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-9/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 scattered AI assets and the difficulty of performing unified inventory in Snowflake environments. In practice, operations and data analytics teams often need visibility into the usage of AI-related resources such as Cortex, Snowpark, Streamlit, and MCP, but manual queries are time-consuming, labor-intensive, and prone to omissions. This tool automatically discovers these assets and outputs a JSON inventory compliant with the agent-bom specification, providing structured data for subsequent auditing, cost analysis, and resource management.
Usage is straightforward: simply install agent-bom locally and configure Snowflake read-only credentials (SSO, OAuth, or key pair authentication is recommended). You can then trigger the discovery process using natural language instructions, such as "Inventory all Cortex and Streamlit assets in the current Snowflake environment." It automatically connects to your Snowflake account, executes read-only queries, writes the results to a JSON file you specify, and supports subsequent scans or pushes. The entire process does not require handing long-term credentials to any third-party service.
It is ideal for teams or individuals managing Snowflake AI infrastructure, especially organizations already using Cortex, Snowpark, or Streamlit to build AI applications and seeking to regularly generate asset inventories for compliance audits or cost optimization. Operations engineers can quickly gain a comprehensive view of the environment, while data analysts can use the inventory for resource planning.
It is recommended to use this tool uniformly after any major changes to the Snowflake environment. Note that it primarily relies on read-only permissions and will not modify any Snowflake resources. It requires a Python 3.11+ environment and ensures the agent-bom snowflake extension is installed. Before first use, configure your Snowflake account, user, and authentication method.
Key Features
Compared to native Snowflake INFORMATION_SCHEMA queries, this Skill automatically discovers AI-specific assets like Cortex, Streamlit, and MCP and generates agent-bom standard JSON, eliminating the need for manual complex SQL writing. Additionally, it does not store long-term credentials, with all operations performed locally for enhanced security.
Limitations
Requires Python 3.11+, the agent-bom snowflake extension installed, and only supports read-only Snowflake credentials (SSO/OAuth/key pair). Direct password interaction is not supported.
FAQ
How do I configure Snowflake read-only credentials?
It is recommended to set the SNOWFLAKE_PRIVATE_KEY_PATH or SNOWFLAKE_AUTHENTICATOR environment variables to avoid using passwords. You can also specify them via the ~/.snowflake/connections.toml configuration file.
What scenarios can the generated JSON inventory be used for?
It can be used for asset auditing, cost analysis, compliance reporting, or as input for other tools within the agent-bom ecosystem (such as scanning or pushing).
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-9/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-9/raw/index.md