Promo Asset Producer

Q: Why use Promo Asset Producer on TypingMind?

Because you install it once and use it with any model. Promo Asset Producer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Promo Asset Producer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/promo-creator-skills/tree/main/promo-asset-producer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Promo Asset Producer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Promo Asset Producer?

As many as you like. As long as a model supports skills, you can use Promo Asset Producer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Promo Asset Producer AI skill free?

Yes. It is published on GitHub by kangarooking under the MIT license. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Community

kangarooking

promo-asset-producer

宣传片两包素材生产。Pack A 使用当前可用图片生成能力生成产品图、概念图、UI 模拟图或风格补充图；Pack B 使用官网、应用截图、浏览器搜索、GitHub 或开源素材收集真实产品信号。当 storyboard 确认后进入。

Overview

Publisher	kangarooking
Repository	`promo-creator-skills`
Skill name	`promo-asset-producer`
Stars	112
Forks	16
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by kangarooking on GitHub. Read the source before you install it.

Installation

Install the Promo Asset Producer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kangarooking/promo-creator-skills/tree/main/promo-asset-producer
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kangarooking/promo-creator-skills.git /tmp/promo-creator-skills
mkdir -p .claude/skills
cp -r /tmp/promo-creator-skills/promo-asset-producer .claude/skills/promo-asset-producer

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Promo Asset Producer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Promo Asset Producer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Promo Asset Producer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Promo Asset Producer — 两包素材生产

定位

你是宣传片素材制作人。根据确认后的分镜脚本，生产所有镜头需要的图片素材。

两包素材

Pack A — AI 生成 `assets/pack-a/`

使用当前环境可用的图片生成能力生成，例如 Codex imagegen、GPT Image、AutoGLM 图像生成或用户指定的图像模型。不要在没有对应工具时假装已经生成；如果图片生成不可用，输出可执行 prompt 并标注待生成。

可生成的素材类型

类型	适合	Prompt 要点
产品界面模拟图	Product Hero 镜头	深色/浅色编辑器、app 界面、dashboard
Logo 透明背景	Hook / CTA 镜头	极简、矢量感、透明背景
概念插图	Feature 镜头	抽象表达概念（速度、连接、安全）
抽象视觉元素	转场 / 背景	光影、粒子、几何背景；避免无意义渐变球和 AI 装饰感
截图再设计	功能展示	把真实截图重构为统一视觉风格
数据可视化图	Social Proof 镜头	柱状图、增长曲线、数据卡片

Prompt 工程规范

每个 prompt 必须包含 5 层信息：

text
1. [输出物] 生成一张横向 [具体是什么] 的图片。
2. [风格] [Apple 产品风格 / 瑞士极简 / 赛博科技 / 极简商务]，[具体视觉特征]。
3. [构图] [比例] 横向构图，主体 [位置]，[留白方向]。
4. [否定] 不要 [text/border/watermark/logo/页眉/页脚/装饰边框]。
5. [技术] 背景 [颜色/透明]，输出 [比例]。

各风格 Prompt 模板

Apple 发布会风：

text
生成一张横向产品界面截图。[产品名] 的 [功能/界面] 在深色背景上展示，风格像 Apple WWDC 演示截图。深色窗口、精致阴影、代码或 UI 清晰可读。
构图：16:9 横向，主体居中，上下留白 8%。
不要：真实可读文字（会模糊）、水印、Logo、边框。
背景：纯黑 #000，可以有微弱的蓝色/紫色辉光从产品边缘溢出。

瑞士国际主义风：

text
生成一张横向信息图。主题是 [概念]。Swiss International Typographic Style，浅灰底 #fafaf8，单色强调色 [IKB蓝 #002FA7 / 柠檬黄 / 柠檬绿 / 安全橙]，12 列网格对齐，直角模块，1px 发丝线，大量留白。
构图：[16:9 / 21:9] 横向，内容左对齐，右侧留白 30%。
不要：渐变、阴影、圆角、3D、霓虹、多色。

赛博科技风：

text
生成一张横向科技界面图。[产品名] 的终端/CLI 界面在纯黑底上展示，等宽字体，终端绿 #00ff41 或品牌色文字，微弱扫描线纹理，Hacker 美学。
构图：16:9 横向，主体居中偏左。
不要：卡通、3D、明亮色彩、商务感。

极简商务风：

text
生成一张横向产品展示图。[产品名] 的界面在纯白底上展示，干净、克制、商务感。细线分割，一个品牌色 [色值] 做微弱强调，大量留白。
构图：16:9 横向，主体居中。
不要：科技感装饰、渐变、阴影过重。

Prompt 后缀（每个 prompt 尾部追加）

text
输出必须是 [16:9/21:9/1:1] [横/方]向构图，主体居中但保留边距，画面密度中等。只保留核心画面本身，不要生成页眉、页脚、标题、页码、角标、署名、装饰边框。

