huawei-cloud-flexus-l-deploy-jiuwenswarm — Claude Code skill
huawei-cloud-flexus-l-deploy-jiuwenswarm is a skill that deploys JiuwenSwarm or JiuwenClaw on Huawei Cloud Flexus L and configures a model API and supported messaging channel.
MIT 260 installs ★ 59 updated 2026-11-12
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a claude-codeWhat huawei-cloud-flexus-l-deploy-jiuwenswarm does
This skill automates deployment of JiuwenSwarm on Huawei Cloud Flexus L. It creates an instance, checks its status and public IP, runs deployment scripts through Huawei Cloud COC, and tracks the task result. It can also configure a systemd service to start the app when the instance boots.
You need a Huawei Cloud account with Flexus L quota, Python 3.8+, the requests, huaweicloudsdkcore, and huaweicloudsdkcoc packages, plus hcloud available in PATH. Credentials can come from ~/.hcloud/config.json or environment variables. Model API credentials are needed to configure a model; channel credentials are needed for Xiaoyi, Feishu, or DingTalk setup.
Web access requires opening port 5173 in the security group after deployment. Without that rule, the app won’t be reachable over the web. Install the Python dependencies with pip install -r requirements.txt; the files in scripts are not to be modified.
What it helps with
- create a Flexus L instance for JiuwenSwarm
- check an instance and retrieve its public IP
- deploy the app remotely through COC
- set up a model API for JiuwenSwarm
- configure a Xiaoyi, Feishu, or DingTalk channel
Example prompts for the agent
- Deploy JiuwenSwarm on Huawei Cloud Flexus L and configure its model.
- Create a Flexus L instance and install JiuwenClaw.
- Set up a Feishu channel for JiuwenSwarm.
How to install huawei-cloud-flexus-l-deploy-jiuwenswarm
1Skills CLI (Vercel)
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a claude-code2Manually: put the files in place
~/.claude/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/
1Skills CLI (Vercel)
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a codex2Manually: put the files in place
.agents/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a cursor2Manually: put the files in place
.cursor/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install huaweicloud/huaweicloud-skills skills/computing/flexus-l/huawei-cloud-flexus-l-deploy-jiuwenswarm2Manually: put the files in place
.github/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.md1Skills CLI (Vercel)
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a gemini-cli2Platform CLI
gemini skills install https://github.com/huaweicloud/huaweicloud-skills --path skills/computing/flexus-l/huawei-cloud-flexus-l-deploy-jiuwenswarmManually: put the files in place
.devin/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about huawei-cloud-flexus-l-deploy-jiuwenswarm
How do I install huawei-cloud-flexus-l-deploy-jiuwenswarm in Claude Code?
Run npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-deploy-jiuwenswarm -a claude-code. The skill file is available at ~/.claude/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm/SKILL.md.
What does huawei-cloud-flexus-l-deploy-jiuwenswarm do?
It creates a Huawei Cloud Flexus L instance and deploys JiuwenSwarm or JiuwenClaw through COC. It can also configure a model and one of the supported messaging channels.
What does this skill need to run?
It requires Python 3.8+, hcloud on PATH, the requests, huaweicloudsdkcore, and huaweicloudsdkcoc packages, and Huawei Cloud credentials with suitable permissions. Model API credentials are needed for model setup.
Source text
SKILL.md · MIT
---
name: huawei-cloud-flexus-l-deploy-jiuwenswarm
description: "One-click deployment of JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances. Usage scenarios: When users need to quickly deploy JiuwenSwarm/JiuwenClaw on Huawei Cloud Flexus L instances, when they need to automatically create cloud instances and deploy AI Agent platforms, when they need to configure model APIs and message channels (Xiaoyi/Feishu/DingTalk). Automatically create instances, deploy applications via COC, configure models and message channels. Trigger keywords: JiuwenSwarm deployment, JiuwenClaw deployment, 九问Swarm部署, 九问Claw部署, 一键部署JiuwenSwarm, AI智能体平台部署, 部署九问Swarm, 部署九问Claw,云服务器部署AI平台."
