agent-bom discover snowflake
Discover Snowflake AI assets and generate a standardized inventory
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: agent-bom discover snowflake. It is used for: Discover Snowflake AI assets and generate a standardized inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-snowflake-x-7/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the challenge of unifying the inventory of enterprise AI infrastructure assets. In real-world operations, Snowflake environments can contain scattered resources such as Cortex AI services, Snowpark jobs, Notebooks, Streamlit applications, MCP endpoints, and various AI observability assets. Manual tracking is time-consuming and prone to omissions. This Skill automatically discovers these resources and outputs a standardized agent-bom inventory JSON, providing a unified data foundation for subsequent asset scanning, compliance audits, and cost analysis.
Usage is straightforward: ensure you have Python 3.11+ and the agent-bom library (with the snowflake extension) installed locally, and have operator-controlled Snowflake read-only credentials ready (SSO, OAuth, or key pair authentication is recommended). You can then trigger the discovery process via natural language instructions, such as "Please inventory the Cortex AI assets in my Snowflake account." The Skill connects to Snowflake to execute read-only queries, writes the discovered assets to a JSON file you specify, and stops at the discovery phase without modifying any Snowflake resources.
It is ideal for operations teams and data analysts who need unified management of Snowflake AI assets, especially organizations that have deployed multiple Cortex, Snowpark, or Streamlit projects but lack a global asset view. With this Skill, teams can quickly obtain an auditable, reusable asset inventory for capacity planning, security compliance checks, or migration assessments.
Before first use, it is recommended to verify the scope of the read-only role permissions for your Snowflake account to avoid incomplete discovery due to insufficient permissions. Note that the Skill primarily relies on the operator's local credential context; credentials are not passed to any external services, and all queries are executed locally. The generated JSON inventory should be scanned regularly and integrated with other tools in the agent-bom ecosystem for continuous asset governance.
Key Features
Unlike directly querying Snowflake system tables or manually exporting via Snowsight, this Skill outputs a standardized JSON inventory compliant with the agent-bom specification, which can be directly consumed by agent-bom scanning tools. The entire process does not expose long-term credentials to any third party, using only the operator's existing SSO/OAuth context.
Limitations
Requires Python 3.11+ and the agent-bom library with the snowflake extension installed. It only supports operator-controlled Snowflake read-only credentials (SSO, OAuth, or key pair) and does not support password-based authentication. The discovery scope is limited by the permissions granted to the read-only role.
FAQ
How do I install this Skill?
Run `pip install agent-bom[snowflake]` to install the dependencies, then invoke it via an AI assistant or run the Python script directly.
What Snowflake permissions are required?
The operator must provide a read-only role. SSO, OAuth, or key pair authentication is recommended; do not use passwords. Permissions should cover the databases, schemas, and Cortex-related objects to be discovered.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-bom-discover-snowflake-x-7/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover snowflake, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-snowflake-x-7/raw/index.md