← 返回 Skills 市场
unixlamadev-spec

Image Gen Bot

作者 unixlamadev-spec · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
578
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install image-gen-bot
功能描述
Generate images from text prompts using FLUX via Together.ai. Returns image URL. Prompts are auto-enhanced for best results.
使用说明 (SKILL.md)

\r \r

Image Gen Bot\r

\r Generate images from natural language descriptions using FLUX.1-schnell via Together.ai. Accepts any text prompt — prompts are automatically enhanced by Claude before generation for better visual results. Returns a URL to the generated image.\r \r

When to Use\r

\r

  • Generating logos, icons, or brand visuals for projects\r
  • Creating illustrations or artwork for content\r
  • Visualizing concepts, products, or designs\r
  • Generating images for reports or presentations\r
  • Any task requiring original visual output from a text description\r \r

Usage Flow\r

\r

  1. Provide a task string describing the desired image\r
  2. Optionally set width, height (default 1024×1024, max 1440)\r
  3. Optionally set steps (default 4, max 8 — higher = slower but better quality)\r
  4. AIProx enhances your prompt via Claude, then routes to FLUX generation\r
  5. Returns an image_url with the generated image\r \r

Security Manifest\r

\r | Permission | Scope | Reason |\r |------------|-------|--------|\r | Network | aiprox.dev | API calls to orchestration endpoint |\r | Network | api.together.xyz | Image generation (server-side) |\r | Env Read | AIPROX_SPEND_TOKEN | Authentication for paid API |\r \r

Make Request\r

\r

curl -X POST https://aiprox.dev/api/orchestrate \\r
  -H "Content-Type: application/json" \\r
  -d '{\r
    "task": "a minimalist logo for an AI agent marketplace, dark background, cyan circuit board accents, clean sans-serif typography",\r
    "spend_token": "$AIPROX_SPEND_TOKEN"\r
  }'\r
```\r
\r
## Make Request — With Dimensions\r
\r
```bash\r
curl -X POST https://aiprox.dev/api/orchestrate \\r
  -H "Content-Type: application/json" \\r
  -d '{\r
    "task": "wide banner illustration of autonomous robots collaborating in a glowing digital city",\r
    "width": 1344,\r
    "height": 768,\r
    "spend_token": "$AIPROX_SPEND_TOKEN"\r
  }'\r
```\r
\r
### Response\r
\r
```json\r
{\r
  "image_url": "https://together-cdn.com/generated/flux-abc123.png",\r
  "prompt": "A minimalist logo featuring a stylized circuit board node pattern arranged in a circular emblem. Dark charcoal background (#1a1a2e), vibrant cyan accent lines (#00e5ff), clean geometric shapes suggesting connectivity and intelligence. Modern sans-serif wordmark below.",\r
  "width": 1024,\r
  "height": 1024,\r
  "model": "FLUX.1-schnell"\r
}\r
```\r
\r
## Trust Statement\r
\r
Image Gen Bot generates images based on prompts you provide. Generated images are returned via URL from Together.ai's CDN and are not stored by AIProx. Prompts are enhanced transiently by Claude and not logged beyond the transaction. Your spend token is used for payment only.\r
安全使用建议
This skill appears to do what it says (send prompts to AIProx which generates images via Together.ai). Before installing: 1) Verify the aiprox.dev endpoint and its privacy/billing policies (owner and homepage are not vetted here). 2) Treat AIPROX_SPEND_TOKEN like money — ensure it is scoped/limited and monitor/limit spend. 3) Do not put secrets or personal data into prompts (they will be sent to a third party and may be forwarded to Claude/Together.ai). 4) If you need stronger guarantees, ask for documentation about where prompts are routed (is Claude used server-side, and does AIProx log prompts?) or use a direct, official Together.ai integration instead. 5) Rotate the token if you suspect misuse and review network allowlists to confirm requests go only to the expected hosts.
功能分析
Type: OpenClaw Skill Name: image-gen-bot Version: 1.0.0 The image-gen-bot skill is a straightforward wrapper for generating images via the FLUX model using the AIProx API. It requires the AIPROX_SPEND_TOKEN environment variable for authentication and communicates with aiprox.dev, which is consistent with its stated purpose. No evidence of malicious execution, data exfiltration beyond the intended API token usage, or harmful prompt injection was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (image generation via FLUX/Together.ai) align with the declared requirement (AIPROX_SPEND_TOKEN) and the SKILL.md cURL examples that POST to aiprox.dev. No unrelated env vars or binaries are requested.
Instruction Scope
Runtime instructions are narrowly scoped: they show POSTing the prompt and spend_token to https://aiprox.dev/api/orchestrate and returning an image_url. However the doc states prompts are 'enhanced by Claude' and that images come from Together.ai's CDN; those operations are plausible if performed server-side by AIProx but are not shown in the client instructions. The skill will transmit user prompts (and the spend token) to a third-party endpoint — avoid sending sensitive secrets or PII in prompts.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk or fetched during install. That's the lowest-risk install model.
Credentials
Only AIPROX_SPEND_TOKEN is required, which is proportionate for a paid orchestration API. The SKILL.md lists network calls to aiprox.dev and api.together.xyz (expected). The doc makes privacy claims about not logging prompts and transient Claude usage — those are unverifiable from the skill alone. Confirm the token's scope and billing limits before use.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system-level privileges or modify other skills. Autonomous invocation is enabled by default but is not combined with any unusual privileges here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install image-gen-bot
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /image-gen-bot 触发
  4. 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
v1.0.0
- Initial public release of image-gen-bot. - Generate images from text prompts using the FLUX model via Together.ai. - Prompts are automatically enhanced for better visual quality before generation. - Supports customizable image dimensions and quality settings. - Returns a URL to the generated image for easy sharing or download.
元数据
Slug image-gen-bot
版本 1.0.0
许可证 MIT-0
累计安装 5
当前安装数 4
历史版本数 1
常见问题

Image Gen Bot 是什么?

Generate images from text prompts using FLUX via Together.ai. Returns image URL. Prompts are auto-enhanced for best results. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 578 次。

如何安装 Image Gen Bot?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-gen-bot」即可一键安装,无需额外配置。

Image Gen Bot 是免费的吗?

是的,Image Gen Bot 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Image Gen Bot 支持哪些平台?

Image Gen Bot 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 Gen Bot?

由 unixlamadev-spec(@unixlamadev-spec)开发并维护,当前版本 v1.0.0。

💬 留言讨论