tags:
- JiuwenSwarm
- JiuwenClaw
- AI Agent
metadata: {"jiuwenswarm": {"requires": {"bins": ["python3", "hcloud"]}, "install": [{"kind": "pip", "command": "pip install -r requirements.txt"}]}}
---
## **Important Notes**:
1. All Python files in the `scripts` directory have implemented all functions. **Do not create additional py files**.
2. **Do not modify** the script files in the `scripts` directory.
3. Please operate directly according to the provided code and documentation. No need to check Huawei Cloud official API documentation.
## security Execution Rules (Highest Priority):
1. All scripts MUST be executed via skill action=exec, NEVER run directly in shell
2. NEVER print script contents or commands containing AK/SK/Token in conversation
3. NEVER create temporary script files, prefer inline execution (python -c)
4. On execution failure, only return error info, do NOT rewrite scripts or print full commansds
5. AK/SK/Token MUST be passed via environment variables or hcloud config, NEVER appear in conversation
6. NEVER interactively collect Huawei Cloud credentials from users. Credentials MUST be obtained only through:
- hcloud CLI config file (~/.hcloud/config.json) — primary source, auto-detected
- Temporary Security Credentials (STS Token) via environment variables — fallback
- Permanent credentials via environment variables — fallback
# JiuwenSwarm Deployment Skill for Huawei Cloud Flexus L Instance
## Overview
This skill provides a complete automated deployment solution for the JiuwenSwarm (JiuwenClaw) multi-Agent collaboration platform on Huawei Cloud Flexus L instances. It implements full-process automation from environment preparation to message channel configuration through phased scripts.
---
## Prerequisites
### 1. Huawei Cloud Account Requirements
- A valid Huawei Cloud account with active subscription
- Sufficient balance or billing method configured
- Flexus L instance quota available in target region (cn-north-4/cn-east-3/cn-south-1/cn-southwest-2)
### 2. IAM Credentials
- Huawei Cloud Access Key (AK) and Secret Key (SK) with appropriate permissions
- **Temporary Security Credentials (STS Token)**: Supports temporary security credentials. When `HUAWEICLOUD_SDK_SECURITY_TOKEN` environment variable is set along with AK/SK, the skill will use temporary credentials for authentication.
- Required IAM permissions: see [references/iam-policies.md](references/iam-policies.md)
### 3. Environment Requirements
- Python 3.8+ installed with pip
- It is recommended to use a Python virtual environment to avoid system package conflicts:
```bash
python3 -m venv .venv && source .venv/bin/activate
```
If you cannot use a virtual environment, you may need to add `--break-system-packages` when running pip on some newer Linux distributions.
