Monorepo Navigator

# Create a "Monorepo Navigator" AI Skill

I want you to help me set up a reusable AI skill that I can use in future conversations. Read the complete skill definition below, then help me install it.

## Complete Skill Definition

# Monorepo Navigator

Navigate, manage, and optimize monorepos at any scale. Covers Turborepo, Nx, pnpm workspaces, and Lerna/Changesets for cross-package impact analysis, selective builds on affected packages only, dependency graph visualization, remote caching configuration, migration from multi-repo to monorepo with preserved git history, and coordinated package publishing with automated changelogs.

**Keywords:** monorepo, Turborepo, Nx, pnpm workspaces, Changesets, dependency graph, remote cache, affected packages, selective builds, cross-package impact, npm publishing, workspace protocol

## Core Capabilities

- **Impact analysis** — determine which apps break when a shared package changes, trace dependency chains, visualize Mermaid graphs, and calculate blast radius.
- **Selective execution** — run tests/builds only for affected packages, filter by changed files since a git ref, and skip unchanged packages in CI.
- **Build optimization** — remote caching (Turborepo/Vercel, Nx Cloud), incremental builds with input/output config, dependency-aware parallel scheduling, and artifact sharing.
- **Publishing** — Changesets for coordinated versioning, automated per-package changelogs, pre-release channels, and `workspace:*` replacement during publish.

## When to Use

- Multiple packages/apps share code (UI components, utils, types, API clients)
- Build times are slow because everything rebuilds on every change
- Migrating from multiple repos to a single monorepo
- Publishing npm packages with coordinated versioning
- Teams work across packages and need unified tooling

## Clarify First

Before analyzing or configuring, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

- **Tooling:** Turborepo, Nx, pnpm workspaces, or Changesets (drives the config and commands generated).
- **Task:** impact/dependency analysis, build optimization, or publishing setup (selects `dependency_graph.py` vs `impact_detector.py` vs `package_analyzer.py`).
- **Repo root & git ref:** the monorepo path and the baseline ref for "affected" detection (sets `--ref` and what counts as changed).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

## Tools Overview

| Tool | Purpose | Command |
|------|---------|---------|
| `dependency_graph.py` | Mermaid dependency graph of internal packages, optionally focused on one package | `python3 scripts/dependency_graph.py <root> --focus @repo/ui --direction dependents` |
| `impact_detector.py` | Packages affected (directly and transitively) by changed files | `python3 scripts/impact_detector.py <root> --ref origin/main --affected-only` |
| `package_analyzer.py` | Package inventory, internal and shared external dependencies, version drift, orphans | `python3 scripts/package_analyzer.py <root> --only-shared` |

Workspace detection order: `pnpm-workspace.yaml`, then the root `package.json` `workspaces` field (npm, Yarn), then `lerna.json`. **Exit codes:** 0 report; 2 no packages found or bad input (a directory that is not a workspace root must not look like an empty monorepo).

## Quick Start

```bash
# from engineering/monorepo-navigator/ (a four-package pnpm workspace)
python3 scripts/package_analyzer.py assets/sample_monorepo                    # 4 packages, 3 internal deps, date-fns drift
python3 scripts/impact_detector.py assets/sample_monorepo --files packages/utils/src/index.ts --affected-only
python3 scripts/dependency_graph.py assets/sample_monorepo --focus @acme/utils --direction dependents --mermaid-only
```

A change in `packages/utils` affects `@acme/ui`, `@acme/utils` and `@acme/web` (through `ui`), but not `@acme/docs`.

## Reference Documentation

Load the reference that matches the task — keep this file lean and pull detail on demand:

- **[references/tooling-and-configuration.md](references/tooling-and-configuration.md)** — tool selection decision matrix, recommended repo structure, full turbo.json and pnpm-workspace config, key Turborepo/pnpm commands, impact-analysis commands, remote-caching setup, affected-only CI workflow, Changesets publishing, and multi-repo→monorepo migration steps. Read when configuring or operating a monorepo.
- **[references/operations-and-best-practices.md](references/operations-and-best-practices.md)** — common pitfalls, best practices, troubleshooting table, and success criteria. Read when something misbehaves or when validating a setup.

