github-featured/triggerdotdev--trigger.dev
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

docs(skills): reflect the SDK-bundled, version-pinned agent reference (#3939)

Browse Source 
## Summary

The agent skills' deep guidance now ships inside `@trigger.dev/sdk` and
is read from `node_modules`, so it tracks the `@trigger.dev/sdk` version
installed in your project automatically. This updates the Skills page,
the Building with AI step, and the rules-redirect page to drop the old
"pinned to the CLI version, re-run to refresh" framing and describe the
version-pinned reference instead.

Pairs with the SDK/CLI change in #3937. Keep this draft until that
ships, since it describes behavior that is not released yet.
This commit is contained in:
Eric Allam
2026-06-16 18:44:58 +01:00
committed by GitHub
parent 07a0e4ade9
commit e829eddd5e
3 changed files with 6 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/building-with-ai.mdx
+1 -1
View File
@@ -22,7 +22,7 @@ We provide multiple tools to help AI coding assistants write correct Trigger.dev
</Step>
<Step title="Install Skills">
Portable instruction sets that teach any AI coding assistant Trigger.dev best practices: writing tasks, realtime frontends, and `chat.agent` AI agents. They ship with the CLI, versioned with it, and install into Claude Code, Cursor, VS Code (Copilot), and AGENTS-compatible tools such as Codex via `.agents/skills/`.
Portable instruction sets that teach any AI coding assistant Trigger.dev best practices: writing tasks, realtime frontends, and `chat.agent` AI agents. They install with the CLI into Claude Code, Cursor, VS Code (Copilot), and AGENTS-compatible tools such as Codex via `.agents/skills/`, and draw their API guidance from a version-pinned reference shipped in `@trigger.dev/sdk`.
```bash
npx trigger.dev@latest skills
docs/mcp-agent-rules.mdx
+1 -1
View File
@@ -11,7 +11,7 @@ sidebarTitle: "Agent rules"
## 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 That has been replaced by [agent skills](/skills): `SKILL.md` directories in the open [Agent Skills standard](https://agentskills.io) that ship inside the CLI, versioned with it, and load on demand instead of always sitting in your context.
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](/skills): `SKILL.md` directories in the open [Agent Skills standard](https://agentskills.io) 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:
docs/skills.mdx
+4 -9
View File
@@ -18,22 +18,17 @@ Each skill is a directory containing a `SKILL.md` file: YAML frontmatter (name,
## Installation
The skills ship inside the `trigger.dev` CLI and are versioned with it. Run:
Run the installer with the CLI:
```bash
npx trigger.dev@latest skills
```
The CLI detects your installed AI tools, lets you pick which skills to install, and copies each one into that tool's native skills directory (`.claude/skills/`, `.cursor/skills/`, `.github/skills/`, `.agents/skills/`). It also writes a one-line pointer into 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.
The CLI detects your installed AI tools, lets you pick which skills to install, and writes each one into that tool's native skills directory (`.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.
<Note>
Because the skills are bundled with the CLI, the guidance your assistant gets is pinned to the CLI
version that installs them. To keep it matched to the Trigger.dev version you are building
against, run the CLI pinned in your project (`pnpm exec trigger skills`) instead of
`npx trigger.dev@latest`.
</Note>
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 `getting-started` skill is self-contained, since it runs before the SDK is installed.
### Non-interactive install
@@ -69,7 +64,7 @@ Using a tool that does not support skills yet? Select "Unsupported target" in th
## Keeping skills updated
Skills are pinned to your installed CLI version. To refresh them after upgrading Trigger.dev, run `npx trigger.dev@latest skills` again, or accept the prompt that `trigger dev` shows when a newer version is available. Re-running overwrites the installed skill files in place without creating duplicates.
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