- Required Python packages: `requests`, `huaweicloudsdkcore`, `huaweicloudsdkcoc`
- KooCLI (`hcloud`) must be installed and available in PATH (used for IAM/RMS queries, see [references/api-specs.md](references/api-specs.md))
### 4. Network Requirements
- Internet access to Huawei Cloud APIs
- Security group rules allowing outbound HTTP/HTTPS traffic (ports 80, 443)
- For web access: Port 5173 needs to be opened in security group after deployment
### 5. Resource Requirements
- Flexus L instance with minimum specifications:
- Flavor: 2c-4g-50g (2 vCPUs, 4GB RAM, 50GB disk) or higher
- Network: Public IP required
- Supported flavors:
- 2c-4g-50g (2 vCPU 4GB 50GB) - ~60 CNY/month
- 2c-4g-70g (2 vCPU 4GB 70GB) - ~100 CNY/month
- 4c-8g-180g (4 vCPU 8GB 180GB) - ~170 CNY/month
### 6. Configuration Requirements
- Model API credentials (API_BASE, API_KEY) for LLM integration (required for Phase 6)
- Message channel credentials (Xiaoyi/Feishu/DingTalk) if channel configuration is needed (required for Phase 7)
### Architecture Diagram
```
User/Agent ──────▶│ Flexus L Instance │──────▶│ JiuwenSwarm App │──────▶│ Model Config │ ──────▶│ Channel Config │
(Skill caller) (Target Host) (Multi-Agent Platform) (API_BASE/KEY) (Xiaoyi/Feishu/Dingtalk)
```
**Component Description**:
- **User/Agent**: Skill caller that triggers JiuwenSwarm deployment operations via natural language or API
- **Flexus L Instance**: Huawei Cloud Elastic Cloud Server, serving as the target host for JiuwenSwarm deployment
- **JiuwenSwarm App**: Multi-agent collaboration platform running on the Flexus L instance
- **Model Config**: Configuration for external LLM services (API_BASE, API_KEY, MODEL_NAME, MODEL_PROVIDER)
- **Channel Config**: Messaging channel configuration (Huawei Xiaoyi, Feishu, Dingtalk)
---
## Skill Responsibilities
### Core Functions
1. **Flexus L Instance Creation** - Call Flexus L API to create instances, supporting parameters like instance name, flavor, region, etc.
2. **Instance Status Query** - Query instance status, public IP, instance ID via KooCLI (`hcloud RMS ListAllResources`)
3. **COC Remote Deployment** - Use Huawei Cloud COC (Cloud Operations Center) to remotely execute deployment scripts on instances
4. **COC Task Status Query** - Query deployment task execution status and results via COC API
5. **System Service Configuration** - Configure systemd service for auto-start on boot
6. **Model Configuration** - Configure API_BASE, API_KEY, MODEL_NAME, MODEL_PROVIDER
7. **Message Channel Configuration** - Support three message channels: Xiaoyi, Feishu, DingTalk
### Typical Use Cases
**English Examples:**
1. **"Help me deploy JiuwenSwarm to Huawei Cloud"**
2. **"I want to install JiuwenClaw on Flexus L instance"**
3. **"How to add Feishu bot to my JiuwenSwarm?"**
4. **"I want to configure JiuwenSwarm to use custom model"**
5. **"Help me deploy JiuwenSwarm with one click and configure Xiaoyi channel"**
## 工作流
This skill executes deployment in 7 phases. Each phase must complete before the next begins.
### Phase 1: Environment Preparation
1. Verify Huawei Cloud credentials (AK/SK)
2. Set environment variable: `PYTHONIOENCODING=utf-8`
3. Check dependency modules: requests, huaweicloudsdkcore, huaweicloudsdkcoc, and KooCLI (`hcloud`)
4. Validate credential validity (via KooCLI `hcloud IAM KeystoneListProjects`)
### Phase 2: Create Flexus L Instance
> ⚠️ **Requires customer confirmation before execution!**
1. If `--region` parameter not provided, interactively prompt user to select a region from supported options
2. Display instance configuration to customer (name, flavor, region, estimated cost)
3. Wait for customer confirmation (reply "confirm" or "agree")
4. After confirmation: Get Project ID (KooCLI) → Call Flexus L create API → Save order_id → Poll RMS via KooCLI for completion (polls every **30 seconds**, defaults to **600s/10 minutes** timeout, configurable via `--timeout`) → Get instance_id, public_ip, ecs_instance_id
