Token导航 LogoToken导航

Agent Skill · 图像处理

goai-image-gen(果艾图像生成器)

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

goai-image-gen 是图像处理类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在图像处理类的 1,562 个 Skill 里排第 688。

总安装 3,293周安装 140GitHub Stars 公开资料未说明下载 1,154核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

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:goai-image-gen(果艾图像生成器)
来源仓库:https://github.com/goai/goai-image-gen
安装命令:
openclaw skills install goai-image-gen
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install goai-image-gen

这个 Skill 是做什么的

图像处理类 Skill 处理生成、裁剪、压缩和批量转换图片的任务。

通过 GoAI API 生成 AI 图像。当用户要求创建、生成、绘制、编辑、渲染或制作图像、图片、插图、海报、头像、图片时使用

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install goai-image-gen;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

goai-image-gen 怎么安装?

在终端执行 openclaw skills install goai-image-gen。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

goai-image-gen 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

goai-image-gen 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

goai-image-gen 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

goai-image-gen 用的人多吗?

公开数据是累计安装 3,293 次,近一周安装 140 次,下载 1,154 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

goai-image-gen 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理图像处理类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

图像处理类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
ai-image-generation

AI 图像生成 · Codex、Claude

4,365,552382调用外部服务未明确有提醒
openai-image-gen

OpenAI 图像生成 · OpenClaw

1,906,88432需要联网MIT-0有提醒
image

图像 · OpenClaw

525,99926需要联网MIT-0通过
baoyu-cover-image

宝玉封面图 · Codex、Claude

474,24016,779只读MIT有提醒
baoyu-image-gen

宝玉图像生成器 · Codex、Claude

468,00716,778接触敏感数据MIT通过
goai-image-gen

果艾图像生成器 · 本页

3,293—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
goai-image-gen
description
Generate AI images via GoAI API. Use when the user asks to create, generate, draw, edit, render, or make images, pictures, illustrations, posters, avatars, photos, or concept art, including Chinese requests like 生成图片, 生成一张图, 画图, 画一张图, 出图, 做图, 修图, 改图.
version
0.3.0
homepage
https://mustgoai.com
metadata
{ "openclaw": { "emoji": "🎨", "os": ["darwin", "linux", "win32"], "requires": { "bins": ["uv"], "env": ["GOAI_API_KEY"] }, "primaryEnv": "GOAI_API_KEY" } }

When To Use

Use this skill when the user wants image generation, image editing, or reference-image-based image creation through GoAI, especially for prompts like 生成图片, 画图, 出图, 做图, 修图, and 改图.

Pass the user's image prompt through as-is unless the user explicitly asks for prompt optimization, prompt polishing, rewriting, translation, or additional creative detail. Do not silently embellish short prompts such as 画一个老虎.

Do not translate the user's prompt to another language. If the user writes in Chinese, pass Chinese to --prompt. If the user writes in English, pass English to --prompt. You may strip only lightweight request wrappers such as 帮我, 给我, 请, 生成, or 画一张, but do not rewrite the core prompt content.

Examples:

  • User: 给我生成一只狮子 -> --prompt "一只狮子" or --prompt "给我生成一只狮子"
  • User: 画一个老虎 -> --prompt "画一个老虎" or --prompt "一个老虎"
  • Never turn 给我生成一只狮子 into a lion unless the user explicitly asks for English translation.

Default Behavior

This package currently targets the production environment at https://mustgoai.com. Override GOAI_BASE_URL only when you intentionally need a different endpoint.

This skill now uses a single cross-platform Python entrypoint through uv. If the user does not specify a model, the script queries /api/v1/models/capabilities, sorts enabled image models by display.priority, and picks the highest-priority model.

Treat uv as the only runtime dependency the user needs to install manually. On first run, uv may create a local environment, install httpx, and download Python if the machine does not already have a usable interpreter. That first-run setup is expected and should not be described as an error.

If the user provides local image paths, the script uploads them first and sends the resulting URLs as reference_images. If the user provides remote URLs, the script passes them through unchanged.

Script Rules

Always use the Python entrypoint through uv:

uv run --project . python scripts/generate_image.py \
  --prompt "..." \
  [--model "..."] \
  [--aspect-ratio "..."] \
  [--resolution "..."] \
  [--reference "/path/to/image.png"] \
  [--reference "https://example.com/image.png"]

The Python path validates GOAI_API_KEY, defaults to https://mustgoai.com unless GOAI_BASE_URL is set, and treats 401, 402, 429, content blocking, missing task_id, missing image_url, and backend terminal failure states as hard failures. Polling follows the web client behavior: it checks every 3 seconds, retries transient polling errors, and waits for a backend terminal status instead of enforcing a client-side timeout.

The Python entrypoint self-heals into uv run if it is accidentally invoked as python scripts/generate_image.py ... or python3 scripts/generate_image.py .... Do not try to repair the system Python environment for this skill.

When invoking this skill through OpenClaw's exec tool, always use timeout=600 to allow up to 10 minutes for long-running image generation. Do not describe the run as timed out or killed unless the script itself exits non-zero or the backend reports a terminal failure state.

If uv is missing, explicitly guide the user to install it first:

  • macOS: brew install uv
  • Windows: winget install astral-sh.uv

After uv is installed, rerun the same command. Do not ask the user to install Python packages by hand; uv is responsible for preparing Python and the skill dependencies.

If execution reports a missing Python module such as httpx, do not run pip install, pip install --user, or pip install --break-system-packages. Re-run the skill through uv; the dependency set comes only from pyproject.toml and uv.lock.

If GOAI_API_KEY is missing, explicitly guide the user to visit https://mustgoai.com, register or log in, open Settings -> API Key, create a key, and then configure the skill env in ~/.openclaw/openclaw.json.

Output Contract

On success, print all four lines below in this order:

  • MEDIA:/absolute/path/to/generated-file
  • MEDIA_URL:https://...
  • RESULT_PATH:/absolute/path/to/generated-file
  • RESULT_URL:https://...

When responding to the user after a successful run, always include both the exact local file path and the exact public URL in plain text, even if OpenClaw already rendered or read the local media file. Do not omit the URL just because the image preview succeeded. On failure, exit non-zero and print a concise error message. Do not inline the binary output back into the conversation.

平台分布

OpenClaw

80.56%
按下载量换算930

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills