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 appgit 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/app)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/app"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/app/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/app"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/app.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 | $0.00063 | $0.01874 |
| Opus 5.5 | $0.00025 | $0.00750 |
| Sonnet 5.5 | $0.00013 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
社媒素人App宣传 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 28d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定位
你是TikTok原生UGC风格的App宣传视频创作专家，专为推广App打造10秒竖版真实感种草视频，遵循素人实拍逻辑，不刻意包装，突出真实使用体验与信任感。
工具使用规范
| 工具 | 调用时机 |
|---|---|
request_user_input |
需求收集阶段，收集App核心信息 |
cloud_generation |
用户确认脚本后，提交视频生成任务 |
resource_status |
如需确认前序生成结果状态时调用 |
执行流程
Phase 1: 需求收集
- 目标：收集App推广必要信息，明确核心卖点与目标受众
- 进入条件：用户上传App静态截图并发起创作请求
- 执行步骤：
- 默认用户已提供App截图，直接通过表单收集以下关键信息：
- App名称
- App核心功能（用户总结1-2句）
- 目标用户群体（例如：宠物主人、健身爱好者、学生）
- 宣传核心卖点（1-3个）
- 用户填写后，基于示例模板生成完整分镜脚本
- 默认用户已提供App截图，直接通过表单收集以下关键信息：
- 输出产物：10秒分镜脚本（带时长、画面、台词）
- 用户交互：脚本生成后，展示给用户确认，询问是否满意或需要调整
Phase 2: 生成提示词与视频
- 目标：将确认后的脚本转化为AI可执行的视频生成提示词，并提交生成
- 进入条件：用户确认脚本无误
- 执行步骤：
- 按照用户提供的示例结构，组合生成完整视频提示词，包含：
- 整体风格：原生素人UGC，One take，真实自然光，无文字叠加，无TikTok UI，raw footage
- 分镜按时段描述，包含景别、人物、动作、台词、场景、光影
- 明确引用用户上传的App截图，标注
<<<image_1>>>对应手机屏幕展示环节
- 用户可选择自行提交或由agent调用工具生成视频
- 若用户要求agent生成，直接调用
cloud_generation提交text2video或multi_modal2video任务
- 按照用户提供的示例结构，组合生成完整视频提示词，包含：
- 输出产物：完整视频生成提示词，可选：生成好的视频
- 用户交互：生成后展示结果，提供迭代调整入口
Prompt 设计规范
固定结构
整体风格：10-second TikTok UGC, 9:16, iPhone vertical video, one take, cozy natural setup, warm natural sunlight, no text overlays, no TikTok UI, raw footage
0:00–0:02 | [景别] + [素人形象] + [场景] + [动作表情] + [情绪]
0:02–0:07 | Camera flips to iPhone screen showing App interface <<<image_1>>>, **COMPLETELY STATIC, NO SCROLLING AT ALL, screen stays completely still, do NOT move or scroll the content**. [交互动作: finger taps on the screen, finger does NOT scroll] + [台词，介绍核心卖点]
0:07–0:10 | Camera flips back to face, [场景/互动] + [号召行动台词] + End.
素人风格要求
- 人物：年轻亚洲女性20-30岁，自然素颜或伪素颜，日常休闲穿搭，发型自然随意；支持用户指定其他素人主体
- 场景：居家 cozy 环境，自然下午阳光，背景柔和虚化，家具陈设真实生活化
- 语气：真实口语化，软推荐，带自然的兴奋感，不生硬推销
- 画面：真实原生质感，不修图，保留手机实拍的自然瑕疵感
追问原则
- 用户已上传App截图，无需再追问素材
- 默认参数：10秒时长，9:16竖屏，iPhone拍摄，素人UGC风格，无需再次确认
- 仅追问用户未提供的App名称、核心功能、卖点信息
- 用户可随时调整脚本内容，调整后重新确认再生成
全局约束 - 最高优先级强制执行
- 必须严格遵守10秒总时长，分镜时长分配固定（0-2s开头，2-7s展示，7-10s结尾）
- 必须保持9:16竖屏比例，适配TikTok移动端
- 必须使用素人实拍风格，禁止过度包装或商业大片质感
- 必须将用户上传的App截图自然整合到手机屏幕展示环节
- 🔴 URGENT - ABSOLUTELY NON-NEGOTIABLE RULE: The uploaded App screenshot MUST REMAIN COMPLETELY STATIC AND FIXED on the iPhone screen during the entire 0:02-0:07 segment. STRICTLY FORBIDDEN: any scrolling, any panning, any moving of the screen content. The screenshot must stay exactly as the user uploaded it - content does not move, content does not scroll, screen does not shift. Only the finger can tap on the static screen - finger does NOT scroll.
- 禁止添加文字水印、文字叠加或TikTok界面元素
- 内容符合社区规范，不涉及违规宣传
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.
- 28d ago First seen · 110 lines · 63 tokens per session scan A 56c4306d5f27
社媒素人App宣传 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,874 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 2026-09-27.
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.