Menu
ShowTime 全方位监控系统 MCP 服务集成。当用户需要查询监控数据、资源信息、指标趋势时使用此 skill。 支持查询资源列表、资源详情、指标类型、指标趋势、指标汇总等监控相关操作。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
Use when an OpenSpec change already has one or more Superpowers plan files and implementation should proceed while syncing completed work back to tasks.md.
Use when an OpenSpec change has proposal, design, and tasks artifacts ready and a Superpowers implementation plan needs to be created before execution.
| name | ShowTime 监控系统 |
| description | ShowTime 全方位监控系统 MCP 服务集成。当用户需要查询监控数据、资源信息、指标趋势时使用此 skill。 支持查询资源列表、资源详情、指标类型、指标趋势、指标汇总等监控相关操作。 |
ShowTime 是云基产品线的全方位监控系统，核心功能是指标采集和监控报表展示。此 skill 使 AI Agent 能够：
当用户提到以下意图时使用此 skill：
确保 ShowTime MCP Server 已正确安装和配置：
# 安装依赖
cd watcher-ai
pip install -r requirements.txt
# 配置环境变量
export SHOWTIME_API_URL=http://localhost:8080
export SHOWTIME_API_TOKEN=your-token
# 运行 MCP Server
python src/showtime_mcp.py
# 列出所有资源
result = await showtime_list_resources(params)
# 按平台过滤
result = await showtime_list_resources(params) # platform="cas"
# 获取特定资源的详细信息
result = await showtime_get_resource_detail(params) # resource_id="xxx"
# 列出所有可用的指标类型
result = await showtime_list_metric_types(params)
# 获取 CPU 使用率在过去 24 小时的趋势
result = await showtime_get_metric_trend(params) # resource_id="xxx", metric_type="cpu_usage", hours=24
# 获取资源的监控汇总
result = await showtime_get_metric_summary(params) # resource_id="xxx"
cpu_usage: CPU 利用率cpu_allocate_rate: CPU 分配比mem_usage: 内存利用率mem_allocate_rate: 内存分配比disk_usage: 磁盘利用率disk_iops: 磁盘 IOPSdisk_latency: 磁盘延迟disk_throughput: 磁盘吞吐量net_throughput: 网络吞吐量health_info: 健康度信息在 CodeBuddy 中配置 MCP Server：
{
"mcpServers": {
"showtime": {
"command": "python",
"args": ["/path/to/showtime_mcp.py"],
"env": {
"SHOWTIME_API_URL": "http://localhost:8080"
}
}
}
}
watcher-agent) 配合使用