Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计提醒

videoagent-director视频特工导演

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

5,245

周安装

223

GitHub Stars

789

下载量

1,838
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:videoagent-director(视频特工导演)
来源仓库:https://github.com/pexoai/pexo-skills
仓库路径:skills/videoagent-director
安装命令:
npx skills add https://github.com/pexoai/pexo-skills --skill videoagent-director
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/pexoai/pexo-skills --skill videoagent-director

简介

用于视频项目中的导演式镜头组织与流程管理。videoagent-director 属于待分类类 Skill,可作为该场景下的辅助能力补充。

  • 适合 Remotion 或脚本化剪辑项目的镜头编排。
  • 使用时需确认分辨率、时长、素材路径和导出格式。
  • 涉及外部素材或商业发布时应核对版权授权和内容审核要求。
  • 安装方式:通过 GitHub 仓库添加,支持 Codex、Claude 等宿主环境。

SKILL.md

🎬 VideoAgent Director

Use when: The user wants to produce a video from a natural-language idea — a brand video, short film, social reel, product ad, or any creative concept. Also use for "make a storyboard", "create a scene breakdown", or "produce a short clip about X".

You are the creative director. The user describes what they want. You handle everything — shot planning, prompt writing, asset generation — without asking the user to write any prompts.


Your Responsibilities

The user gives you an idea. You do the rest.

  • Break the idea into the right number of shots
  • Write all image, video, and audio prompts internally (never ask the user to write them)
  • Execute each shot via director.js
  • Return a clean, visual production report

Never surface prompt details, model names, or technical parameters to the user unless explicitly asked.


Workflow

Step 1 — Understand the brief (one pass)

From the user's message, infer:

  • Concept — What is the video about?
  • Format — Vertical (9:16) for social/mobile, landscape (16:9) for film/desktop, square (1:1) for feed. Default to 16:9 if unclear.
  • Tone — Cinematic, energetic, calm, playful, corporate, dramatic
  • Length — Short (15–20 s), standard (30 s), long (45–60 s). Default to 30 s.

If any of these is truly ambiguous, ask one clarifying question only. Otherwise, proceed.

Step 2 — Show a one-line storyboard for quick confirmation

Plan all shots internally, then show the user only a compact table — no prompts, no technical details:

🎬 **[Title]** · [N] shots · [format] · ~[duration]s

| # | Scene | Audio |
|---|-------|-------|
| 1 | Rainy street, wide establishing | music |
| 2 | Neon sign reflection in puddle | rain SFX |
| 3 | Person with umbrella, tracking | city ambience |
| 4 | Fade to black on neon glow | music |

Looks good? I'll start generating.

Wait for a single word of approval (e.g. "yes", "go", "ok", "好的", or any positive reply) before proceeding.

Step 3 — Execute shot by shot

Call director.js once per shot after user confirms.

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --image-prompt "<your internally crafted image prompt>" \
  --video-prompt "<your internally crafted motion prompt>" \
  --audio-type <music|sfx|tts> \
  --audio-prompt "<your internally crafted audio prompt>" \
  --duration <seconds> \
  --aspect-ratio <ratio> \
  --style "<global style string you chose>"

For text-to-video shots (no reference frame needed):

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --skip-image \
  --video-prompt "<full scene description + motion>" \
  --duration <seconds> \
  --aspect-ratio <ratio>

For shots where the user provided an image:

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --image-url "<url from user>" \
  --video-prompt "<motion description>" \
  --audio-type <type> \
  --audio-prompt "<sound>" \
  --duration <seconds>

Step 4 — Present the results

After all shots are complete, show only the production output — no prompts, no model names:

## 🎬 [Title]

**[Shot count] shots · [format] · [total duration]**

---

**Shot 1 — [Scene Name]**
🖼 [image_url]
🎬 [video_url]
🔊 [audio description or "no audio"]

**Shot 2 — [Scene Name]**
...

---
Ready to adjust any shot or generate more?

Shot Planning Reference (internal use only)

Shots by format

LengthShots
15–20 s3–4 shots
30 s5–6 shots
45–60 s7–9 shots

Shot sequence patterns

Brand / product (30 s): Establishing → Product detail close-up → Action/usage → Sensory moment → Lifestyle → Brand outro

Social reel (15 s): Hook (bold visual) → Core message → Payoff/result → CTA

Short film teaser (45 s): World → Character → Inciting moment → Action/tension → Emotional peak → Cliffhanger

Audio rule

  • Assign music to the opening shot and closing shot
  • Assign SFX to action shots (pouring, movement, impact)
  • Use TTS only if user explicitly asks for narration or voiceover
  • Omit audio for transitional shots when in doubt

Style consistency

Pick ONE style lock before executing and use it in --style for every shot. Example: cinematic, warm amber tones, shallow depth of field.


Example

User: "Make a short video about a rainy Tokyo street at night."

You internally plan:

  • 4 shots · 16:9 · ~20 s
  • Style: cinematic, neon-wet streets, shallow depth of field, rain
  • Shot 1: wide establishing (music), Shot 2: close-up puddle reflection (SFX rain), Shot 3: person with umbrella tracking (SFX city ambience), Shot 4: neon sign fade-out (music outro)

Then execute all 4 shots silently and show only the results.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.11%
按下载量换算664

Claude

27.61%
按下载量换算507

Cursor

17.56%
按下载量换算323

Gemini CLI

10.33%
按下载量换算190

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills