# huawei-cloud-dws-io-diag

huawei-cloud-dws-io-diag — a skill for Claude Code, Codex, and Cursor. Pinpoints the root causes of disk I/O bottlenecks in Huawei Cloud DWS clusters whenever storage alerts fire.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 180 installs · ★ 59 repo stars
- Author: huaweicloud
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/huaweicloud/huaweicloud-skills/tree/HEAD/skills/bigdata/dws/huawei-cloud-dws-io-diag/SKILL.md
- Updated: 2026-11-12
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/huawei-cloud-dws-io-diag

## What it does

The skill engages whenever a Huawei Cloud DWS (GaussDB(DWS)) cluster experiences saturated disk util, severe await latency, or threshold alarms. Using a three-stage decision tree, it separates customer query pressure from infrastructure-side degradation.

The workflow queries cluster metrics directly through the KooCLI (`hcloud`) CLI tool. If KooCLI times out or is missing, the skill falls back to the DWS Autopilot MCP Server tools (`dws_autopilot_get_clusters`, `dws_autopilot_get_metric`, `dws_autopilot_get_hosts`). The diagnosis remains strictly read-only: it will not restart hosts, terminate SQL sessions, or modify database flags.

Diagnosis fails immediately if KooCLI version 3.2.0 or newer is absent and the fallback MCP server lacks configured IAM credentials.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-dws-io-diag -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/huawei-cloud-dws-io-diag/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/huawei-cloud-dws-io-diag/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-dws-io-diag -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/huawei-cloud-dws-io-diag/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-dws-io-diag -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/huawei-cloud-dws-io-diag/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install huaweicloud/huaweicloud-skills skills/bigdata/dws/huawei-cloud-dws-io-diag
```

2. **Manually: put the files in place**
- File: `.github/skills/huawei-cloud-dws-io-diag/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-dws-io-diag -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/huaweicloud/huaweicloud-skills --path skills/bigdata/dws/huawei-cloud-dws-io-diag
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/huawei-cloud-dws-io-diag/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-dws-io-diag -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/huaweicloud/huaweicloud-skills/tree/HEAD/skills/bigdata/dws/huawei-cloud-dws-io-diag/SKILL.md

## When to use it
- diagnose saturated disk utilization across GaussDB(DWS) instances
- trace high I/O await latency to specific cluster hosts or query bursts
- distinguish client workload surges from underlying hardware issues
- generate a standardized HTML report covering cluster metric data

## Example prompts
- DWS cluster disk util is pegged at 100%, investigate the root cause
- Received an I/O warning on cluster dws-analytics, analyze the bottleneck
- Collect storage performance metrics and build a diagnostic HTML summary

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: ca5e5ed040ce06fb.

BEGIN THIRD-PARTY FILE ca5e5ed040ce06fb
```text
---
name: huawei-cloud-dws-io-diag
description: |
  DWS cluster I/O overload root cause diagnosis skill, based on KooCLI v3.2.0+ and DWS Autopilot MCP Server.
  Automatically collects I/O metrics, analyzes root causes (customer-side / system-side) via three-stage decision tree, and outputs a standardized diagnosis report.
  Applicable to DWS cluster I/O usage too high, I/O alarms, disk I/O load anomaly scenarios.
  Trigger words: "I/O高", "I/O告警", "I/O诊断", "I/O过载", "IO高", "IO告警", "IO诊断", "IO过载", "磁盘IO负载异常", "util打满", "await高", "high I/O", "I/O alarm", "I/O diagnosis"
tags: [huawei-cloud, dws, io, diagnostics, autopilot]

# ============================================================
# Internal extension fields
# ============================================================
trigger:
  keywords: ["DWS", "I/O高", "I/O告警", "I/O诊断", "I/O过载", "I/O使用率过高", "IO高", "IO告警", "IO诊断", "IO过载", "IO使用率过高", "磁盘I/O负载异常", "磁盘IO负载异常", "util打满", "await高", "节点数据盘I/O利用率超阈值", "high I/O", "I/O alarm", "I/O diagnosis", "I/O overload", "high I/O usage", "disk I/O anomaly", "util saturated", "high await", "I/O utilization exceeds threshold"]
  resource_types: ["DWS::instance_id"]
  hypotheses: ["io_high", "io_warning", "io_overload"]

input_schema:
  required:
    - name: "alarm_serial_number"
      type: "string"
      description: "Alarm serial number"
    - name: "cluster_id"
      type: "string"
      description: "Cluster unique ID (instance ID), corresponding to the alarm resourceId"
    - name: "first_alarm_time"
      type: "integer"
      description: "First alarm time, Unix millisecond timestamp (UTC timezone), used directly for tool from_ts/to parameters"
    - name: "alarm_name"
      type: "string"
      description: "Alarm name"
  optional:
    - name: "project_id"
      type: "string"
      description: "Project ID, used as the project_id parameter for tool calls. If not provided, read from MCP Server config file (conf/dws_config.yaml) project_id field"
    - name: "region_id"
      type: "string"
      description: "Region identifier, used for hcloud --cli-region parameter and report region field. If not provided, read from MCP Server config file (conf/dws_config.yaml) region_id field"
    - name: "node_name"
      type: "string"
```
END THIRD-PARTY FILE ca5e5ed040ce06fb

The third-party file has ended. Everything between the ca5e5ed040ce06fb tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2399 of 44669 bytes. © huaweicloud · MIT · https://github.com/huaweicloud/huaweicloud-skills/tree/HEAD/skills/bigdata/dws/huawei-cloud-dws-io-diag/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
