Best use case
api-monitor is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. >
>
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "api-monitor" skill to help with this workflow task. Context: >
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/api-monitor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How api-monitor Compares
| Feature / Agent | api-monitor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
>
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# API 使用量监控技能(询问确认模式) ## 概述 监控 OpenClaw 模型 API 使用量,配额不足时**询问用户确认后再切换**,确保用户知情。 ## 功能 - ✅ 实时监控当前模型 API 状态 - ✅ 检测配额不足/错误 - ✅ 询问用户确认后再切换模型 - ✅ 支持多个模型优先级配置 - ✅ 手动指定切换到某个模型 ## 使用方法 ### 准备工作 ```bash # 确认Python环境 python3 --version # 确认脚本存在(路径根据实际安装位置调整) ls -la ~/.openclaw/skills/api-monitor/api_monitor.py ``` ### 查看当前状态 ```bash # 替换为实际脚本路径 SCRIPT_PATH="$HOME/.openclaw/skills/api-monitor/api_monitor.py" python3 "$SCRIPT_PATH" --check ``` ### 询问是否切换(生成询问消息) ```bash SCRIPT_PATH="$HOME/.openclaw/skills/api-monitor/api_monitor.py" python3 "$SCRIPT_PATH" --ask ``` ### 确认切换(用户确认后执行) ```bash SCRIPT_PATH="$HOME/.openclaw/skills/api-monitor/api_monitor.py" python3 "$SCRIPT_PATH" --confirm ``` ### 指定切换到某个模型 ```bash # 替换为目标模型 TARGET_MODEL="mydamoxing/MiniMax-M2.5" SCRIPT_PATH="$HOME/.openclaw/skills/api-monitor/api_monitor.py" python3 "$SCRIPT_PATH" --model "$TARGET_MODEL" ``` ### 列出所有可用模型 ```bash SCRIPT_PATH="$HOME/.openclaw/skills/api-monitor/api_monitor.py" python3 "$SCRIPT_PATH" --list-models ``` ## 可用模型列表 1. `mydamoxing/MiniMax-M2.5-highspeed` - MiniMax高速版 2. `mydamoxing/MiniMax-M2.5` - MiniMax普通版 3. `volcengine/ark-code-latest` - 火山引擎 4. `hajimi/claude-sonnet-4-20250511` - 免费模型 ## 工作流程 1. **定时检查** → 运行 `--check` 查看状态 2. **发现问题** → 运行 `--ask` 生成询问消息 3. **用户确认** → 运行 `--confirm` 执行切换 4. **或者** → 用户指定 `--model xxx` 直接切换 ## 示例对话 ``` 用户: 检查一下API状态 助手: (运行 --check) 当前模型: mydamoxing/MiniMax-M2.5-highspeed 状态: API配额可能不足,建议切换模型 错误次数: 3 用户: 那就切换吧 助手: (运行 --confirm) 确认切换: mydamoxing/MiniMax-M2.5-highspeed → mydamoxing/MiniMax-M2.5 切换成功! ``` ## 定时任务配置(可选) 如需定时自动检查,可配置 cron: ```bash # 编辑 crontab crontab -e # 添加定时任务(每30分钟检查一次) # 替换为实际路径 */30 * * * * cd $HOME/.openclaw/skills/api-monitor && python3 api_monitor.py --check >> /var/log/api-monitor.log 2>&1 ``` ## 注意事项 - 切换模型会中断当前会话 - 建议在非高峰期操作 - 始终需要用户确认才切换 - 定期检查日志 `/var/log/api-monitor.log` 了解运行状态
Related Skills
Competitor Monitor
Tracks and analyzes competitor moves — pricing changes, feature launches, hiring, and positioning shifts
Agent Observability & Monitoring
Score, monitor, and troubleshoot AI agent fleets in production. Built for ops teams running 1-100+ agents.
pc-monitor-cn
name: pc-monitor-cn
hatsune-miku-monitor
初音未来监控器 - 可爱的桌面系统监控工具(GIF动画 + 贴边隐藏 + 一键加速)
desktop-monitor-widget
桌面监控悬浮球 - 实时显示系统资源状态
openclaw-version-monitor
监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
jarvis-stock-monitor
全功能智能股票监控预警系统 Pro 版。支持成本百分比、均线金叉死叉、RSI 超买超卖、成交量异动、跳空缺口、动态止盈等 7 大预警规则。基础功能免费,高级功能 SkillPay 付费。
renewal-risk-monitor
识别续约风险信号,区分可挽回风险与高概率流失信号。;use for renewal, risk, customer-success workflows;do not use for 伪造健康度数据, 替代正式续约决策.
Amazon Review Monitor — Track, Analyze, Respond
**Never miss a negative review again. AI-drafted responses included.**
token-budget-monitor
Track and control token consumption across OpenClaw cron jobs
session-health-monitor
Context window health monitoring for OpenClaw agents — threshold warnings via Telegram, pre-compaction snapshots, and memory rotation.
cc-changelog-monitor
Monitor Claude Code releases and get Telegram alerts when new versions ship. Zero AI credits — pure bash monitoring.