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.
Scanned 6/5/2026
Install via CLI
openskills install preset-io/agent-skills---
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
- Use `preset-snowflake-cortex` first for account, auth, role, warehouse, database/schema, privileges, and safety context.
- 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`.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.