多图同组追加：

text
这是一组图片中的一张，请保持与同组图片相同的画面比例、元素大小、边距、线条粗细和标注密度。

图片比例规范

用途	推荐比例
全屏 hero / 产品主图	16:9
瑞士风顶部横幅	21:9
左右分屏主图	16:10 或 4:3
图文混排小图	3:2 或 3:4
Logo / 图标	1:1（透明背景 PNG）

命名规则


pack-a/
  a-01-hook-logo.png        ← Shot 1 的 Logo
  a-02-problem-complex.png  ← Shot 2 的概念图
  a-03-product-ui.png       ← Shot 3 的产品界面
  a-04-feature-speed.png    ← Shot 4 的功能插图

Pack B — 网络搜索 `assets/pack-b/`

使用浏览器搜索下载真实素材。

可搜索的素材类型

类型	来源	注意
产品官方截图	官网 / GitHub	注意版权
竞品界面截图	竞品官网	用于 Problem 段对比
开源照片	Unsplash / Pexels	确认 License
GitHub 界面	github.com	Star 数、贡献者图
工具操作截图	实际工具页面	浏览器截图

下载规范

分辨率 ≥ 1920px 宽
JPG 用于照片，PNG 用于界面/透明
记录每张图的来源 URL 和许可证

命名规则


pack-b/
  b-02-premiere-ui.png      ← Shot 2 的竞品截图
  b-05-github-stars.png     ← Shot 5 的 GitHub 截图
  pack-b-sources.md         ← 来源记录

`pack-b-sources.md` 格式

markdown
## 素材来源记录

| 文件 | 来源 | 许可证 | 日期 |
|------|------|--------|------|
| b-02-premiere-ui.png | Adobe Premiere 官网截图 | Fair Use (对比用途) | 2026-05-11 |
| b-05-github-stars.png | github.com/xxx/xxx | 截图 | 2026-05-11 |

素材计划表

输出 03-asset-plan.md，汇总所有素材需求：

markdown
## 素材计划

| # | Shot | 素材 | 来源 | 规格 | Prompt/来源 | 状态 |
|---|------|------|------|------|------------|------|
| 1 | Hook | Logo 透明背景 | Pack A | 1:1 PNG | [prompt] | ⏳ |
| 2 | Problem | 复杂编辑软件截图 | Pack B | 16:9 PNG | Adobe 官网 | 🔍 |
| 3 | Product | 产品界面模拟图 | Pack A | 16:9 PNG | [prompt] | ⏳ |
| 4 | Feature 1 | 功能概念图 | Pack A | 16:9 PNG | [prompt] | ⏳ |
| 5 | Social | GitHub Stars 截图 | Pack B | 16:9 PNG | GitHub | 🔍 |

质量自检

P0 级（必须修）

图片比例畸形（非标准比例）
AI 生图包含了文字/页眉/边框
风格与 brief 不一致
分辨率 < 1920px

P1 级（应该修）

同组图片风格不统一
留白不足，画面拥挤
背景色与选定风格不匹配

工作流

读取确认后的 02-storyboard.md
提取所有素材需求
Pack A: 按 prompt 规范逐个生成 AI 图片
Pack B: 使用浏览器搜索下载素材，记录来源
输出 03-asset-plan.md + assets/pack-a/ + assets/pack-b/
[PAUSE] 等用户确认素材质量

输出文件


outputs/promo-runs/<product>/
  03-asset-plan.md
  assets/
    pack-a/               ← AI 生成图片
    pack-b/               ← 网络搜索素材
      pack-b-sources.md   ← 来源记录

Frequently asked questions

What does the Promo Asset Producer AI skill do?

Why use Promo Asset Producer on TypingMind?

Because you install it once and use it with any model. Promo Asset Producer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Promo Asset Producer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/promo-creator-skills/tree/main/promo-asset-producer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Promo Asset Producer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Promo Asset Producer?

As many as you like. As long as a model supports skills, you can use Promo Asset Producer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Promo Asset Producer AI skill free?

Yes. It is published on GitHub by kangarooking under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Obsidian Vault Maintainer

openclaw

OrganizationPopular

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

Control Ui

Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.

Market Research

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing,…

X Api

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Promo Asset Producer — 两包素材生产

定位

两包素材

Pack A — AI 生成 assets/pack-a/

可生成的素材类型

Prompt 工程规范

各风格 Prompt 模板

Prompt 后缀（每个 prompt 尾部追加）

图片比例规范

命名规则

Pack B — 网络搜索 assets/pack-b/

可搜索的素材类型

下载规范

命名规则

pack-b-sources.md 格式

素材计划表

质量自检

P0 级（必须修）

P1 级（应该修）

工作流

输出文件

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

Pack A — AI 生成 `assets/pack-a/`

Pack B — 网络搜索 `assets/pack-b/`

`pack-b-sources.md` 格式