openclaw-starter-guide
OpenClaw 小白养成手册。从零开始搭建多 Agent AI 助手系统的完整指南,包含免费起步方案(Qwen 零成本)、进阶方案(MiniMax Coding Plan ¥49/月)、旗舰外援(SiliconFlow/NewCLI 按需调用)。涵盖模型策略、Fallback 链设计、额度管理、常见故障排查。适合首次部署 OpenClaw 或想优化模型成本的用户。当用户说"怎么开始"、"新手指南"、"省钱方案"、"模型怎么选"、"fallback 怎么配"时使用此 skill。
Why use this skill?
Learn to build multi-agent AI systems with OpenClaw. A complete guide for cost-effective deployment, model strategies, and automated fallback chains.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jooey/openclaw-starter-guideWhat This Skill Does
The OpenClaw Starter Guide is an essential documentation and advisory skill designed to bootstrap your journey into multi-agent AI systems. It provides a structured, phased approach to building, scaling, and optimizing your OpenClaw setup. Whether you are a beginner looking to deploy your first agent at zero cost or a power user seeking to optimize operational expenses through sophisticated Fallback chains and multi-provider strategies, this skill acts as your personal technical advisor.
Installation
To install this guide and have it available within your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/jooey/openclaw-starter-guide
Ensure you have Node.js installed and your clawhub CLI configured to point to the official repository.
Use Cases
- Zero-Cost Deployment: Learning how to leverage Qwen and SiliconFlow for free tiers without sacrificing system reliability.
- Cost Optimization: Implementing the 'MiniMax Coding Plan' strategy to secure 7200 daily requests for just ¥49/month.
- Resilience Engineering: Designing Fallback chains where primary agents switch to free models automatically during rate limits or outages.
- Model Selection Strategy: Determining which models are best for logic-heavy tasks vs. background automation.
Example Prompts
- "我刚开始用 OpenClaw,怎么配置免费模型让我先跑起来?"
- "我的 MiniMax 额度快用完了,能教我怎么配置 fallback 自动切换到 Qwen 吗?"
- "现在有哪些高性价比的省钱方案推荐给个人开发者?"
Tips & Limitations
- Context Management: While the starter guide highlights 200K context models like MiniMax, always monitor your token usage in long-running agents to keep costs predictable.
- Fallback Priority: Always place your 'Free' models at the bottom of your fallback list to ensure the system prioritizes high-quality responses first.
- System Updates: Periodically run
clawhub updateto ensure you have the latest model recommendations and provider configurations. - Scope: This skill is a documentation helper. It provides configuration logic and best practices, but actual model interaction requires valid API keys from the respective providers (SiliconFlow, MiniMax, etc.).
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jooey-openclaw-starter-guide": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
callmac
Remote voice control for Mac from mobile devices using commands like /callmac or /voice. Broadcast announcements, play alarms, tell stories, wake up kids - all triggered from Telegram/WhatsApp messages. Uses edge-tts with mixed Chinese/English support, local playback, loops, and volume control. | 从移动设备通过 /callmac 或 /voice 命令远程控制 Mac 语音功能。广播公告、播放闹钟、讲故事、叫孩子起床 - 全部通过 Telegram/WhatsApp 消息触发。使用 edge-tts 支持中英文混合、本地播放、循环播放和音量控制。
add-minimax-provider
为 OpenClaw 配置 MiniMax 作为模型源。MiniMax 提供两种接入方式:API Key 直连(openai-completions 协议)和 OAuth 门户(anthropic-messages 协议)。包含 provider 注册、模型定义、别名配置、fallback 链接入和验证的完整流程。当管理员说想"加 MiniMax"、"配 minimax"、"接入 MiniMax 模型"、"加海螺模型"、"配 M2.1"时使用此 skill。
add-newcli-provider
为 OpenClaw 配置 code.newcli.com 作为模型源,包含四个 provider:newcli(Claude 主线路)、newcli-aws(Claude AWS 特价线路,消耗 1/24)、newcli-codex(GPT 系列)、newcli-gemini(Gemini 系列)。适用于需要接入 Claude 或 GPT 模型的场景。包含 provider 注册、模型定义、别名配置、fallback 链接入和验证的完整流程。当管理员说想"加 Claude"、"加 GPT"、"配 newcli"、"加 fox 源"、"接入 Claude 模型"、"接入 GPT 模型"、"加 codex"、"加 aws 线路"时使用此 skill。
add-siliconflow-provider
为 OpenClaw 配置硅基流动 (SiliconFlow) 作为模型源。SiliconFlow 是国内领先的 AI 模型推理平台,提供 98+ 个 chat 模型,包含多个免费模型(Qwen3-8B、DeepSeek-R1-8B 等)。使用标准 OpenAI 协议(openai-completions)。包含 provider 注册、模型定义、别名配置、fallback 链接入和验证的完整流程。当管理员说想"加硅基流动"、"配 SiliconFlow"、"接入 SF 模型"、"加 Kimi"、"加 Qwen3"、"加免费模型"、"接入 DeepSeek V3.2"时使用此 skill。