## Anti-Patterns

**Mistake:** Running every test and build on every change.
**Why it matters:** CI time grows with the repo, not with the change, and teams start skipping checks.
**Instead:** Use the affected set from `impact_detector.py` (or the build tool's filter) and run the full suite on a schedule.

**Mistake:** Letting shared dependencies drift between packages.
**Why it matters:** Two versions of the same library ship twice, and bugs reproduce in one app but not another.
**Instead:** Check `package_analyzer.py --only-shared` and pin shared versions in one place (catalog or root constraints).

**Mistake:** Deep imports across package boundaries (`../../packages/ui/src/...`).
**Why it matters:** The dependency never appears in `package.json`, so impact analysis and the build cache miss it.
**Instead:** Import through the package name and declare it with `workspace:*`.

## Files

| File | Purpose |
|------|---------|
| `scripts/package_analyzer.py`, `scripts/impact_detector.py`, `scripts/dependency_graph.py` | Stdlib CLIs |
| `assets/sample_monorepo/` | pnpm workspace: `apps/web`, `apps/docs`, `packages/ui`, `packages/utils` |

## Scope & Limitations

**This skill covers:**
- Turborepo, Nx, and pnpm workspace configuration and optimization
- Cross-package dependency analysis and impact visualization
- Remote caching setup (Vercel, Nx Cloud, self-hosted)
- Changesets-based coordinated versioning and npm publishing

**This skill does NOT cover:**
- Application-level build configuration (webpack, Vite, esbuild internals) — see `performance-profiler`
- CI/CD pipeline design beyond monorepo-specific filters — see `ci-cd-pipeline-builder`
- Git branching strategies and release flow — see `release-manager`
- Dependency vulnerability scanning and license auditing — see `dependency-auditor`

---

## What I Need You to Do

First, detect which platform I'm using (Claude.ai, ChatGPT, etc.) and follow the matching instructions below.

### If I'm on Claude.ai:

Walk me through these exact steps:

1. **Create the Project:** Tell me to go to **claude.ai > Projects > Create project** and name it **"Monorepo Navigator"**

2. **Add Project Knowledge:** Give me the COMPLETE skill definition above as a single copyable text block inside a code fence. Tell me to click **"Add content" > "Add text content"** inside the project, then paste that entire block. Do NOT say "paste from above" -- give me the actual text to copy right there.

3. **Set Custom Instructions:** Tell me to open project settings and paste this exact instruction:
   "You are an expert Monorepo Navigator in the Engineering domain. Use the project knowledge as your expertise. Follow the workflows, frameworks, and templates defined there. Always provide specific, actionable output."

4. **Test It:** Give me a specific sample prompt I can use inside the new project to verify it works. Pick a real task from the skill's workflows.

### If I'm on ChatGPT:

Walk me through these exact steps:

1. **Create a Custom GPT:** Tell me to go to **chatgpt.com > Explore GPTs > Create**
2. **Configure it:**
   - Name: **"Monorepo Navigator"**
   - Description: "Manage and optimize monorepos with Turborepo, Nx, pnpm workspaces, and Changesets. Use when working in monorepos, running impact analysis, optimizing build times with remote caching, migrating from multi-repo, or coordinating publishing."
   - Instructions: Give me the COMPLETE skill definition above as a single copyable text block inside a code fence to paste into the Instructions field. Do NOT say "paste from above."
3. **Test It:** Give me a sample prompt to verify it works.

### If I'm on another platform:
Ask which tool I'm using and adapt the instructions accordingly.

## Important
- Always provide the full skill text in a ready-to-copy code block -- never tell me to "scroll up" or "copy from above"
- Keep the setup steps simple and numbered
- After setup, test it with me using a real workflow from the skill

Source: https://github.com/borghei/Claude-Skills/tree/main/engineering/monorepo-navigator/SKILL.md