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 yutianxiao6/openreel-studio --skill video-promptgit clone --depth 1 https://github.com/yutianxiao6/openreel-studioWrote 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/yutianxiao6/openreel-studio/video-prompt)<a href="https://agentmods.dev/skills/yutianxiao6/openreel-studio/video-prompt"><img src="https://agentmods.dev/badge/skills/yutianxiao6/openreel-studio/video-prompt/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/yutianxiao6/openreel-studio/video-prompt"><img src="https://agentmods.dev/badge/skills/yutianxiao6/openreel-studio/video-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.02977 |
| Opus 5 | $0.00044 | $0.01489 |
| Sonnet 5 | $0.00017 | $0.00595 |
| Haiku 4.5 | $0.00009 | $0.00298 |
Grade A, and why
video-prompt 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 12d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频提示词 Skill
用于最终 video 节点。它只处理 video prompt、时长、画幅、制作路径和引用关系。
读取素材
写视频 prompt 前读取或确认:
- 视频总时长、画幅、视频类型、整体视觉风格和目标节奏。
- 剧情段落、角色关系、动作目标、情绪变化、对白需求和结尾画面。
- 文生视频所需的主体设定、场景设定、光线、天气、空间关系和声音目标。
- 图生视频所需的分镜图、首帧图、尾帧图、人物图、场景图和其他参考图的用途。
- 分镜图的真实宫格布局、阅读顺序、每格主体、构图、动作瞬间、景别和视线方向。
- 当前视频模型支持的参考图数量、时长字段和画幅字段。
分镜图、首帧或尾帧有真实图片输出时,先用视觉能力查看图片。根据图中实际行列判断布局,读取顺序为从左到右、从上到下。视觉信息缺失时,用分镜 image 节点 prompt 和上游剧情作为有限依据。
通用写法
prompt 写成连续视频描述。先写视频类型、主体、场景、整体风格和参考图片用途;再按时间顺序写每个镜头或分镜格的动作、镜头变化、景别、构图、转场、节奏、物理反馈和声音。
视频模型更容易执行具体、可见、连续的画面描述。每个时间段按三层组织:
- 镜头层:景别、机位、镜头运动和速度。
- 主体层:一个核心动作、表情或姿态变化、动作速度和动作结果。
- 画面层:光线方向、环境运动、自然元素、道具反馈和空间连续性。
常用景别:大远景、远景、全景、中景、中近景、近景、特写、大特写。
常用镜头运动:静止、缓推、拉远、环绕、跟拍、横移、上摇、下摇、手持、俯冲。
常用光线:黄金时刻、蓝色时刻、柔和窗光、霓虹光、月光、烛光、逆光、侧光、顶光。
动作描述使用具体动词和速度副词,例如“缓缓转头”“轻轻抬手”“突然后撤”“渐渐握紧”“微微低头”“快速越过门槛”。每个时间段安排一个核心动作,并允许一个自然动作结果。
文生视频格式
纯文生视频、没有可用参考图或用户要求直接根据文字创意生成视频时,使用这个格式。写入 node.prompt 时替换花括号,不保留模板占位符。
生成一个{duration}、{aspect_ratio}、{shot_count}个镜头的{video_type}。
视频类型:
{电影短片 / 黑暗奇幻预告片 / 真实纪录片 / 一镜到底 / 短剧 / 广告片等具体类型。}
主体设定:
{主体是谁,外貌、年龄感、服装、道具、姿态、情绪、当前状态和关键识别点。纯文生视频需要写清楚可见特征,保证模型能稳定保持主体。}
场景设定:
{地点、时间、天气、空间结构、主体和环境的位置关系、主要光源、背景活动和可见动态元素。}
整体风格:
{色调、光影、节奏、质感、摄影风格、画面情绪、真实感或动画质感。}
镜头一 —— {镜头名},{开始}-{结束}秒,{景别},{机位/运镜}。
{主体在哪里,动作如何开始,主体做什么,环境如何运动,动作造成什么物理结果,镜头如何配合动作。}
转场:
{用动作方向、遮挡、光线、焦点、声音、视线或空间位置自然承接到下一个镜头。}
镜头二 —— {镜头名},{开始}-{结束}秒,{景别},{机位/运镜}。
{承接上一个镜头继续写动作发展、物理反馈、环境变化和镜头运动。}
声音设计:
{环境声、动作声、道具声、氛围声、音乐情绪、对白/旁白/字幕要求。}
稳定性要求:
全程保持同一主体、同一服装、同一道具、同一场景逻辑、同一光源方向和统一色调。动作缓慢连贯,镜头稳定,人体结构正常,面部清晰,布料、头发、烟雾、风雪、水面、火花、粒子和光效等运动自然真实。
15 秒短片通常使用 3-5 个镜头:建立镜头 2-4 秒,动作发展 4-8 秒,收束镜头 3-5 秒。一镜到底视频使用一个镜头段落,重点写主体运动路线、镜头运动路线、空间变化、环境动态和结尾停留画面。
分镜图生视频格式
根据已完成的分镜图、宫格分镜、首尾帧、参考图和剧情,为 video 节点写最终提示词时,使用这个格式。分镜图只作为镜头构图和动作节奏参考,最终画面是连续视频。
图片引用:
@{精确参考图标签}:{人物/场景/首帧/尾帧/分镜图/风格图}参考,{说明它锁定的主体、场景、构图或动作信息}。
@{另一精确参考图标签}:{用途}参考,{说明它锁定的信息}。
整体设置:
{duration}秒,{aspect_ratio},{video_type}。视觉风格为{style},画面保持{色调、光线、质感、节奏和摄影风格}。参考分镜图的真实宫格顺序组织镜头,成片是连续视频画面。
0-3秒 | 第1排第1格 | {画面概述} -> {动作变化} | {镜头运动}
{景别},{机位},镜头{缓推/拉远/环绕/跟拍/横移/上摇/下摇/手持/俯冲/静止}。{主体从什么状态开始,以什么速度做一个核心动作,表情、姿态、道具和服装如何变化。}{光线方向、环境细节、风、雾、水面、火花、布料或头发等自然元素如何运动。}
3-7秒 | 第1排第2格 | {画面概述} -> {动作变化} | {镜头运动}
{按分镜下一格继续写动作承接、运动方向、镜头变化、主体情绪和环境反馈。}
声音设计:
{环境声、动作声、道具声、材质声、氛围声、音乐情绪、对白或旁白。}
一致性要求:
全程保持同一主体、同一服装、同一道具、同一场景逻辑、同一光源方向和统一色调。动作缓慢连贯,镜头稳定,人物结构自然,面部清晰,布料、头发、烟雾、风雪、水面、火花和光效运动真实。
What ships with it
1 file 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.
- 12d ago First seen · 171 lines · 87 tokens per session scan A 6a4e6b665f0f
video-prompt is a skill published in the GitHub repository yutianxiao6/openreel-studio (29 stars, last pushed 26d ago), licensed MIT. It adds 87 tokens to every session and 2,977 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…