Skip to content
Back to skills

preset-cortex-agents

ASecurity

Use Snowflake Cortex Agent REST and SQL APIs for listing, describing, creating, updating, deleting, running agents, streaming responses, and SQL wrappers. Use only for direct API workflows; Do not use for MCP-only work.

  • 13 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added June 5, 2026
ai-agentssqlapidatabase

Works with

  • api
  • mcp

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned October 6, 2026

npx -y skills add preset-io/agent-skills --skill preset-cortex-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of preset-cortex-agents?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for preset-cortex-agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/preset-io-preset-cortex-agents/badge)](https://www.skillsdirectory.com/skills/preset-io-preset-cortex-agents)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: preset-cortex-agents
description: Use Snowflake Cortex Agent REST and SQL APIs for listing, describing, creating, updating, deleting, running agents, streaming responses, and SQL wrappers. Use only for direct API workflows; Do not use for MCP-only work.
---

# preset-cortex-agents

Use for Snowflake Cortex Agent object management and run workflows.

## Always

- Account, auth, role, warehouse, database/schema, privilege, and safety context comes from `preset-snowflake-cortex`; consult it when that context is missing.
- Prefer read-only list/describe before mutations.
- Require confirmation of query, role, tools, budget, and output handling before any run.
- Require rollback planning before create, update, replace, or delete.
- Treat streamed events as sensitive; store redacted summaries unless raw output handling is approved.
- Do not rely on pre-2025 Cortex Agent schemas.

## Decision Rules

- Distinguish list and describe from run, create, update, and drop operations.
- Require approval for data-returning agent runs and mutations.
- Preserve streaming output handling and redaction.
- Require AUTOCOMMIT for SQL DDL workflows.

## Workflow Order

1. Verify Snowflake Cortex account, auth, role, warehouse, database, schema, and privilege context.
2. List or describe agents first.
3. Prepare run or mutation approval summary with tools, query, budget, and output handling.
4. Stop before run, create, update, replace, or drop until approved.

## Retrieve

- Object-based or ad hoc `agent:run`: [references/agent-runs.md](references/agent-runs.md)
- List/describe/create/update/delete agents: [references/agent-management.md](references/agent-management.md)
- SQL create/alter/show/describe/drop: [references/sql-agent-ddl.md](references/sql-agent-ddl.md)
- `SNOWFLAKE.CORTEX.DATA_AGENT_RUN` SQL wrapper: [references/sql-wrapper.md](references/sql-wrapper.md)
- Safety and approval checklist: load `preset-snowflake-cortex` and then `references/cortex-safety.md`.

Files in this skill

  • SKILL.md1.9 KB
  • references/agent-management.md1.7 KB
  • references/agent-runs.md4.5 KB
  • references/sql-agent-ddl.md2 KB
  • references/sql-wrapper.md2.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.