### Phase 3: COC Remote Dependency Installation
1. Execute dependency installation script via COC
2. Install base tools: git, curl, vim, wget, net-tools, etc.
3. Check Python and Node.js environment
4. Wait for completion (~8 minutes). Only retry if script execution errors occur.
### Phase 4: COC Remote JiuwenSwarm Service Deployment
1. Read deployment script template (assets/deploy_script_template.sh)
2. Execute complete deployment script on instance via COC
3. Install JiuwenSwarm, configure systemd service, start service
4. Wait for completion (~15 minutes). Only retry if script execution errors occur.
### Phase 5: Verify Deployment Result
1. Query COC deployment task status
2. Verify `jiuwenswarm` service is running (`systemctl is-active`)
3. Verify `.env` has `FRONTEND_HOST=0.0.0.0`
4. Verify all ports bound to 0.0.0.0: 5173, 18092, 19000, 19001
5. Check service health (`curl localhost:5173` returns 200)
6. Output web access URL: `http://{public_ip}:5173`
7. Remind user to configure security group for external access
### Phase 6: Model Configuration
1. Interactively collect: API_BASE, API_KEY, MODEL_NAME, MODEL_PROVIDER
2. Generate COC remote execution script: backup `.env`, update 4 core parameters, set permission 600
3. Restart JiuwenSwarm service
### Phase 7: Message Channel Configuration
1. Select channel type: xiaoyi / feishu / dingtalk
2. Collect configuration based on channel type:
- xiaoyi: AK, SK, Agent ID
- feishu: App ID, App Secret
- dingtalk: Client ID, Client Secret, Allow From
3. Generate COC remote execution script: backup `config.yaml`, update channel fields, set permission 644
4. Restart JiuwenSwarm service
### COC Task Status Query
Query COC execution status by UUID. Supports single query, verbose output, wait-for-completion, and file loading. See [references/verification-method.md](references/verification-method.md) for details.
| Status | Description |
|--------|-------------|
| READY | Ready |
| PROCESSING | Running, waiting required |
| FINISHED | Completed successfully |
| ABNORMAL | Execution abnormal, failed |
| CANCELED | Canceled |
---
### 在已有实例上部署 (Deploy on an Existing Instance)
If the Flexus L instance is **already created**, skip `create_instance.py` and deploy JiuwenSwarm directly onto it: run `install_deps.py` → `deploy_service.py` → `verify_deployment.py` → `config_model.py` → `config_channel.py`, chaining with `--ip <public_ip>` (or `--instance-id` / `--ecs-instance-id`). Keep the customer confirmation step before any COC execution. Full step-by-step guide and command examples: [references/existing-instance-deploy-and-resource-cleanup.md](references/existing-instance-deploy-and-resource-cleanup.md)
## 资源清理 (Resource Cleanup)
Deployed Flexus L instances keep being billed (esp. **包年包月 / prePaid**). When no longer needed, release via Flexus L Console (**释放/删除**, or **退订** for prePaid) after customer confirmation. Full cleanup steps, backup and post-cleanup verification: [references/existing-instance-deploy-and-resource-cleanup.md](references/existing-instance-deploy-and-resource-cleanup.md)
---
## 核心命令
### Environment Setup
```bash
# Install dependencies
pip install -r requirements.txt
```
**Credential configuration (choose one):**
Option A — hcloud CLI config (recommended, no env vars needed):
```bash
hcloud configure set --cli-mode=AKSK --cli-region=cn-north-4 \
--cli-access-key=<your-ak> --cli-secret-key=<your-sk>
# For STS token: also add --cli-security-token=<your-token>
```
Option B — Environment variables:
```bash
export HUAWEICLOUD_SDK_AK=<your-access-key>
export HUAWEICLOUD_SDK_SK=<your-secret-key>
export HUAWEICLOUD_SDK_SECURITY_TOKEN=<your-security-token> # STS only
export HUAWEICLOUD_REGION="cn-north-4"
```
### Deployment Commands
```bash
