• User-friendly: Maintain a professional and friendly tone, using respectful language when addressing users
• Transparent operation: All key configuration information must be displayed to users and confirmed
• Security first: Follow the principle of least privilege to avoid accidental operations
• Error handling: Provide clear error messages and solutions
• Format specification: Use simple, clear, and easy-to-read output formats

• Step1: Preload Configuration
• Step2: Precondition Check
• Step3: Job Management Execution
• Step4: Job Task Execution Result Output

[MUST] Must first attempt to read the

./jobconfig/pre-config.json

file, strictly prohibited to skip this check step.

• File exists and read successfully: Load the parameter values, prompt the user that the pre-configuration has been loaded and display a summary of key parameters, then proceed to Step 2.
• File does not exist: Prompt the user that no pre-configuration file is detected, necessary parameters will be obtained through interaction in Step 2, then proceed to Step 2.
• File exists but read/parsing failed (such as JSON format error, insufficient permissions, etc.): Report specific error information to the user, ask whether to continue (skip pre-configuration and enter Step 2) or abort execution.

1. Alibaba Cloud CLI Configuration: Verify that CLI is installed and AccessKey is configured
   • CLI version requirement >= 3.3.3: Run

     aliyun version

     to verify version >= 3.3.3. If not installed or version is too low, refer to the installation instructions in references/aliyun-cli.md for installation or update.
   • [MUST] Run

     aliyun configure set --auto-plugin-install true

     to enable automatic plugin installation.
   • [MUST] Run

     aliyun plugin update

     to ensure installed plugins are always up to date.
   • If no configuration is found, guide users to install and configure interactively
   • Reference: references/aliyun-cli.md
   • [MUST] CLI User-Agent — Each

     aliyun

     CLI command call must include:

     --user-agent AlibabaCloud-Agent-Skills/alibabacloud-ehpc-instant-job-skill

   • Enable Alibaba Cloud CLI AI Mode: Run the following initialization commands to attach AI identity information for this Skill execution:

   bash

   aliyun configure ai-mode enable
   aliyun configure ai-mode set-user-agent --user-agent "AlibabaCloud-Agent-Skills/alibabacloud-ehpc-instant-job-skill"
   aliyun plugin update

   Alibaba Cloud CLI provides AI Mode. After enabling it, the CLI will automatically attach AI identity information, allowing the server to identify and optimize the Agent call chain. [MUST] Disable AI Mode at every exit point — Before delivering the final response for any reason, be sure to disable AI Mode first. This applies to all exit paths: workflow success, workflow failure, error/exception, user cancellation, session end, or any scenario where no more CLI commands will be executed. AI Mode is only used for Agent Skill invocation scenarios, and must remain disabled after the skill stops running.

   bash

   aliyun configure ai-mode disable

2. Region Information: Obtain the user-specified region or use the default region

   cn-shanghai

3. Permission Verification: Ensure the AccessKey has permissions related to E-HPC Instant

1. Image Preparation: Container/VM image has been added to the E-HPC Instant platform
   • If no image exists, guide users to add it interactively
   • Reference: references/instant-image.md
2. Network Configuration: vSwitch has been created and is available
   • If no vSwitch exists, guide users to create it interactively
   • Reference: references/vswitch.md
3. Storage Configuration: NAS mount path is prepared (if needed)
   • If NAS is required, guide users to configure it interactively
   • Reference: references/storage.md
4. Computing Resource Configuration: Cores/Memory or InstanceType specifications have been specified
   • Guide users to select appropriate resource configurations
   • Reference: references/resource.md
5. Execution Command: Job execution command line has been specified
   • Ensure the command format is correct (especially JSON array format)
   • Reference: references/job-command.md

1. Container Job

aliyun ehpcinstant CreateJob \
    --region cn-shanghai \
    --JobName 'container-job' \
    --Tasks '[{
        "TaskSpec": {
            "TaskExecutor": [{
                "Container": {
                    "Image": "registry.cn-shanghai.aliyuncs.com/registry/image:tag",
                    "Command": "[\"/bin/sh\", \"-c\", \"python /app/main.py\"]"
                }
            }],
            "Resource": {
                "Cores": 2,
                "Memory": 4,
                "Disks": [{"Type":"System","Size":40}]
            },
	    "VolumeMount": [
              {
                "MountPath": "/mnt",
                "VolumeDriver": "alicloud/nas",
                "MountOptions": "{\"server\":\"xxx.cn-shanghai.nas.aliyuncs.com\",\"vers\":\"3\",\"path\":\"/\",\"options\":\"nolock,tcp,noresvport\"}"
              }
            ],
        },
        "ExecutorPolicy": {"MaxCount": 1}
    }]' \
    --DeploymentPolicy '{"Network":{"Vswitch":["vsw-xxxx"]},"AllocationSpec":"Standard"}' \
    --user-agent AlibabaCloud-Agent-Skills/alibabacloud-ehpc-instant-job-skill

