agentleFS
Ucmp0001Ucmp0001/video-production-skills/skills/generated-broll/SKILL.md

generated-broll

Skill27 starsChanged 38 days agoMITView on GitHub

Plan optional generated conceptual B-roll with prompts, native resolution verification, budget authorization and recoverable provider tasks.

The file

Files
SKILL.md

English instructions · 简体中文

For English-language tasks, read SKILL.en.md and its English reference templates before proceeding. Both editions use the same tools and authorization boundaries.

AI 概念补充镜头

用于无法用真实素材或简洁解释图表达的概念画面。用户不用 AI 视频或仅改字幕/Logo 时跳过。生成内容不能提供新闻证据,也不能伪造已发生的行动、交易或现场。

准备具体计划

按 生成计划与恢复 记录镜头目的、概念性质、视觉事件、参考素材权利、实际 provider/model、每组时长、比例、原生分辨率、数量、单价证据、总预算和备选方案。 短片/常规片可先以最多三组作预算建议,按叙事更少即可;这是可调整建议,不覆盖用户选择。开场使用时首帧有主体、前三秒有具体变化,与首句和正文一致,计入原计划,不另加组数。

提示词写清主体、动作、镜头、材质/光影、首尾状态与应避免的事实误导。文字、准确数字、Logo、图表和 UI 优先后期叠加。不要把个人账号、私有路径、token 或未授权素材送入提示词。

提交边界

先核对已安装官方客户端帮助或官方 API 文档,不能编造参数。实际请求有 dry-run 时核对 provider/model/resolution 等字段,预演不提交付费任务。 已有授权仅覆盖同一具体计划与预算。新增付费计划或变更提示词/参考/数量/费用等实质项,说明变化并取得对应确认;不把“做视频”自动当作无限付费重试许可。未知费用不得签预算内。 请求超时或结果不明,先用任务 ID/请求指纹恢复、查询、等待或下载同一任务;避免重复计费。每次重试累计成本,按用户上限停止;查询的网络失败不直接视为生成失败。

原片验收

保存净化后的回执、任务状态、原片哈希、实测尺寸/比例/时长、实际模型与成本。请求原生 2K/4K 等时,按当前官方尺寸表及实际回执核对;无尺寸表就注明待核,提示词里的“2K”或本地放大均不能证明原生规格。 实际看整个拟用区间的动作、变形、主体连续和首尾接缝;有音轨或同步要求时实际听辨。模型名称、成功回执和尺寸通过不代表观感通过。 不合适时优先重排已有素材或自制图,不无限重提。AI 来源留内部记录,公开声明按当地有效规则与目标平台处理。

交付生成计划、提示词、预算/授权绑定、净化任务记录、原片、采用区间和验收范围。鉴权信息仅由本机现有认证系统提供。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.