# 1. Environment preparation
python scripts/prepare_env.py
# 2. Create instance (interactive confirmation)
python scripts/create_instance.py --name jiuwenSwarm-<timestamp> --flavor 2c-4g-50g --wait
# 3. Install dependencies
python scripts/install_deps.py --ip <public_ip>
# 4. Deploy service
python scripts/deploy_service.py --ip <public_ip>
# 5. Verify deployment
python scripts/verify_deployment.py --ip <public_ip>
# 6. Configure model
python scripts/config_model.py --ip <public_ip> --interactive
# 7. Configure message channel
python scripts/config_channel.py --channel xiaoyi --ip <public_ip> --interactive
# 8. Query COC task status
python scripts/query_coc_status.py --uuid <execute_uuid> --verbose
```
### COC Status Query Commands
```bash
# Query single task status
python scripts/query_coc_status.py --uuid <execute_uuid>
# Wait for task completion with custom timeout
python scripts/query_coc_status.py --uuid <execute_uuid> --wait --timeout 3600 --interval 30
# Load UUID from JSON file
python scripts/query_coc_status.py --from-file new_instance_info.json
```
## 参数确认
### ⚠️ Customer Confirmation Required
**Before executing any cloud resource creation operations, explicit customer consent must be obtained!**
| Operation | Confirmation Required |
|-----------|----------------------|
| Create new Flexus L instance | **Required** |
| Deploy application on existing instance | **Required** |
| Modify cloud resource configuration | **Required** |
**Confirmation Template**:
```
============================================================
⚠️ Cloud Resource Creation Confirmation
============================================================
Operation to be executed: Create new Flexus L instance
Instance Specifications:
- Name: {instance_name}
- Flavor: {flavor} (2c-4g-50g ~60 CNY/month / 2c-4g-70g ~100 CNY/month / 4c-8g-180g ~170 CNY/month)
- Region: {region}
- Estimated Cost: Calculated based on selected flavor
Resources will be created immediately after confirmation.
Please reply "confirm" or "agree" to continue.
============================================================
```
### User-Configurable Parameters
#### create_instance.py
| Parameter | Description | Default Value |
|-----------|-------------|---------------|
| --name | Instance name | jiuwenSwarm-{timestamp} |
| --flavor | Instance flavor (2c-4g-50g / 2c-4g-70g / 4c-8g-180g) | 2c-4g-50g |
| `--region` | Region (cn-north-4/cn-east-3/cn-south-1/cn-southwest-2). If not specified, interactive selection will be shown. | (Interactive) |
| `--image` / `--image-id` | System image. **Only Ubuntu 24.04 is supported** and used by default. Any other image is rejected with a clear message ("仅支持 Ubuntu 24.04,您指定的 {image} 不被支持") instead of being silently replaced. | Ubuntu 24.04 |
| `--charging-mode` | Charging mode: only `prePaid` (包年包月) is supported by the HCSS CreateFlexusL API. `postPaid` is NOT supported and rejected with a clear message. | prePaid |
| `--wait` | Wait for creation completion (polls RMS every **30s** for instance status) | False |
| --timeout | Maximum time to wait in seconds when `--wait` is used | 600 (10 minutes) |
| --confirm | Skip confirmation prompt | False |
#### deploy_service.py
| Parameter | Description | Default Value |
|-----------|-------------|---------------|
| --ip | Instance public IP | Required |
| --wait | Wait for deployment completion | True |
| --timeout | Timeout in seconds | 1800 |
#### config_model.py
| Parameter | Description |
|-----------|-------------|
| --api-base | Model API URL |
| --api-key | Model API key |
| --model-name | Model name |
| --model-provider | Model provider |
| --ip | Instance public IP |
| --interactive | Interactive configuration |
#### config_channel.py
| Parameter | Description |
|-----------|-------------|
