Skip to main content

Skill

NineData-Skill is a set of capabilities for AI Agents and Vibe Coding tools. With Skill, an AI Agent can call NineData platform capabilities under NineData authentication, permission checks, SQL rule checks, data masking, throttling, and audit logging. Typical scenarios include listing data sources, executing SQL, and submitting SQL to an approval workflow.

What Skill Can Do​

  • SQL execution: Execute explicit SQL in a permitted data source context, or retrieve execution plans and related information.
  • SQL task: Submit SQL to a secure approval workflow for scenarios that require rule checks, approval, and audit.
  • Platform capability calls: Let AI Agents call NineData platform capabilities through OpenAPI, such as listing data sources, checking database status, or validating development data.
  • Security controls: Skill calls are governed by NineData account identity, organization permissions, SQL rules, data masking, throttling, and audit logs.

Prerequisites​

  • You are logged in to the NineData console.
  • Your account has permission to access the Skill page.
  • To execute SQL or submit SQL tasks through Skill, your account must have the required permissions on the target data source and DevOps workflow.

View Skill Capabilities​

  1. Log in to the NineData Console.

  2. In the left navigation pane, click Skill.

  3. On the NineData-Skill page, view the supported Skill capabilities.

    The page shows what NineData-Skill is used for and lists the feature name, description, and release time of each capability.

Page Actions​

On the upper-right corner of the NineData-Skill page, you can use the following actions:

ActionDescription
DescriptionView the NineData-Skill version, tool IDs, invocation method, OpenAPI endpoints, return fields, and usage boundaries.
DownloadDownload ninedata-skill.zip, which includes the Skill guide, sample configuration, client installation references, and scripts.
Quick setup guideView installation paths and validation prompts for Claude Code, Codex, Cursor, Hermes, OpenClaw, Trae, Qoder, Open Code, and other clients.

Download and Configure Skill​

  1. On the upper-right corner of the NineData-Skill page, click the download icon to download ninedata-skill.zip.

  2. Extract the package to get the ninedata-skill directory.

  3. Copy the complete ninedata-skill directory to the Skill directory of the target AI Agent client.

    ClientInstallation path example
    Claude Code~/.claude/skills/ninedata-skill/
    Codex~/.codex/skills/ninedata-skill/
    Cursor~/.cursor/skills/ninedata-skill/
    Hermes Agent~/.hermes/skills/ninedata-skill/
    OpenClaw~/.openclaw/skills/ninedata-skill/
    Trae~/.trae/skills/ninedata-skill/
    Qoder~/.qoder/skills/ninedata-skill/
    Open Code~/.opencode/skills/ninedata-skill/

  4. Edit config.json in the Skill root directory.

    {
      "endpoint": "https://your-ninedata-domain.example.com",
      "accessKeyId": "replace-with-access-key-id",
      "accessKeySecret": "replace-with-access-key-secret",
      "defaultDsId": "replace-with-default-datasource-id",
      "defaultDbName": "replace-with-default-database-name",
      "defaultSchemaName": "replace-with-default-schema-name",
      "source": "NINEDATA_SKILL",
      "defaultPageSize": 50,
      "defaultLanguage": "enus"
    }
    Configuration itemDescription
    endpointNineData console endpoint. For SaaS, use https://console.ninedata.cloud. For private deployment or Dedicated Cluster, use the actual console endpoint.
    accessKeyId, accessKeySecretNineData OpenAPI credentials. Keep them secure and do not write them into chats, logs, or repositories.
    defaultDsIdDefault data source ID. It is optional for listing data sources. SQL execution uses it when no data source is specified in command arguments.
    defaultDbNameDefault database name.
    defaultSchemaNameDefault schema name. Fill it in as required by the database type.
    sourceInvocation source. Keep NINEDATA_SKILL unless you have a specific reason to change it.
    defaultPageSizeDefault page size.
    defaultLanguageResponse language, such as enus.

  5. Set permissions for the configuration file.

    chmod 600 config.json

  6. Confirm that the client can execute scripts/*.sh in the Skill directory, then restart the client or start a new Agent session.

  7. Ask the Agent to use NineData Skill.

    Use ninedata-skill to list available MySQL data sources.

Validate Configuration​

After configuration, start a validation request in the AI Agent client.

Use ninedata-skill to list available MySQL data sources.

If the configuration is valid, the Agent queries data sources that are visible to the current OpenAPI credential and returns the data source list or the platform error message.

Query Data with Skill​

After Skill is configured, describe your query requirement in natural language in the AI Agent client. For example:

Use ninedata-skill to query the order count in the production MySQL data source.

The Agent should identify accessible data sources and show the full SQL that will be executed. Confirm the SQL, target data source, and query purpose before letting the Agent continue.

NineData returns the execution result or the next recommended action according to platform rules. Common outcomes include:

  • The query is executed and a result preview is returned.
  • Full SQL confirmation is required again.
  • The SQL is rejected by permission, rule, or safety policy.
  • The SQL must be handled through a SQL task or approval workflow.
  • Database execution fails, and an error message and request ID are returned.

Submit SQL Changes with Skill​

For SQL that changes data or schema, such as INSERT, UPDATE, DELETE, CREATE, ALTER, and DROP, the Agent should submit a NineData SQL task instead of executing it directly.

The typical workflow is:

  1. Describe the change requirement in the AI Agent client.

    Use ninedata-skill to submit a SQL task for adding a remark column to the orders table in the test database.

  2. The Agent shows the target data source, database, full SQL, and optional rollback SQL.

  3. After confirming the content, explicitly agree to submit the SQL task.

  4. NineData creates the SQL task and returns the task ID, rule check result, approval status, and console task link.

  5. Continue to submit for approval, wait for approval, or execute the task based on the task status.

For approval, execution, pause, resume, stop, cancel, reject, or approval transfer operations, the Agent should show the current task status and operation impact, and continue only after your explicit confirmation.

Recommendations​

  • Before letting an AI Agent call Skill, confirm that the target data source, SQL content, and account permissions are correct.
  • For SQL that changes data or schema, use the SQL task capability to submit the SQL to an approval workflow.
  • For read-only queries, execution plan retrieval, or development data validation, use the SQL execution capability according to your organization permissions and security rules.
  • Skill results can help an AI Agent make decisions, but production changes should still be reviewed together with approval, audit, and business impact.
  • Do not let the Agent connect directly to databases, and do not store database usernames or passwords in the Skill.
  • Do not expose accessKeySecret, cookies, tokens, signatures, or database credentials in chats, logs, or commits.
  • When the platform returns rejection, failure, confirmation required, SQL task required, or approval required, do not bypass the platform decision.
  • Approval actions such as approve, reject, and transfer-approval are high-risk operations. Run them only after the user explicitly confirms the exact action.