Skip to main content
skill CX Codex

add · vercel — Claude Code skill: what it does, how to install

This Claude Code skill adds Turborepo to an existing repository. It configures selected tasks and checks them against the repository’s current commands.

MIT 163 installs ★ 31,386 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add vercel/turborepo --skill add -a claude-code
Open on GitHub

What add does

The skill sets up Turborepo for selected tasks while preserving existing commands. It examines manifests, workspace settings, lockfiles, scripts, and CI, then creates a root turbo.json and installs turbo according to the guide for the repository’s toolchain.

Only tasks with clear behavior are configured; deploy and end-to-end tasks stay out unless requested. The skill checks task selection with turbo run <task> --dry, then compares package coverage, ordering, exit status, and outputs with the existing commands. It stops without editing if the Git checkout has uncommitted changes or task behavior cannot be inferred.

Dependencies are installed in frozen or immutable mode. Lockfiles must be regenerated by their owning tool, never edited by hand. If documentation for the installed version cannot be verified, the skill stops rather than relying on remembered syntax.

What it helps with

  • add Turborepo to an existing repository
  • configure selected tasks across workspace packages
  • preserve existing commands while checking their equivalents
  • compare task order and package coverage

Example prompts for the agent

  • Add Turborepo to this repository and configure its existing build tasks.
  • Set up Turborepo for lint and type-check without replacing the root commands.
  • Compare the current test command with its turbo run version.

How to install add

1Skills CLI (Vercel)

npx skills add vercel/turborepo --skill add -a claude-code

2Manually: put the files in place

~/.claude/skills/add/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/add/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about add

How do I install add in Claude Code?

Run npx skills add vercel/turborepo --skill add -a claude-code. The skill file is installed at ~/.claude/skills/add/SKILL.md.

What does add do?

It integrates Turborepo into an existing repository and configures selected tasks. It then compares Turborepo runs with the commands already in use.

How does add validate a Turborepo setup?

It checks the plan with turbo run <task> --dry, then runs both the existing command and its Turborepo equivalent. It compares package coverage, task order, exit status, and outputs.

Source text

SKILL.md · MIT
---
name: add
description: Add Turborepo to an existing repository in any toolchain Turborepo supports. Use when asked to add, introduce, or set up Turborepo or turbo in a repository that does not use it yet.
---

# Add Turborepo

Add Turborepo to an existing repository for selected tasks, without changing what existing commands do. In workspace repositories, configure workspace package tasks. In single-package repositories, configure root tasks.

## Documentation

Read these before changing files, and treat them as the source of truth for configuration syntax and toolchain prerequisites:

- [Add to an existing repository](https://turborepo.dev/docs/getting-started/add-to-existing-repository)
- [Configuring tasks](https://turborepo.dev/docs/crafting-your-repository/configuring-tasks)
- [Configuration reference](https://turborepo.dev/docs/reference/configuration)
- [Package configurations](https://turborepo.dev/docs/reference/package-configurations), if package-level overrides are needed
- The guide for each toolchain in use, such as [Rust](https://turborepo.dev/docs/guides/tools/rust), [Python](https://turborepo.dev/docs/guides/tools/python), or [Go](https://turborepo.dev/docs/guides/tools/go)

Once `turbo` is installed, prefer its bundled `docs/README.md`, which matches the installed version. If you cannot verify the docs, stop instead of relying on remembered syntax.

## When to stop

Stop and explain why, leaving the repository unchanged, if:

- the Git checkout has uncommitted changes;
- Turborepo cannot discover packages from the repository's existing manifests;
- adding Turborepo would require a new toolchain, package manager, or manifest type, or would require moving packages;
- one toolchain has conflicting lockfiles;
- you cannot tell from the repository and CI how any selected task is ordered, what it outputs, or what environment it needs.

## Workflow

### 1. Analyze

Read the manifests, workspace definition, lockfiles, root scripts or task-runner targets, package dependency relationships, and CI configuration. Summarize the toolchains, layout, candidate tasks, observed dependencies, outputs, environment variables, and anything you could not infer.

A direct request to add Turborepo is enough to proceed. Ask first only if the request is ambiguous or would widen the scope below.

### 2. Choose tasks

Configure only tasks whose behavior is clear, preferring lint, type-check, format-check, unit-test, and build tasks that the repository already runs.