| --channel | Channel type (xiaoyi/feishu/dingtalk) |
| --ip | Instance public IP |
| --interactive | Interactive configuration |
#### query_coc_status.py
| Parameter | Description | Default Value |
|-----------|-------------|---------------|
| --uuid, -u | COC execution UUID | Required |
| --from-file, -f | Read UUID from JSON file | - |
| --key, -k | UUID key name in JSON file | execute_uuid |
| --verbose, -v | Show detailed output | False |
| --wait, -w | Wait for task completion | False |
| --timeout, -t | Wait timeout in seconds | 1800 |
| --interval, -i | Polling interval in seconds | 60 |
## Directory Structure
```
huawei-cloud-flexus-l-deploy-jiuwenswarm/
├── SKILL.md # Skill documentation
├── requirements.txt # Python dependency list
├── scripts/ # Phased deployment scripts
│ ├── utils.py # Utility functions
│ ├── prepare_env.py # Environment preparation
│ ├── create_instance.py # Create Flexus L instance
│ ├── install_deps.py # COC remote dependency installation
│ ├── deploy_service.py # COC remote service deployment
│ ├── verify_deployment.py # Verify deployment result
│ ├── config_model.py # Model configuration
│ ├── config_channel.py # Message channel configuration
│ └── query_coc_status.py # COC task status query
├── assets/ # Template files
│ ├── deploy_script_template.sh # Deployment script template
│ ├── jiuwenswarm.service.template # systemd service template
│ ├── config_template.yaml # Configuration template
│ └── env_template.env # Environment variable template
└── references/ # Reference documents
├── api-specs.md # API specifications
├── deployment-checklist.md # Deployment checklist
├── iam-policies.md # IAM policies
├── verification-method.md # Verification methods
├── acceptance-criteria.md # Acceptance criteria
└── troubleshooting.md # Troubleshooting guide
```
---
## Web UI Access
Web UI access requires two conditions:
1. **Service bound to 0.0.0.0** (configured via `.env` `FRONTEND_HOST=0.0.0.0`)
2. **Security group allows port 5173** (configured in Huawei Cloud Console)
#### .env Configuration (Service-side)
The `.env` file at `/root/.jiuwenswarm/config/.env` must use the correct variable names:
| .env Variable | Purpose | Required Value |
| :------------------- | :------------------- | :------------- |
| `FRONTEND_HOST` | Frontend HTTP bind | `0.0.0.0` |
| `FRONTEND_PORT` | Frontend HTTP port | `5173` |
| `WEB_HOST` | WebChannel bind | `0.0.0.0` |
| `AGENT_SERVER_HOST` | AgentServer bind | `0.0.0.0` |
| `GATEWAY_HOST` | Gateway bind | `0.0.0.0` |
#### Security Group Configuration (Cloud-side)
1. Login to [Flexus L Console](https://console.huaweicloud.com/smb/?/resource/list)
2. Find your JiuwenSwarm instance → instance details → Security/Network
3. Configure security group rules to open port 5173 (TCP inbound)
**Access URL**: `http://<instance_public_ip>:5173`
**Security Warning**: After opening the port, JiuwenSwarm Web interface will be accessible. Please evaluate security risks before enabling. It is recommended to open temporarily only when needed and close after use.
---
## Huawei Cloud Credential Configuration
**Credential priority: hcloud config file → environment variables.**
### Option 1: hcloud CLI Config File (Recommended)
Credentials are read from `~/.hcloud/config.json`. If encryption is enabled (`authEncrypt=true`), the script automatically disables it to read plaintext values.
```bash
# Permanent credentials
hcloud configure set --cli-mode=AKSK --cli-region=cn-north-4 \
--cli-access-key=<AK> --cli-secret-key=<SK>
# Temporary credentials (STS Token)
hcloud configure set --cli-mode=AKSK --cli-region=cn-north-4 \
--cli-access-key=<AK> --cli-secret-key=<SK> --cli-security-token=<TOKEN>
```
No environment variables needed — the script reads directly from the config file.
