agent-bom discover snowflake
Discover Snowflake AI assets and generate 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 standardized inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-snowflake-x-5/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 inefficiency and risk of oversight in manually inventorying AI assets (such as Cortex, Snowpark, Streamlit, MCP, etc.) within Snowflake environments. In practice, data teams and AI engineers often need to understand what AI-related resources are deployed in Snowflake but lack standardized discovery and inventory tools.
Usage is straightforward: you simply configure read-only Snowflake credentials (SSO or key-pair authentication is recommended) and run the command specifying the account and output path. It automatically queries Snowflake metadata to discover Cortex, Snowpark, Notebook, Streamlit, MCP, and AI observability assets, generating a JSON inventory file compliant with the agent-bom specification. You can then scan or push this inventory without providing long-term credentials to the agent-bom service.
It is ideal for teams or individuals managing Snowflake AI infrastructure, especially organizations already using agent-bom for asset inventory management, enabling seamless integration. Data analysts, operations engineers, and agent developers can all benefit by quickly gaining a comprehensive view of their environment.
Before first use, ensure a Python 3.11+ environment and install the agent-bom snowflake extension. Note that it performs read-only operations and will not modify any Snowflake resources. Credentials should be passed via environment variables or configuration files to avoid exposing sensitive information in conversations.
Key Features
Unlike querying Snowflake's INFORMATION_SCHEMA directly, agent-bom-discover-snowflake outputs a standardized agent-bom inventory format, supporting subsequent scanning and auditing. It also enhances security by eliminating the need to expose long-term credentials to the agent-bom service.
Limitations
Requires Python 3.11+, depends on the agent-bom library's snowflake extension, supports only read-only Snowflake credentials (SSO/OAuth/key-pair authentication recommended; password authentication is not supported).
FAQ
What permissions are required?
Only read-only permissions for Snowflake are needed; SSO or key-pair authentication is recommended.
Will it modify my Snowflake data?
No, it performs only read-only queries and does not execute any write operations.
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-5/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-5/raw/index.md