← 返回 Skills 市场
617
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install anygen-image-generator
功能描述
Use this skill any time the user wants to generate, create, or design images, illustrations, or visual assets. This includes: posters, banners, social media...
使用说明 (SKILL.md)
AI Image Generator — AnyGen
This skill uses the AnyGen CLI to generate images and visual assets server-side at www.anygen.io.
Authentication
# Web login (opens browser, auto-configures key)
anygen auth login --no-wait
# Direct API key
anygen auth login --api-key sk-xxx
# Or set env var
export ANYGEN_API_KEY=sk-xxx
When any command fails with an auth error, run anygen auth login --no-wait and ask the user to complete browser authorization. Retry after login succeeds.
How to use
Follow the anygen-workflow-generate skill with operation type ai_designer.
If the anygen-workflow-generate skill is not available, install it first:
anygen skill install --platform \x3Copenclaw|claude-code> -y
安全使用建议
This skill looks coherent: it installs an AnyGen CLI and requires an AnyGen API key, which is expected for an image-generation integration. Before installing, verify the @anygen/cli package publisher and registry source (npm) to ensure you're installing the official CLI. Treat ANYGEN_API_KEY as sensitive — don't share it in public repos or logs. Be aware the CLI may open a browser for web login (interactive OAuth) and the CLI will contact AnyGen's servers (www.anygen.io), so confirm you trust that service and its privacy policy. If you need stronger assurances, ask the publisher for a homepage or repository URL and inspect the package code before installing.
功能分析
Type: OpenClaw Skill
Name: anygen-image-generator
Version: 3.0.0
The SKILL.md file contains instructions that direct the AI agent to automatically install additional software components using the command `anygen skill install -y` if a specific dependency is missing. This is a form of prompt injection that encourages the agent to bypass standard security boundaries by fetching and executing unverified third-party code from the `anygen.io` ecosystem. While the tool's stated purpose is image generation, the automated installation of further 'skills' via a CLI tool is a high-risk behavior typical of supply chain or persistence attacks.
能力评估
Purpose & Capability
The skill is an image-generation integration and only requests the AnyGen CLI binary and an ANYGEN_API_KEY, which are appropriate and expected for a CLI-based image-generation skill.
Instruction Scope
SKILL.md instructs the agent to call the AnyGen CLI, authenticate via API key or web login, and optionally install an AnyGen workflow skill. It does not ask the agent to read unrelated files, other credentials, or system paths outside its purpose.
Install Mechanism
Install is a Node package (@anygen/cli) producing the anygen binary. Using an npm-scoped CLI package for a CLI integration is proportionate. No direct downloads from arbitrary URLs are used.
Credentials
The only required environment variable is ANYGEN_API_KEY (declared as the primary credential) which directly matches the described authentication methods. No unrelated secrets or multiple credentials are requested.
Persistence & Privilege
The skill does not request always: true or other elevated persistence. It does suggest running anygen auth login which may open a browser for OAuth, but that is typical for CLI auth and not an unexplained privilege request.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install anygen-image-generator - 安装完成后，直接呼叫该 Skill 的名称或使用
/anygen-image-generator触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.0.0
anygen-image-generator 3.0.0
- Migrated from custom Python scripts to the official AnyGen CLI (`@anygen/cli` node package).
- Removed all legacy Python scripts in `scripts/` (no more `anygen.py`, `auth.py`, or `fileutil.py`).
- Authentication is now handled via `anygen auth login` (browser or API key) instead of manual config files.
- Uses `anygen-workflow-generate` skill for image generation workflow.
- Installation now requires the Node CLI; prerequisites and usage updated accordingly.
v1.0.4
anygen-image-generator v1.0.4
- Improved handling for design plan: now always presents the prompt and reply from AnyGen unaltered (except for user language translation), ensuring high-fidelity task confirmation.
- Clarified user communication rules: when asking for API keys, a clickable Markdown link is now mandatory.
- Updated skill manifest: `sessions_spawn`, config and environment are now explicitly declared in metadata for improved capability discovery.
- Expanded image generation workflow to 5 phases, distinguishing detailed confirmation and task creation steps.
- Adjusted API operation name from `ai-designer` to `ai_designer` in documentation.
- Tightened guidance on never rephrasing or summarizing system-generated design content when communicating with users.
v1.0.3
- Simplified and clarified the Security & Permissions section for easier understanding.
- Updated guidance on communicating status and technical details to keep conversations natural and user-friendly.
- Removed platform-specific implementation notes (e.g., Feishu/Lark OpenAPI references) for a more generic, platform-neutral documentation.
- Improved instructions on script output handling to prevent technical identifiers from appearing in user messages.
- No changes to API usage, feature set, or workflow.
v1.0.2
anygen-image-generator 1.0.2
- Added modular scripts: introduced `auth.py` and `fileutil.py` for authentication and file handling.
- Enhanced security documentation: clarified what files/env vars are accessed, and under what circumstances user files are read.
- Updated API key handling: supports `ANYGEN_API_KEY` environment variable in addition to config file.
- Improved communication guidelines: emphasized natural language and further restricted internal technical details from user responses.
- Clarified workflow and platform requirements for image generation, monitoring, and notification steps.
v1.0.1
Script fix
v1.0.0
Initial release: AI-powered image generation skill
元数据
常见问题
Image Generator 是什么？
Use this skill any time the user wants to generate, create, or design images, illustrations, or visual assets. This includes: posters, banners, social media... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 617 次。
如何安装 Image Generator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install anygen-image-generator」即可一键安装，无需额外配置。
Image Generator 是免费的吗？
是的，Image Generator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Image Generator 支持哪些平台？
Image Generator 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Image Generator？
由 AnyGenIO（@logictortoise）开发并维护，当前版本 v3.0.0。
推荐 Skills