1. VM Job

aliyun ehpcinstant CreateJob \
    --region cn-shanghai \
    --JobName 'longrunning-job' \
    --JobDescription 'Long-running VM job' \
    --Tasks '[{
        "TaskSpec": {
            "TaskExecutor": [{
                "VM": {
                    "Image": "m-xxxx",
                    "Script": "base64_encoded_script"
                }
            }],
            "Resource": {
                "Disks": [{"Type":"System","Size":50}],
                "InstanceTypes": ["ecs.c6.xlarge"],
                "Cores": 4,
                "Memory": 8
            },
	    "VolumeMount": [
              {
                "MountPath": "/mnt",
                "VolumeDriver": "alicloud/nas",
                "MountOptions": "{\"server\":\"xxx.cn-shanghai.nas.aliyuncs.com\",\"vers\":\"3\",\"path\":\"/\",\"options\":\"nolock,tcp,noresvport\"}"
              }
            ],
        },
        "ExecutorPolicy": {"MaxCount": 1}
    }]' \
    --DeploymentPolicy '{"Network":{"Vswitch":["vsw-xxxx"]},"AllocationSpec":"Standard"}' \
    --user-agent AlibabaCloud-Agent-Skills/alibabacloud-ehpc-instant-job-skill

• Format and output execution results
• Provide follow-up operation suggestions (such as monitoring, log viewing, etc.)
• Record key information for future reference

/home/admin/.openclaw/workspace/skills/ehpcinstant-job-skill/scripts/

• create_container_job.sh

  - Create container job

• create_vm_job_batch.sh

  - Create VM job

• create_vm_job_longrunning.sh

  - Create long-running VM job

• list_jobs.sh

  - List jobs (supports pagination)

• get_job.sh

  - Get job details

• delete_jobs.sh

  - Delete jobs

• Corresponding Python SDK version scripts are located in the

  scripts/sdk/

  directory

• create_container_job.py

  - Create container job

• create_vm_job_batch.py

  - Create VM job

• create_vm_job_longrunning.py

  - Create long-running VM job

• list_jobs.py

  - List jobs (supports pagination)

• get_job.py

  - Get job details

• delete_jobs.py

  - Delete jobs

1. CLI Command Accuracy: E-HPC Instant uses the

   aliyun ehpcinstant

   command, not

   aliyun ehpc

   !
2. Region Consistency: All resources must be in the same region; cross-region operations will fail
3. Quota Limits: Pay attention to account quota limits to avoid operation failures
4. Cost Awareness: Job running incurs fees, clean up unnecessary resources in a timely manner
5. Least Privilege: Configure AccessKey with minimal necessary permissions to improve security

1. Naming Conventions:
   • Job name:

     Application-Case-Timestamp

     (e.g.:

     prod-training-20260411

     )
   • Resource name: Include purpose, environment, and region information
2. Resource Configuration Optimization:
   • Select appropriate instance specifications based on application characteristics
   • Avoid over-provisioning to prevent resource waste
3. Cost Control:
   • Clean up completed jobs in a timely manner
   • Use appropriate job timeout settings
   • Monitor resource usage
4. Reliability Assurance:
   • Implement job status monitoring and retry mechanisms
   • Configure appropriate error handling and alerts
   • Regularly back up important configurations and data
5. Security Enhancement:
   • Use private image repositories
   • Configure AccessKey with minimal permissions
   • Enable network access control and encryption

• references/ehpcinstant.md - E-HPC Instant Complete CLI Command Manual
• CLI help command:

  aliyun ehpcinstant <ApiName> --help

• references/aliyun-cli.md - Alibaba Cloud CLI Configuration Guide
• references/instant-image.md - Image Management Guide
• references/vswitch.md - Network vSwitch Management Guide
• references/storage.md - NAS Storage Management Guide
• references/resource.md - Computing Resource Configuration Guide
• references/job-command.md - Job Command Configuration Guide

• Alibaba Cloud E-HPC Instant Product Documentation: https://help.aliyun.com/product/ehpcinstant.html
• E-HPC Instant API Documentation: https://api.aliyun.com/document/EhpcInstant/2023-07-01/overview
• Alibaba Cloud CLI Official Documentation: https://help.aliyun.com/document_detail/121529.html

[MUST] Prohibit Skipping API Calls — When the Agent performs operations such as deletion, it must not skip the actual API call based on query results (such as GetJob returning NotFound) and self-judge "no operation needed". There is a time window between query and change, and the server status may have changed. The Agent must always execute the target API requested by the user (such as DeleteJobs), and the server returns the authoritative final result.

• ✅ Region Consistency: Ensure all resources are in the same region
• ✅ Quota Check: Verify sufficient resource quota
• ✅ Dependency Verification: Confirm dependent resources (image, network, storage) exist and are available
• ✅ Permission Verification: Ensure AccessKey has necessary permissions
• ✅ Cost Reminder: Provide reminders for operations that may incur high fees

1. Information Summary: Display all key configuration parameters
2. Impact Description: Explain the scope of impact and potential risks of the operation
3. User Confirmation: Wait for explicit user confirmation ("Yes", "Confirm", "Continue", etc.)
4. Execute Operation: Execute the confirmed operation
5. Result Feedback: Provide detailed operation results and follow-up suggestions