MUST use for ANY query mentioning packages, monorepo, workspace, catalog, turbo, turborepo, or pnpm in a multi-package context. MUST use when sharing config (ESLint, tsconfig, prettier) across packages, fixing build order between packages, adding new packages, scoping CI installs/caching to changed packages, or debugging pnpm catalog version resolution. This skill OWNS all cross-package coordination problems — even when they look like build, CI, config, or dependency issues. If two or more packages interact in the query, this skill applies. Takes priority over other skills when the problem spans package boundaries.
npx skills add https://github.com/avibebuilder/claude-prime --skill monorepo
Project-specific patterns for pnpm workspaces + Turborepo.
apps/ for deployables, packages/ for shared libraries.@org/ to avoid npm conflicts.pnpm-lock.yaml at root only. Never commit multiple lockfiles.../ to reach into other packages; import via dependencies.workspace:* protocol — Always for internal package dependencies.pnpm-workspace.yaml for large repos.^ for build dependencies — "dependsOn": ["^build"] for topological order.10. Always define outputs — Without outputs, nothing gets cached.
11. Mark dev servers as persistent — "persistent": true, "cache": false.
12. Be explicit about environment — List all build-affecting vars in env or globalEnv.
outputs in turbo.json silently disables caching for that task. The task runs every time and you won't get an error — just slow builds. Always verify outputs are configured.pnpm install does NOT respect --filter for installation — it always installs the entire workspace. Filtering only works for pnpm run and pnpm exec.workspace:* resolves to the CURRENT version of the local package, not "latest from npm". If the package has "version": "0.0.0", published packages will have "dependency": "0.0.0" — set meaningful versions before publishing.env field in turbo.json uses GLOB patterns, not exact matches. "env": ["API_*"] captures API_KEY, API_URL, etc. Forgetting this causes over-invalidation.turbo run build --filter=app-a builds app-a AND all its workspace dependencies. If a dependency fails, app-a won't build. Check transitive deps.packages/ requires running pnpm install before the workspace recognizes it. The new package also needs a valid package.json with name matching the workspace pattern.references in tsconfig.json) must match the workspace dependency graph. Mismatches cause type errors that only appear during tsc --build, not in IDE.turbo.json's globalDependencies invalidates ALL tasks when listed files change. Don't put frequently-changed files here — use task-level inputs instead.@source directives pointing to consuming packages' source directories, otherwise classes used in shared packages are purged.pnpm deploy (for production) copies a single package and its dependencies to a target directory. It does NOT run build scripts — build first, then deploy.outputs to be correct. If outputs are wrong, cached artifacts will be incomplete and downstream tasks break silently.persistent: true tasks prevent turbo run from exiting. Don't include persistent tasks in CI pipelines unless they have a timeout.| When you need... | Read |
|------------------|------|
| workspace.yaml, workspace: protocol, filtering | pnpm-workspace.md |
| turbo.json schema, tasks, dependsOn | turborepo.md |
| Cache outputs/inputs, remote cache setup | caching.md |
| Directory layout, package naming, tsconfig | structure.md |
| Tailwind v4 shared theme package | tailwind-v4.md |
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take avibebuilder/monorepo from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm.
Without those the skill loads but fails at the first command.