Graceful rate limit handling with Ollama fallback. Notifies on rate limits, offers local model switch with confirmation for code tasks.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install llm-supervisor或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install llm-supervisor⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/llm-supervisor/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: llm-supervisor description: Graceful rate limit handling with Ollama fallback. Notifies on rate limits, offers local model switch with confirmation for code tasks. ---
Handles rate limits and model fallbacks gracefully.
When I encounter rate limits or overload errors from cloud providers (Anthropic, OpenAI):
Before using local models for code generation, ask: > "Cloud is rate-limited. Switch to local Ollama (qwen2.5:7b)? Reply 'yes' to confirm."
For simple queries (chat, summaries), can switch without confirmation if user previously approved.
/llm statusReport current state:
/llm switch localManually switch to Ollama for the session.
/llm switch cloudSwitch back to cloud provider.
# Check available models
ollama list
# Run a query
ollama run qwen2.5:7b "your prompt here"
# For longer prompts, use stdin
echo "your prompt" | ollama run qwen2.5:7bCheck with ollama list. Configured default: qwen2.5:7b
Track in memory during session:
currentProvider: "cloud" | "local" lastRateLimitAt: timestamp or nulllocalConfirmedForCode: booleanReset to cloud at session start.
安装 LLM Supervisor 后，可以对 AI 说这些话来触发它
Help me get started with LLM Supervisor
Explains what LLM Supervisor does, walks through the setup, and runs a quick demo based on your current project
Use LLM Supervisor to graceful rate limit handling with Ollama fallback
Invokes LLM Supervisor with the right parameters and returns the result directly in the conversation
What can I do with LLM Supervisor in my developer & devops workflow?
Lists the top use cases for LLM Supervisor, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/llm-supervisor/ 目录（个人级，所有项目可用），或 .claude/skills/llm-supervisor/（项目级）。重启 AI 客户端后，用 /llm-supervisor 主动调用，或让 AI 根据上下文自动发现并使用。
LLM Supervisor 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
LLM Supervisor 可免费安装使用。请查阅仓库了解许可证信息。
Graceful rate limit handling with Ollama fallback. Notifies on rate limits, offers local model switch with confirmation for code tasks.
LLM Supervisor 属于「Developer & DevOps」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my developer & devops tasks using LLM Supervisor
Identifies repetitive steps in your workflow and sets up LLM Supervisor to handle them automatically