← 返回 Skills 市场
Geepers Llm
作者
Lucas Steuber
· GitHub ↗
· v1.0.0
658
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install geepers-llm
功能描述
Send requests to the dr.eamer.dev LLM API for chat completions, vision analysis, image generation, text-to-speech, and video generation across 12 model provi...
使用说明 (SKILL.md)
Dreamer LLM
Access 12 LLM providers through a single unified API at https://api.dr.eamer.dev.
Authentication
Set your API key in an environment variable or pass it per-request:
export DREAMER_API_KEY=your_key_here
Get a key: email [email protected] or visit https://dr.eamer.dev
Endpoints
Chat Completion
POST https://api.dr.eamer.dev/v1/llm/chat
Headers: X-API-Key: $DREAMER_API_KEY
Body:
{
"model": "claude-sonnet-4-5-20250929",
"messages": [{"role": "user", "content": "Hello"}],
"provider": "anthropic"
}
Available Providers
anthropic, openai, xai, mistral, cohere, gemini, perplexity, groq, huggingface, ollama
List Models
GET https://api.dr.eamer.dev/v1/llm/models
Vision (image analysis)
POST https://api.dr.eamer.dev/v1/llm/vision
Body: { "model": "claude-sonnet-4-5-20250929", "image_url": "...", "prompt": "Describe this image" }
Image Generation
POST https://api.dr.eamer.dev/v1/llm/image
Body: { "prompt": "A sunset over the ocean", "provider": "openai" }
Text-to-Speech
POST https://api.dr.eamer.dev/v1/llm/tts
Body: { "text": "Hello world", "voice": "alloy" }
When to Use
- Comparing responses across multiple LLM providers
- Accessing providers you don't have direct API keys for
- Building applications that need multi-provider LLM access
Don't Use When
- You already have direct API keys for the provider you need
- You need streaming responses (use direct provider APIs instead)
安全使用建议
This skill is an instruction-only adapter for the third-party endpoint api.dr.eamer.dev and will send your prompts to that service. Before installing: (1) Be aware you need a DREAMER_API_KEY (the SKILL.md documents this) but the registry metadata does not declare it — confirm how and where to provide the key. (2) Treat it like any external LLM proxy: do not send sensitive data (passwords, secrets, personal data) unless you trust the operator and their data-handling policies. (3) Ask the publisher for source/homepage and for the missing required-env declaration so the manifest matches runtime instructions. (4) If you already have direct provider keys for the model you need, prefer calling those provider APIs directly (the skill itself even recommends that). If you want me to, I can draft questions to ask the publisher (e.g., data retention, logging, exact provider mapping) or help you verify the DREAMER_API_KEY usage.
功能分析
Type: OpenClaw Skill
Name: geepers-llm
Version: 1.0.0
The skill bundle is benign. It describes a legitimate purpose: interacting with an external LLM API at `https://api.dr.eamer.dev`. The `SKILL.md` file provides clear instructions for API usage, including authentication via a `DREAMER_API_KEY` environment variable, which is standard practice. There is no evidence of malicious prompt injection, data exfiltration beyond the skill's stated purpose, unauthorized execution, or any other harmful behavior.
能力评估
Purpose & Capability
The SKILL.md describes a multi-provider LLM proxy (dr.eamer.dev) and the listed endpoints match that purpose. Minor inconsistency: the description text implies '12 model providers' while the 'Available Providers' list in the instructions shows 10 names. More importantly, the skill logically requires an API key for the proxy service (DREAMER_API_KEY) but the registry metadata declares no required environment variables or primary credential.
Instruction Scope
Runtime instructions explicitly instruct the agent to use an environment variable (DREAMER_API_KEY) and to POST requests to https://api.dr.eamer.dev and include X-API-Key. The instructions do not reference unrelated files or system paths, but they do reference an env var that the registry did not declare. That divergence means the agent may attempt to read an undeclared secret or the user may be unaware of the credential requirement.
Install Mechanism
No install spec and no code files — instruction-only skill. This is low-risk from an install/remote-code perspective because nothing is downloaded or written by an install step.
Credentials
The SKILL.md requires DREAMER_API_KEY for operation (and shows that API key is sent in X-API-Key), but the skill manifest lists no required env vars or primary credential. Requesting a single API key for the described proxy service is proportionate, but the manifest omission is an incoherence that could lead to accidental exposure or misconfiguration.
Persistence & Privilege
The skill does not request persistent/always-on presence (always:false) and does not declare actions that modify agent-wide configuration or other skills. Autonomy (disable-model-invocation:false) is the platform default and not a sole reason for concern here.
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 geepers-llm - 安装完成后,直接呼叫该 Skill 的名称或使用
/geepers-llm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
v1.0.0
Initial release of geepers-llm skill.
- Unified API access to 12 LLM providers for chat, vision analysis, image generation, text-to-speech, and video generation.
- Supports: anthropic, openai, xai, mistral, cohere, gemini, perplexity, groq, huggingface, ollama.
- Endpoints for chat completion, model listing, image analysis, image generation, and TTS.
- Designed for easy comparison of LLM provider responses and quick access without direct API keys.
- Simple API key setup via environment variable or per-request header.
元数据
常见问题
Geepers Llm 是什么?
Send requests to the dr.eamer.dev LLM API for chat completions, vision analysis, image generation, text-to-speech, and video generation across 12 model provi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 658 次。
如何安装 Geepers Llm?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install geepers-llm」即可一键安装,无需额外配置。
Geepers Llm 是免费的吗?
是的,Geepers Llm 完全免费(开源免费),可自由下载、安装和使用。
Geepers Llm 支持哪些平台?
Geepers Llm 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 Geepers Llm?
由 Lucas Steuber(@lukeslp)开发并维护,当前版本 v1.0.0。
推荐 Skills