Turborepo

Step 2: Identify task type from user request

Analyze $ARGUMENTS to determine:

• Topic: configuration, caching, filtering, environment, CI, or CLI
• Task type: new setup, debugging, optimization, or implementation

Use decision trees in SKILL.md to select the relevant reference files.

Step 3: Read relevant reference files

Based on task type, read from references/<topic>/:

Step 4: Execute task

Apply Turborepo-specific patterns from references to complete the user’s request.

CRITICAL - When creating tasks/scripts/pipelines:

1. Prefer package tasks over Root Tasks. Root Tasks (//#taskname) are only for tasks that truly cannot exist in packages, such as Vitest Projects’ //#test, repo-wide release scripts, or tooling that does not invoke turbo itself.
2. Add scripts to each relevant package’s package.json (e.g., apps/web/package.json, packages/ui/package.json)
3. Register the task in root turbo.json
4. Root package.json only contains turbo run <task> - never actual task logic, unless defining a valid Root Task exception

Other things to verify:

• outputs defined for cacheable tasks
• dependsOn uses correct syntax (^task vs task)
• Environment variables in env key
• .env files in inputs if used
• Use turbo run (not turbo) in package.json and CI

Step 5: Summarize