中间地带部分可用。任何东西重新触发之前，每条交付镜头必须拿到五种裁定之一：
| 裁定 | 适用情形 | 下一步 |
|---|---|---|
| 保留（Keep） | 镜头使命已交付，无致命伤 | 锁定、记录、继续 |
| 后期修复 | 瑕疵属于剪辑师的领域（调色、文字、混音、修剪、首尾帧不稳） | 绝不为几分钟能剪好的事烧掉好几条 |
| 编辑而非重生成 | 构图与时机都对，恰好只有一层错了 | 只修出错的那一层——"当编辑而非当重跑器" |
| 重掷（Re-roll） | 提示词是对的，只是采样运气不好 | 同一提示词原样再来 |
| 重写（Rewrite） | 同一瑕疵出现在两条镜头上 | 是系统问题不是运气——先诊断，再改提示词 |
What ships with it
4 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 · 149 lines · 149 tokens per session scan A 455fccba6b3a
影视剧作工坊-13-交付文件审核 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 149 tokens to every session and 3,744 once invoked, about $0.0006 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.