### Option 2: Environment Variables (Fallback)
| Environment Variable | Description | Required |
|---------------------|-------------|----------|
| `HUAWEICLOUD_SDK_AK` | Access Key (permanent or temporary) | Yes |
| `HUAWEICLOUD_SDK_SK` | Secret Key (permanent or temporary) | Yes |
| `HUAWEICLOUD_SDK_SECURITY_TOKEN` | Security Token (STS only) | No |
| `HUAWEICLOUD_REGION` | Huawei Cloud Region (default: cn-north-4) | No |
**Reference**: https://support.huaweicloud.com/iam_faq/iam_01_0620.html
---
## Key API Endpoints
| Service | Endpoint | Purpose |
|---------|----------|---------|
| Flexus L | https://hcss.{region}.myhuaweicloud.com/v1/light-instances | Create/query instances |
| IAM | KooCLI: `hcloud IAM KeystoneListProjects --cli-region=<region> [--name=<region>]` | Get Project ID / domain ID (global service, hcloud auto-resolves domain ID with valid credentials) |
| RMS | KooCLI: `hcloud RMS ListAllResources --cli-region=cn-north-4 --cli-domain-id=<domain_id> [--region_id=<region>] [--type=hcss.l-instance]` | Query resources (global service: always use unified cn-north-4 endpoint, filter by target region via `region_id` param) |
| COC | https://coc.myhuaweicloud.com/v1/job/scripts/{script_uuid} | Remote script execution (global service: SDK client always uses cn-north-4 endpoint, each target instance's region is carried in the request body) |
**Supported Regions**: cn-north-4 (North Beijing 4), cn-east-3 (East Shanghai 1), cn-south-1 (South Guangzhou), cn-southwest-2 (Southwest Guiyang 1)
**System Image & Charging Mode**: Only **Ubuntu 24.04 LTS** is supported — a different requested image (e.g. CentOS) is rejected with a clear message, never silently replaced. Instances are **包年包月 (prePaid)** only — the HCSS CreateFlexusL API (POST `/v1/light-instances`) does not support `postPaid` (按需), and passing it returns HTTP 400 (`chargingMode illegal, periodNum/periodType must not be null`); any request for on-demand billing is rejected with a clear message. The mandatory period fields (`period_type`/`period_num`) are always included.
---
## Output Standards
### Success Output Template
```
============================================================
JiuwenSwarm COC Deployment - Complete
============================================================
Target Instance:
Name: {instance_name}
ID: {instance_id}
IP: {public_ip}
COC Execution:
Execute UUID: {execute_uuid}
Status: FINISHED
Deployment Result:
Web Access: http://{public_ip}:5173
Port Binding: 0.0.0.0:5173 (verified)
Submit Time: {submit_time}
NOTE: Huawei Cloud security group must allow inbound TCP 5173
for external web access. Configure at:
https://console.huaweicloud.com/smb/?/resource/list
============================================================
[SUCCESS] Deployment task completed!
============================================================
```
### Error Output Template
```
============================================================
[ERROR] Deployment Failed
============================================================
Error: {error_message}
Suggestions:
1. Check Huawei Cloud credentials
2. Verify instance status
3. Check deployment logs
============================================================
```
---
## 参考文档
The following reference documents provide detailed information for this skill:
| Document | Description |
|----------|-------------|
| [references/api-specs.md](references/api-specs.md) | API specifications for Huawei Cloud services (Flexus L, IAM, RMS, COC) |
| [references/iam-policies.md](references/iam-policies.md) | IAM permission policies and policy JSON for deployment |
| [references/deployment-checklist.md](references/deployment-checklist.md) | Pre/post deployment checklist for all phases |
| [references/verification-method.md](references/verification-method.md) | Verification methods and acceptance testing procedures |
| [references/acceptance-criteria.md](references/acceptance-criteria.md) | Acceptance criteria and sign-off requirements |
| [references/troubleshooting.md](references/troubleshooting.md) | Troubleshooting guide for common deployment issues |
| [references/existing-instance-deploy-and-resource-cleanup.md](references/existing-instance-deploy-and-resource-cleanup.md) | Deploy on an existing instance and resource cleanup / release guide |
© huaweicloud · MIT · huaweicloud/huaweicloud-skills