What are agent skills?
Skills are portable instruction sets that teach AI coding assistants how to use Trigger.dev effectively. Unlike vendor-specific config files (.cursor/rules, CLAUDE.md), skills use an open standard that works across all major AI assistants, so Cursor users and Claude Code users get the same knowledge from a single install.
Each skill is a directory containing a SKILL.md file: YAML frontmatter (name, description) plus markdown instructions with patterns, examples, and common mistakes that AI assistants discover on demand and follow.
Skills pair with the MCP Server, which gives your assistant live access to
your project (deploy, trigger, monitor). Skills teach it how to write the code; the MCP server
lets it act on your project. See how they fit together.
Installation
Run the installer with the CLI:.claude/skills/, .cursor/skills/, .github/skills/, .agents/skills/). It also adds a one-line pointer to your primary instructions file (CLAUDE.md, .cursor/rules, etc.) so your assistant always knows the skills are there and loads the right one on demand.
When you run trigger dev for the first time, the CLI offers to install the skills for you.
The installed skills are lightweight. Most point to the full, version-pinned reference that ships inside @trigger.dev/sdk, which your assistant reads straight from node_modules. The API guidance it follows always matches the @trigger.dev/sdk version installed in your project, with no extra step on your part. The trigger-getting-started skill is self-contained, since it runs before the SDK is installed.
Non-interactive install
Pass--target to choose tools and -y to install every skill without prompting (useful in scripts and CI):
Available skills
| Skill | Use for | Covers |
|---|---|---|
trigger-authoring-tasks | Writing background and scheduled tasks | task/schemaTask, retries, queues, waits, idempotency, metadata, triggering, cron, trigger.config.ts |
trigger-realtime-and-frontend | Live run updates and triggering from the browser | runs.subscribeToRun, @trigger.dev/react-hooks, public access tokens, streams |
trigger-authoring-chat-agent | Building durable AI chat agents | chat.agent run loop, toStreamTextOptions, server actions, useChat transport, tools, lifecycle hooks |
trigger-chat-agent-advanced | Advanced chat.agent patterns | sessions, human-in-the-loop, sub-agents, compaction, fast starts, resilience, version upgrades |
trigger-cost-savings | Auditing and reducing compute spend | right-sizing machines, maxDuration, batch vs sequential, debounce, schedule frequency, MCP run analysis |
trigger-authoring-tasks; it covers the most common patterns for writing Trigger.dev tasks.
Supported AI assistants
Skills use the open Agent Skills standard. The CLI installs natively into the tools that support a skills directory today:| Assistant | Installs to |
|---|---|
| Claude Code | .claude/skills/ |
| Cursor | .cursor/skills/ |
| GitHub Copilot (VS Code) | .github/skills/ |
| Codex CLI, Jules, OpenCode | .agents/skills/ |
Keeping skills updated
The API guidance updates on its own: it lives in@trigger.dev/sdk and is read from node_modules, so upgrading the SDK in your project upgrades the guidance with it. Re-run npx trigger.dev@latest skills (or accept the prompt that trigger dev shows when a newer version is available) only to add skills or refresh the installed pointer files. Re-running overwrites them in place without creating duplicates.
Next steps
MCP Server
Give your AI assistant direct access to Trigger.dev tools and APIs.
Building with AI
See how skills and the MCP server compare, plus a copy-paste context snippet.
Writing tasks
Learn the task patterns that skills teach your AI assistant.
AI agents
Build durable chat agents with chat.agent, the focus of two of the skills.