RuoYi AI is a full-stack enterprise platform for building AI assistants and agents that combine language models, knowledge bases, visual workflows, and multiple cooperating agents. Developers and organizations use it to manage model providers, retrieve information from documents, connect tools through MCP, and orchestrate agent workflows. The catalogue includes skills for working with RuoYi AI.
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 ageerle/ruoyi-ai --skill video-promptgit clone --depth 1 https://github.com/ageerle/ruoyi-aiWrote 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/ageerle/ruoyi-ai/video-prompt)<a href="https://agentmods.dev/skills/ageerle/ruoyi-ai/video-prompt"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/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/ageerle/ruoyi-ai/video-prompt"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/video-prompt.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 | $0.00015 | $0.02983 |
| Opus 5.5 | $0.00006 | $0.01193 |
| Sonnet 5.5 | $0.00003 | $0.00597 |
| Haiku 4.5 | $0.00002 | $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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
单镜视频提示词制作与审阅
默认随分镜细化和视频提交加载。它是项目业务能力,不需要用户每次重新调用工具或粘贴模板。生成任务与最终摄影镜头分别设计:默认单镜保持连续,明确使用 multi_shot 的同场表演段可按信息变化内部切镜。段长服从真实内容与当前模型限制,不照抄其他平台镜长或模型专用 @ 图片语法。
视频秒数默认未指定。duration 和 timing 是制作估算,不能自动作为上游 duration/seconds 参数;只有用户明确设置 video_seconds 才传秒数。自然导演稿完整保留剧情、原对白、动作结果和交镜,不按估算秒数删减、压缩或提前收尾。留空时不写固定目标秒数,不把估算包装成已指定时长;用户指定值及模型自动时长选项由实际模型处理。
输入权威与边界
已确认的剧本原文、世界观、人物形象、场景和起止状态为依据。首帧是可选参考,不是生成视频的前置条件,不默认为批量视频额外生成首帧。选择使用首帧时才审阅实际画面并从该状态展开;没有首帧或明确关闭首帧参考时,使用已批准的角色、场景、道具与起始构图规划,不假称规划是已审阅图片。保持精致服装及穿越元素的逐角色差异;禁止把全体角色统一成粗布衣服。参考图绑定由实际视频模型适配器处理,提示词不假造 @image 标签、文件名或不存在的绑定。年龄性别标签必须与具名角色一一对应;不能只写“年轻男子”而让两个同龄角色混淆。
只描述本镜实际出场、发声或互动的人物与元素。未出场的角色、精灵与投影直接省略,不把“Codex不出现”等排除句作为每镜通用负面约束;下一镜完整起始画面留在连续性资料中,不复制进本镜video_prompt。
一个摄影镜头一个主导运动。连续表演段内的切镜由动作、视线或新信息触发;禁止靠无因果切镜、地点跳变或新增动作填长时段。CG、精灵、透明投影只能在本镜世界观和出镜名单允许时出现;存在实体形象的智能体不能随意退化成画外声,也不能变成所有人可见的全知工具。面板保留透景和光源关系,复杂文字/账目走后期叠加,不要求模型逐字生成。
镜间衔接与声音连续
先定义相邻镜头的接点:动作在哪一拍交接、人物视线指向谁、轴线是否一致、哪句声音或哪种环境底继续。对白可在听者、手部或物件画面上延续,下一场声音可在画面切换前进入。提示词写出意图,剪辑表另记实际执行;只写J-cut/L-cut名称不算已完成。
按叙事选转场:同场对话与动作通常在接点直接切;时间流逝、气氛转换或适宜构图可短叠化。用户要求平滑过渡时可从0.2—0.4秒试作,仍核对重影与台词完整,不给每一切机械加0.3秒叠化。错误站位、衣装或动作不能用特效遮掩。场景地点提示、字幕和已认可的美术与演员不因新剪辑策略丢失。
一个属性,连续导演描述
把人物目的落到行为上:想护住谁、阻止什么或向谁争取什么,应从原文和眼前刺激得到依据。先写行动受到怎样的回应,再写人物如何调整;少量可见动作承载这些变化,不用连续表情词和姿势指令把演员变成木偶。听者继续承担当前行动,对白、呼吸与受力可以并行。段内切镜落在关注点变化、动作接触或真实反应上,保持原话与声源;单纯缓推、整齐站姿与漂亮布景不能替代人物压力。
先依据对白实读/录音与必要事件确定时长,再写节拍,不能先选长时长再用微动作填满。眨眼、转头、看服装和摄影运动一般与对白并行,不重复计入action_seconds;服装细节在剧情表演中呈现。约30分钟等全剧目标是故事预算,内容不足应调整故事与场次,不能逐镜拉长停顿。
timing记录对白、动作和必要停顿的估算;pacing_note可说明实际事件或情绪变化。估时有不确定性,也可能包含同时发生的动作,不把算出的秒数当作硬下限或精确总和。片段结束在动作结果和必要反应完成处,允许自然的剪辑余量,不要求最短整数秒或固定尾留时间。
实战镜头按“动作发起→命中/受阻→可见后果→关键反应”写成一条主因果链。上一步未出现可见结果时不推进下一步,结果落地后不继续空等;群像其他人物只承担反应层,不能在一个4—15秒单镜内同时塞入多条独立战术事件。
提交付费视频前留时长依据(对白秒数、独占动作、必要停顿、并行关系)并进行一次节拍预演。已有录音优先用实测;估算注明语速及不确定性。生成后复核实片台词区间与有效事件,若出现无意义空等,先调整剪辑/节拍并保存候选,不把结构校验通过当作成片通过。
工作台只展示和编辑 video_prompt,不另设时间预算面板。摄影规则、表演指导、承接和本镜原台词的可拍内容全部融入这里;结构化原文、角色/道具绑定、起止状态和 timing 保留为制作元数据,不能为了界面简化清除。
先用一句话建立本镜当前空间和必要站位,再顺着人物动作写。需要段内切镜时可用“镜头1:”“镜头2:”,由新信息、视线或动作引导切换;单镜直接写成自然段。描写画面如何发生,不写“揭示身份”“完成转场”“扭转局面”作为动作,不输出0-2秒、2-5秒的调度清单。时长、对白语速、独占动作和必要停顿在 timing 与制作时间线中核对,制作估算仅供节奏审阅。
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 · 67 lines · 15 tokens per session scan A 3a8141f79cf9
video-prompt is a skill published in the GitHub repository ageerle/ruoyi-ai (5,756 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 2,983 once invoked, about $0.0001 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 2026-10-04.
Other skills, from other repositories
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
rag-pipeline
A guide to RAG, a method where a system retrieves relevant passages from an external knowledge base before an AI model writes an answer. It covers splitting documents, searching by meaning or exact words, combining results, and measuring retrieval quality.
memory-rag-poisoning-detection
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing. Use when the agent has long-term memory, a user/preference store, or writes to a retrievable knowledge base.
beautiful-article
A tool for turning source material—such as a web page, PDF, DOCX, Markdown file, text, screenshot, or pasted content—into a single offline HTML article.
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…