Huawei Cloud Flexus L Deploy Jiuwenswarm logo

Huawei Cloud Flexus L Deploy Jiuwenswarm

Organization
huaweicloud
huawei-cloud-flexus-l-deploy-jiuwenswarm

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.

Overview

Publisherhuaweicloud
Repositoryhuaweicloud-skills
Skill namehuawei-cloud-flexus-l-deploy-jiuwenswarm
Stars
59
Forks
24
Bundled files
21
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 21 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by huaweicloud on GitHub. Read the source before you install it.

Installation

Install the Huawei Cloud Flexus L Deploy Jiuwenswarm AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/huaweicloud/huaweicloud-skills/tree/master/skills/computing/flexus-l/huawei-cloud-flexus-l-deploy-jiuwenswarm
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skills.git /tmp/huaweicloud-skills
mkdir -p .claude/skills
cp -r /tmp/huaweicloud-skills/skills/computing/flexus-l/huawei-cloud-flexus-l-deploy-jiuwenswarm .claude/skills/huawei-cloud-flexus-l-deploy-jiuwenswarm
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Huawei Cloud Flexus L Deploy Jiuwenswarm in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Huawei Cloud Flexus L Deploy Jiuwenswarm on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Huawei Cloud Flexus L Deploy Jiuwenswarm is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

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)

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 for details.

StatusDescription
READYReady
PROCESSINGRunning, waiting required
FINISHEDCompleted successfully
ABNORMALExecution abnormal, failed
CANCELEDCanceled

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!

OperationConfirmation Required
Create new Flexus L instanceRequired
Deploy application on existing instanceRequired
Modify cloud resource configurationRequired

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
ParameterDescriptionDefault Value
--nameInstance namejiuwenSwarm-{timestamp}
--flavorInstance flavor (2c-4g-50g / 2c-4g-70g / 4c-8g-180g)2c-4g-50g
--regionRegion (cn-north-4/cn-east-3/cn-south-1/cn-southwest-2). If not specified, interactive selection will be shown.(Interactive)
--waitWait for creation completion (polls RMS every 30s for instance status)False
--timeoutMaximum time to wait in seconds when --wait is used600 (10 minutes)
--confirmSkip confirmation promptFalse
deploy_service.py
ParameterDescriptionDefault Value
--ipInstance public IPRequired
--waitWait for deployment completionTrue
--timeoutTimeout in seconds1800
config_model.py
ParameterDescription
--api-baseModel API URL
--api-keyModel API key
--model-nameModel name
--model-providerModel provider
--ipInstance public IP
--interactiveInteractive configuration
config_channel.py
ParameterDescription
--channelChannel type (xiaoyi/feishu/dingtalk)
--ipInstance public IP
--interactiveInteractive configuration
query_coc_status.py
ParameterDescriptionDefault Value
--uuid, -uCOC execution UUIDRequired
--from-file, -fRead UUID from JSON file-
--key, -kUUID key name in JSON fileexecute_uuid
--verbose, -vShow detailed outputFalse
--wait, -wWait for task completionFalse
--timeout, -tWait timeout in seconds1800
--interval, -iPolling interval in seconds60

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 VariablePurposeRequired Value
FRONTEND_HOSTFrontend HTTP bind0.0.0.0
FRONTEND_PORTFrontend HTTP port5173
WEB_HOSTWebChannel bind0.0.0.0
AGENT_SERVER_HOSTAgentServer bind0.0.0.0
GATEWAY_HOSTGateway bind0.0.0.0
Security Group Configuration (Cloud-side)
  1. Login to Flexus L Console
  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 VariableDescriptionRequired
HUAWEICLOUD_SDK_AKAccess Key (permanent or temporary)Yes
HUAWEICLOUD_SDK_SKSecret Key (permanent or temporary)Yes
HUAWEICLOUD_SDK_SECURITY_TOKENSecurity Token (STS only)No
HUAWEICLOUD_REGIONHuawei Cloud Region (default: cn-north-4)No

Reference: https://support.huaweicloud.com/iam_faq/iam_01_0620.html


Key API Endpoints

ServiceEndpointPurpose
Flexus Lhttps://hcss.{region}.myhuaweicloud.com/v1/light-instancesCreate/query instances
IAMKooCLI: hcloud IAM KeystoneListProjects --cli-region=<region> [--name=<region>]Get Project ID / domain ID (global service, hcloud auto-resolves domain ID with valid credentials)
RMSKooCLI: 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)
COChttps://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: Ubuntu 24.04 LTS


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:

DocumentDescription
references/api-specs.mdAPI specifications for Huawei Cloud services (Flexus L, IAM, RMS, COC)
references/iam-policies.mdIAM permission policies and policy JSON for deployment
references/deployment-checklist.mdPre/post deployment checklist for all phases
references/verification-method.mdVerification methods and acceptance testing procedures
references/acceptance-criteria.mdAcceptance criteria and sign-off requirements
references/troubleshooting.mdTroubleshooting guide for common deployment issues

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Huawei Cloud Flexus L Deploy Jiuwenswarm AI skill do?

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...

Why use Huawei Cloud Flexus L Deploy Jiuwenswarm on TypingMind?

Because you install it once and use it with any model. Huawei Cloud Flexus L Deploy Jiuwenswarm is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Huawei Cloud Flexus L Deploy Jiuwenswarm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huaweicloud/huaweicloud-skills/tree/master/skills/computing/flexus-l/huawei-cloud-flexus-l-deploy-jiuwenswarm. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Huawei Cloud Flexus L Deploy Jiuwenswarm?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Huawei Cloud Flexus L Deploy Jiuwenswarm?

As many as you like. As long as a model supports skills, you can use Huawei Cloud Flexus L Deploy Jiuwenswarm with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Huawei Cloud Flexus L Deploy Jiuwenswarm AI skill free?

Yes. It is published on GitHub by huaweicloud under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