Download for macOS
Skill

configure

@alation Updated 2026-09-30

Use when the user wants to create, modify, or manage AI agents, custom tools, LLM configurations, or data source connections. Triggers: create agent, configure agent, clone agent, publish agent as tool, export agent, import agent, share agent, create HTTP tool, create SMTP tool, add tool, configure LLM, bring your own model, BYOM, add data source, create connection, parameter bindings, tool authentication, set up agent, set up tool, manage LLM credentials. Key signal: if "set up" refers to infrastructure (agents, tools, LLMs, connections), use this skill. If "set up" refers to scheduling or automation, use automate. Not for scheduling or workflows — use automate. Not for creating data products — use curate.

Install

With your agent

Install OMGSkills skill "alation/alation-plugins:skills/configure" into this agent's normal skills directory: use the OMGSkills MCP get_skill tool, install only the pinned_install commit and path, verify SKILL.md against pinned_install.skill_md_sha, and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.

Manual command

git clone https://github.com/Alation/alation-plugins /tmp/alation-plugins && ln -s /tmp/alation-plugins/skills/configure ~/.claude/skills/configure

From README

Configure Create and manage agents, tools, LLMs, and data source connections. Routing | User Intent | CLI Command | When to Use | |---|---|---| | Manage AI agents | scripts/run-cli agent | Create, clone, update, delete, publish, export, import agents | | Manage tools | scripts/run-cli tool | Create HTTP/SMTP tools, update, delete | | Manage LLMs | scripts/run-cli llm | BYOM , credentials, LLM configs | | Manage data sources | scripts/run-cli datasource | Create, update, delete data source connections | Not This Skill User wants to schedule or automate workflows → use automate User wants to query data or chat with an agent → use ask User wants to create a data product → use curate User wants to browse data source contents → use explore Key distinction: configure creates and manages the infrastructure (agents, tools, LLMs, connections). automate uses that infrastructure in workflows. "Create an SMTP tool" is configure. "Set up a daily email report" is automate.