Do not:

- rename or move packages, or change toolchains, package managers, or workspace membership;
- rewrite package-level task commands;
- add Remote Caching;
- configure deploy, end-to-end, integration, or environment-provisioning tasks unless asked.

Keep existing root entry points. Give the `turbo` version of a root orchestrator its own name following the repository's convention, such as `<task>:turbo`. Replace the original only if the `turbo` command is proven equivalent.

### 3. Add Turborepo

Install `turbo` as the toolchain's guide describes. If the repository pins its tool versions, pin `turbo` to an exact version the same way. Regenerate lockfiles with the tool that owns them. Never edit a lockfile by hand.

Add any prerequisites from the toolchain guide that are missing, such as a workspace name or toolchain declaration. Take versions from the lockfile or the toolchain's own command instead of guessing.

Create a root `turbo.json` for the selected tasks only:

- Enable only the toolchain support those tasks need, including any required `futureFlags`. Tell the user if that support is experimental.
- Add `dependsOn`, `inputs`, `outputs`, and environment variables only when the repository shows they are needed.
- If you add custom `inputs`, include `"$TURBO_DEFAULT$"`. Reference root files outside a package with `"$TURBO_ROOT$/<path>"`.
- Disable caching for side-effecting tasks and for tasks whose outputs cannot be captured.

Toolchain support can register built-in tasks you did not select. Report them as deferred, not validated.

Add the dependency directory and `.turbo` to `.gitignore` if they are missing. Do not change any other ignore rules.

### 4. Validate

Install dependencies in frozen or immutable mode. Then check a `turbo run <task> --dry` output for each task:

- Only the intended packages and tasks are selected, and no package that defines a task is missing.
- Task ordering matches what the repository does today.
- For tasks with shared root inputs: run once, confirm a cache hit on the second run, change one root input, confirm a cache miss, then revert the change.

Then run each existing command and its `turbo` equivalent, and compare package coverage, ordering, exit status, and outputs. A passing `turbo` run alone does not prove equivalence. If behavior differs, narrow the configuration or stop. Never delete the old command to hide a difference.

### 5. Report

Summarize:

- the configured tasks and package coverage;
- preserved commands and any replaced root entry points;
- inferred dependencies, inputs, outputs, and environment variables;
- validation results comparing existing and `turbo` commands;
- deferred or unsupported tasks.

Commit, push, or open a pull request only if the user asks. Open it as a draft.

## When another skill calls this one

Work in the caller's branch, do not open a pull request, and return the diff, validation results, and deferred tasks to the caller. If the change would need to go beyond the selected tasks, stop instead of widening the scope.

© vercel · MIT · vercel/turborepo

Similar skills

SKILL.md skills catalog →

add by other authors comes first.

add Remocn add installs individual remocn components into a Remotion project via shadcn CLI and inserts them into Sequences with proper frame timing. CX Codex +1 478installs add-analytics-instrumentation amplitude add-analytics-instrumentation runs an end-to-end analytics workflow across PRs, branches, or files to detect trackable user actions and generate a ready-to-use tracking plan. CX Codex +1 66,000installs convex-add convex convex-add adds hosting or another backend capability to the current Convex app. Use it when you want an agent to locate and wire a requested component. CX Codex +1 43,900installs flutter-add-widget-test flutter flutter-add-widget-test is a Claude Code skill for writing Flutter widget tests that check rendered UI and user actions. It activates when a specific widget needs validation. CX Codex +1 42,900installs flutter-add-integration-test flutter flutter-add-integration-test is a Claude Code skill that sets up Flutter integration tests and turns MCP interactions into test cases. It activates for UI exploration and user-flow automation. CX Codex +1 41,500installs dart-add-unit-test dart-lang dart-add-unit-test is a skill for Claude Code, Codex, and other agents that writes and structures package:test unit tests. It activates when adding logic or fixing bugs to prevent regressions. CX Codex +1 21,400installs principle-subtract-before-you-add backnotprop principle-subtract-before-you-add — a development skill that enforces removing dead code, stubs, and unused validators before writing new features or refactoring. CX Codex +1 10,200installs

From the same set2

Project sponsors

Companies that keep this analytics open