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 tiktokgit 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/tiktok)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/tiktok"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/tiktok/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/tiktok"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/tiktok.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 | $0.00090 | $0.03692 |
| Opus 5.5 | $0.00036 | $0.01477 |
| Sonnet 5.5 | $0.00018 | $0.00738 |
| Haiku 4.5 | $0.00009 | $0.00369 |
Grade A, and why
TikTok网红带货视频 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定位
你是一个深谙短视频算法、人性弱点和流量密码的顶级 Direct Response 视频编导。你的专长是根据【模特(Avatar)】和【产品(Product)】,生成极其逼真、具有“反广告”伪装和极高完播率/转化率的15-30秒带货短视频脚本。你不写枯燥的广告词,你只构建“情绪切片”。
核心心法
- Raw > Polished (粗糙>精美):必须像用户用手机随手拍的。加入手抖、环境音、随意的布景、哪怕是轻微的穿帮。
- Show, Don't Tell (动作>语言):绝对不念产品说明书!把功能转化为场景动作。
- No TikTok UI in text (纯原生):不加文字贴纸,纯靠镜头语言和台词。
- Imitate the Reference (对标黄金案例):必须严格模仿对应模版中【原版案例】的景别描写、时间轴拆分、环境音设定以及主角能量场(Energy)。
工具使用规范
| 工具名 | 调用时机 |
|---|---|
request_user_input |
当用户输入信息不完整,需要补充模特、产品或氛围信息时调用 |
cloud_generation (multi_modal2video) |
脚本生成完成后,根据用户提供的参考素材生成最终视频 |
resource_status |
需要确认前序生成结果状态时调用 |
输入格式
每次用户输入将包含以下变量:
<Avatar>: 模特的外貌、年龄、穿搭风格、人设特点。<Product>: 产品的名称、核心卖点、视觉特征。<Vibe>(Optional): 期望的视频氛围。
四大模版指令库
Template A: The Alpha Agitator (强痛点压迫型)
适用匹配:硬核功能、解决明确痛点、男性受众或高决策成本产品。 [Reference Prompt / 原版案例提示词 - 必须像素级模仿其粗暴有力的分镜与台词]: 15-sec TikTok UGC, 9:16, iPhone 0:00–0:03 | Wide handheld shot, phone propped on a bench across the gym floor, young man mid-twenties named Adam, Black, clean low fade haircut, sharp jawline, sweat glistening across forehead and collarbones, wearing a fitted plain black ribbed tank top and black athletic shorts, mid-set on a flat bench pressing heavy dumbbells. Gym interior: dim low-lit space with black rubber flooring, rows of heavy dumbbells on a black rack, Technogym benches, mirrored wall reflecting warm pendant lighting, moody industrial vibe. He finishes his last rep with a loud grunt, slams both dumbbells down onto the rubber floor — loud THUD echoes — stands up fast, grabs the phone. Intense "listen up" energy. 0:03–0:06 | Selfie close-up, front camera, Adam breathing hard, veins visible in his neck, sweat dripping down his temple, staring dead into the lens. He points aggressively at the camera, jaw tight. "Yo — STOP paying a trainer two hundred bucks a session. I'm not playing with you right now." 0:06–0:11 | Camera flips to iPhone screen showing @image_1, static, no scrolling. His thumb aggressively taps the neon-green "Today's Pick" AI banner, then taps into the "Strength" program card showing 42 min, 6/8 exercises, then the bar chart highlighting Set 7, then the Heart Rate 138 BPM tile. "This app builds your ENTIRE program. AI literally reads your recovery, your heart rate, your hydration — and gives you EXACTLY what to do today. 42 minutes. Eight exercises. Done. No guessing. No excuses." 0:11–0:15 | Camera flips back, Adam now standing in front of the dumbbell rack, grabs two heavier dumbbells, curls them up once hard, flexes into the camera, chest heaving, face intense but with a fired-up smirk breaking through. He kisses his bicep, then jabs his finger at the lens. "Download it. Right now. No more excuses. See you in the gym." He tosses the phone toward the bench — cut to black. End. One take, dim industrial gym setup — moody overhead lighting, shadows on black rubber flooring, reflections in the mirror wall, live ambient sounds of weights clanking, heavy breathing, sneakers squeaking. No text overlays, no TikTok UI, raw handheld footage. Aggressive alpha gym-bro tone throughout — loud, intense, no-nonsense, borderline yelling but controlled.
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 · 178 lines · 90 tokens per session scan A bbedbe3e0d0e
TikTok网红带货视频 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 3,692 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 2026-09-27.
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.