← Back to Skills Marketplace
妙达文字生成图片
by
nice1234-h
· GitHub ↗
· v1.0.0
· MIT-0
279
Downloads
1
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install miaoda-text-gen-image
Description
让 AI 生成的图片像真实摄影师拍的一样。不用学 prompt 技巧，一句话生成电影感大片。触发词：生成图片, 画图, 图片生成, text to image, 文字生成图片, AI 画图, 生成配图, 生成封面, 生成插图, generate image, 画一张, 做一张图
Usage Guidance
This skill is essentially a prompt-engineering guide that delegates execution to an external npm CLI (miaoda-studio-cli). Before installing or running that CLI, check the package on npm and its source repository (readme, maintainer, recent versions, issues), avoid installing unknown global packages in production systems, and run it in a sandbox if possible. Be aware that any prompts (especially ones containing personal data or private images) will likely be sent to remote servers by the CLI—do not submit sensitive information. If the CLI later asks for API keys, verify why they are needed and where they will be stored.
Capability Analysis
Type: OpenClaw Skill
Name: miaoda-text-gen-image
Version: 1.0.0
The skill bundle is a documentation-based guide for generating realistic AI images using the 'miaoda-studio-cli' tool. It provides prompt engineering formulas, keyword libraries, and command-line examples (SKILL.md) that align perfectly with its stated purpose. There is no evidence of malicious code, data exfiltration, or prompt injection attacks; the only external action is a standard recommendation to install a specific npm package for the tool's functionality.
Capability Assessment
Purpose & Capability
Name/description promise (generate realistic photographic prompts and example CLI usage) matches the SKILL.md content. No unrelated environment variables, binaries, or config paths are requested.
Instruction Scope
Instructions focus on prompt templates and give example commands that call an external CLI (miaoda-studio-cli). They do not instruct reading arbitrary files or harvesting environment variables, but they do expect the agent/user to run a third-party CLI that will likely send prompts to remote servers.
Install Mechanism
There is no built-in install spec, but SKILL.md recommends installing a global npm package (npm install -g miaoda-studio-cli). Installing global npm packages runs code from the npm registry and can execute arbitrary install scripts; the package name is unknown and should be reviewed before installation.
Credentials
The skill declares no required environment variables or credentials, which is consistent with an instruction-only prompt-helper. However, the external CLI it references may later request API keys or other credentials—those are not declared here.
Persistence & Privilege
Skill does not request persistent presence (always:false) and does not claim to modify other skills or system settings. It is user-invocable and can be run by an agent, which is normal.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install miaoda-text-gen-image - After installation, invoke the skill by name or use
/miaoda-text-gen-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
miaoda-text-gen-image 1.0.0
- 初始版本发布，主打“真实感AI图片生成”，无需掌握复杂 prompt 技巧。
- 提供真实感 prompt 公式与关键词库，帮助用户写出更像摄影作品的描述。
- 内置风格参考库（电影/纪录片、日系写真、欧美时尚、中国风）快速切换不同效果。
- 提供避坑指南，明确哪些描述容易出现“假感”并推荐替换方式。
- 详细命令参数说明及用途建议，支持自定义宽高比和输出格式。
- 包含丰富的应用场景、使用示例及常见问题答疑。
Metadata
Frequently Asked Questions
What is 妙达文字生成图片?
让 AI 生成的图片像真实摄影师拍的一样。不用学 prompt 技巧，一句话生成电影感大片。触发词：生成图片, 画图, 图片生成, text to image, 文字生成图片, AI 画图, 生成配图, 生成封面, 生成插图, generate image, 画一张, 做一张图. It is an AI Agent Skill for Claude Code / OpenClaw, with 279 downloads so far.
How do I install 妙达文字生成图片?
Run "/install miaoda-text-gen-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 妙达文字生成图片 free?
Yes, 妙达文字生成图片 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 妙达文字生成图片 support?
妙达文字生成图片 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 妙达文字生成图片?
It is built and maintained by nice1234-h (@nice1234-h); the current version is v1.0.0.
More Skills