The official Turborepo skill from the vercel/turborepo repo: points an agent at the docs bundled inside the installed turbo package, so turbo.json, caching, filtering and CI changes follow the exact version in use.
Nx Workspace Skill
Nx's official read-only skill for exploring an Nx monorepo: list and filter projects, read fully resolved project and target configuration, and inspect nx.json and affected projects.
Install
Other ways to install
About
- Lists and filters projects by glob, tag, directory, target, type or affected status
- Reads fully resolved project config via nx show project --json, including inferred targets
- Inspects target executors, options, inputs and outputs for caching
- Reads nx.json targetDefaults, namedInputs, plugins and generators
- Bundled reference for affected-project queries
- Read-only; picks npx, pnpx or yarn from the lockfile
Nx Workspace is a skill published by Nrwl, the company behind the Nx build system, in its nx-ai-agents-config repository. It teaches a coding agent how to understand an Nx monorepo before acting on it: which projects exist, what targets they have, how they are configured and how they depend on each other. It is meant for answering questions about the workspace and for checking available targets when an nx command fails.
The key instruction is to ask Nx rather than read files. project.json holds only part of a project's configuration, because Nx plugins infer many targets, so the skill directs the agent to nx show project <name> --json (piped through jq) for the fully resolved targets, executors, options, inputs and outputs. It documents the project filter syntax shared by nx show projects, nx run-many and nx release: globs, tag: references, directories, negation, --withTarget, --type and --affected.
For workspace-level settings it reads nx.json directly (targetDefaults, namedInputs, plugins, generators) and points to the JSON schemas shipped in node_modules/nx. A bundled reference covers affected-project queries. The skill is strictly read-only and reminds the agent to prefix commands with npx, pnpx or yarn based on the workspace lockfile. MIT licensed.
SKILL.md
The instructions your agent loads, as published by Nx.
Related Skills
See all Nx Workspace alternativesBuild crash-safe AI agents on AgentKit and step.ai — durable tool calls, human-in-the-loop approval, realtime progress, and when not to reach for an agent loop at all.
Inngest's durable-execution playbook as an agent skill — steps and memoisation, event and cron triggers, idempotency, cancellation, retries and non-retriable errors.
Prisma's official command reference for Prisma ORM 7: init, generate, migrate, db, dev, studio and mcp, with a safety checkpoint before destructive commands.
