Agent rules

<Note> Agent rules are now **agent skills**. The standalone rule files have been replaced by skills that work across every major AI assistant from a single install. See [Skills](/skills). </Note>

What changed

Trigger.dev used to install per-tool rule files (.cursor/rules/trigger.*.mdc, regions in CLAUDE.md, and so on) fetched from GitHub. That has been replaced by agent skills: SKILL.md directories in the open Agent Skills standard that install with the CLI, draw their API guidance from a version-pinned reference in @trigger.dev/sdk, and load on demand instead of always sitting in your context.

The install command is the same, and now installs skills:

npx trigger.dev@latest install-rules still works as an alias for skills, and trigger dev offers to install the skills on first run.

The old task and realtime guidance now lives in the trigger-authoring-tasks and trigger-realtime-and-frontend skills, alongside two new skills for building chat.agent AI agents. See Skills for the full list and supported assistants.

Next steps

<CardGroup cols={2}> <Card title="Skills" icon="wand-magic-sparkles" href="/skills"> Install Trigger.dev agent skills into your AI coding assistant. </Card> <Card title="MCP Server" icon="sparkles" href="/mcp-introduction"> Give your AI assistant direct access to Trigger.dev tools and APIs. </Card> <Card title="Building with AI" icon="layer-group" href="/building-with-ai"> See how skills and the MCP server compare. </Card> <Card title="Writing tasks" icon="code" href="/tasks/overview"> Learn the task patterns that skills teach your AI assistant. </Card> </CardGroup>