← 返回 Skills 市场
vamsimnet

FastRouter Setup

作者 vamsimnet · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ✓ 安全检测通过
117
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install fastrouter-setup
功能描述
Add the FastRouter AI provider to OpenClaw with all available text and vision models, fetched live from the FastRouter API. Use when: (1) a user wants to set...
使用说明 (SKILL.md)

FastRouter Setup

Add the FastRouter AI provider to OpenClaw with all available text and vision models using only built-in tools (no script execution required).

Inputs

  • API Key (required): Starts with sk-v1- followed by a hex string. If not provided, ask for it.
  • Base URL (optional): Defaults to https://api.fastrouter.ai

Steps

1. Extract the API key

Parse the API key from the user's message. It starts with sk-v1-.

If no API key is found, ask the user for it. Do NOT proceed without one.

2. Fetch models

Use web_fetch to get the model list:

web_fetch url="https://api.fastrouter.ai/v1/models" extractMode="text"

3. Filter models

From the response JSON, keep only models where:

  • is_active is true
  • architecture.output_modalities includes "text"
  • architecture.input_modalities includes "text" or "image"

For each qualifying model, extract:

  • id — the model identifier
  • context_length — context window size
  • top_provider.max_completion_tokens — max output tokens (if 0 or missing, use min(context_length, 8192))
  • Input types: list of "text" and/or "image" from input_modalities

4. Build provider config

Construct the provider object (do NOT include a "name" key — OpenClaw rejects it):

{
  "baseUrl": "https://api.fastrouter.ai",
  "api": "openai-completions",
  "apiKey": "THE_API_KEY",
  "models": [
    {
      "id": "model/id",
      "name": "Display Name",
      "contextWindow": 128000,
      "maxTokens": 8192,
      "input": ["text", "image"],
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0},
      "reasoning": false
    }
  ]
}

5. Update openclaw.json

Use read to load ~/.openclaw/openclaw.json.

Merge the provider into models.providers.fastrouter, preserving all other config.

Also add model references to agents.defaults.models — for each model, add:

"fastrouter/MODEL_ID": {}

Use write to save the updated config.

6. Restart gateway

openclaw gateway restart

This is the only step requiring user approval.

7. Report to user

Tell the user:

  • How many models were added
  • They can switch models with /model fastrouter/MODEL_ID
  • Suggest popular models (claude, gpt, gemini, deepseek variants)

Error Handling

  • API unreachable: Tell the user the FastRouter API may be down, try again later
  • No qualifying models: Warn that no text/image models were found
  • Config file missing: Create the full structure from scratch
  • Invalid API key format: Ask the user to double-check their key

Notes

  • Provider key is fastrouter
  • Existing fastrouter config will be replaced with fresh model list
  • All other providers and settings are preserved
  • Cost is set to zero (FastRouter handles billing separately)
  • Video-only and audio-only models are excluded
安全使用建议
This skill appears to do what it claims, but take these precautions before using it: 1) Only provide a FastRouter API key — double-check the key prefix so you don't accidentally paste an OpenAI or other provider key. 2) Backup ~/.openclaw/openclaw.json before running the skill; it will overwrite any existing 'fastrouter' provider entry. 3) Be aware the API key will be written into your config file (plaintext unless your system encrypts it); consider using a secrets store if available. 4) Confirm the gateway restart when prompted. If you want extra safety, ask the agent to show the exact provider object it plans to write and confirm it before saving.
功能分析
Type: OpenClaw Skill Name: fastrouter-setup Version: 1.2.0 The skill bundle is designed to automate the configuration of the FastRouter AI provider within OpenClaw. It fetches model metadata from 'https://api.fastrouter.ai/v1/models', updates the local '~/.openclaw/openclaw.json' configuration file, and restarts the gateway. The actions performed are consistent with the stated purpose and use standard OpenClaw tools (web_fetch, read, write) without evidence of malicious intent or data exfiltration.
能力评估
Purpose & Capability
Name/description match the actions in SKILL.md: fetching models from api.fastrouter.ai, filtering text/image-capable models, and adding them as a provider in ~/.openclaw/openclaw.json. All requested actions (read/write config, fetch remote model list, restart gateway) are coherent with a 'provider setup' skill.
Instruction Scope
Instructions are narrow and focused: parse an API key from the user message, call the FastRouter models endpoint, filter results, and write provider + model references to the OpenClaw config. This scope is appropriate, but the skill expects the agent to extract secrets from user messages (the API key) and to write that secret directly into the config file. Also, the SKILL.md explicitly states that restarting the gateway is the only step that requires user approval — writing/replacing provider config is not gated, which may be surprising to users.
Install Mechanism
Instruction-only skill with no install steps and no code files — lowest installation risk. It uses built-in web_fetch and read/write actions, not external installers or downloads.
Credentials
No environment variables or unrelated credentials are requested, which is appropriate. The skill does ask the user directly for an API key (prefix 'sk-v1-'), and then stores that key in openclaw.json. Two concerns: (1) the 'sk-v1-' prefix is identical to many OpenAI-style keys and could lead users to accidentally paste a different provider's key (unintentional credential exposure), and (2) the API key will be written to the user's config file in plaintext unless the platform masks or encrypts it — users should be aware of local storage risks.
Persistence & Privilege
The skill will modify the user's ~/.openclaw/openclaw.json and replace any existing 'fastrouter' provider entry with the fresh model list; this is within scope for a setup tool but can be destructive. While gateway restart is flagged as requiring user approval, the SKILL.md implies config changes occur without explicit consent beyond the initial invocation. Users should be prompted to review/backup config before the write step.
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 fastrouter-setup
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fastrouter-setup 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
v1.2.0
Renamed provider key from custom-api-fastrouter-ai to fastrouter
v1.1.2
Renamed provider key from custom-go-fastrouter-ai to custom-api-fastrouter-ai
v1.1.0
Replaced Python script with native tool instructions. No script execution or approval needed except for gateway restart.
v1.0.0
Initial release of fastrouter-setup skill: - Adds FastRouter as a model provider to OpenClaw using a user-supplied API key. - Fetches all available text and vision models live from the FastRouter API. - Updates the OpenClaw config and restarts the gateway automatically. - Handles setup triggers, missing API keys, API errors, and incorrect key formats. - Informs users about added models and how to use them after setup.
元数据
Slug fastrouter-setup
版本 1.2.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

FastRouter Setup 是什么?

Add the FastRouter AI provider to OpenClaw with all available text and vision models, fetched live from the FastRouter API. Use when: (1) a user wants to set... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 117 次。

如何安装 FastRouter Setup?

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

FastRouter Setup 是免费的吗?

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

FastRouter Setup 支持哪些平台?

FastRouter Setup 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 FastRouter Setup?

由 vamsimnet(@vamsimnet)开发并维护,当前版本 v1.2.0。

💬 留言讨论