← Back to Skills Marketplace
jkbwfi

zmg-srew

by jkbwfi · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
52
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install stoe
Description
Create shootable storyboard scripts for ZMGClaw internal demos. Use when the user asks to turn a news topic, campaign concept, documentary idea, short-video...
README (SKILL.md)

ZMG分镜脚本生成

Purpose

Transform an idea into a production-facing storyboard script. Optimize for clarity: directors, editors, reporters, camera operators, and AI video/image tools should understand what to create.

Inputs

Useful inputs:

  • Story premise, news topic, campaign theme, or desired message.
  • Duration and format: 15s, 30s, 60s, 3min, vertical, horizontal, TV package, short video, or explainer.
  • Audience and platform.
  • Style: documentary, warm human story, fast social edit, policy explainer, youth culture, cinematic, official, or investigative.
  • Required facts, people, locations, slogans, products, or compliance constraints.

If duration is missing, assume 60-90 seconds for social video and state the assumption.

Workflow

  1. Restate the core story in one sentence.
  2. Choose a narrative structure:
    • Hook -> context -> character/problem -> turning point -> resolution -> call to action.
    • Problem -> evidence -> explanation -> solution -> takeaway.
    • Before -> change -> after.
  3. Divide the runtime into scenes or beats.
  4. For each beat, specify image, shot type, motion, narration/dialogue, sound, text overlay, and material needs.
  5. Add interview questions when human subjects are involved.
  6. Add AI-generation prompts only when the user wants assets for image/video tools.
  7. Check continuity: time, place, causality, character motivation, and tone.

Output Format

Use this structure by default:

## 创作定位
- 片名/暂定标题:
- 核心表达:
- 时长与比例:
- 风格:

## 分镜脚本
| 时间 | 镜号 | 画面/场景 | 景别/运动 | 旁白/对白 | 声音 | 字幕/包装 | 备注 |
|---|---:|---|---|---|---|---|---|

## 采访设计
- 采访对象:
- 关键问题:

## 素材清单
- 实拍:
- 资料:
- AI生成:
- 包装:

## 连贯性检查
- 逻辑:
- 人物:
- 节奏:
- 风险:

Quality Rules

  • Make every shot filmable or generatable.
  • Avoid vague instructions like "beautiful picture"; name the visible subject, action, environment, composition, and mood.
  • Keep narration speakable. Prefer short sentences.
  • Do not invent factual claims for news or public-policy content.
  • Flag missing source material when the script depends on unprovided facts, quotes, archive footage, or approvals.
Usage Guidance
This skill appears safe to install as a writing aid. For news, policy, or documentary uses, provide verified source material and review the generated script for factual accuracy before production.
Capability Analysis
Type: OpenClaw Skill Name: stoe Version: 1.0.0 The skill bundle is a purely instructional set of markdown files (SKILL.md and skill.md) designed to guide an AI agent in generating storyboard scripts for video production. It contains no executable code, external dependencies, or instructions that would lead to data exfiltration or unauthorized system access.
Capability Assessment
Purpose & Capability
The stated purpose and instructions are coherent: the skill helps turn user-provided ideas into scene-by-scene storyboard scripts with production notes.
Instruction Scope
The workflow is limited to drafting and formatting creative/storyboard output, and it includes appropriate guidance not to invent factual claims for news or public-policy content.
Install Mechanism
There is no install specification, no required binaries, no code files, and the static scan reported no suspicious patterns.
Credentials
The skill requests no environment variables, credentials, configuration paths, network access, or local file access.
Persistence & Privilege
The artifacts show no persistence, background activity, account access, privilege use, or long-running behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install stoe
  3. After installation, invoke the skill by name or use /stoe
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of zmg-storyboard-generator: - Generates detailed, shootable storyboard scripts for ZMGClaw internal demos. - Supports various video concepts: news, campaigns, documentaries, short videos, and brand stories. - Structures scripts with scene-by-scene breakdowns, including visuals, narration, sound, subtitles, and production notes. - Includes interview question drafting and material/asset lists. - Designed for clarity and usability for directors, editors, camera crew, and AI media generation tools.
Metadata
Slug stoe
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is zmg-srew?

Create shootable storyboard scripts for ZMGClaw internal demos. Use when the user asks to turn a news topic, campaign concept, documentary idea, short-video... It is an AI Agent Skill for Claude Code / OpenClaw, with 52 downloads so far.

How do I install zmg-srew?

Run "/install stoe" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is zmg-srew free?

Yes, zmg-srew is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does zmg-srew support?

zmg-srew is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created zmg-srew?

It is built and maintained by jkbwfi (@jkbwfi); the current version is v1.0.0.

💬 Comments