Nx AI Agents Config - Setup Guide¶

Source: nrwl/nx-ai-agents-config GitHub: nrwl/nx-ai-agents-config Skills: 10 skills · 44.7K total installs Category: Monorepo Tooling First Seen: catalogued August 17, 2026 evening sweep (nx-workspace on skills.sh since January 27, 2026) Quality Tier: 🟢 Production - official Nx org; flagship nx-workspace passes all three security audits (3/3 Pass)

The official Nx (nrwl) agent configuration gives coding agents read-only exploration of Nx monorepos, task orchestration, code generation, and CI monitoring. nx-workspace is the largest monorepo-navigation skill on the platform at 31.4K installs, and the read-only-by-design posture makes it safe to load in production workspaces.

Installation¶

npx skills add nrwl/nx-ai-agents-config

Individual skills install with the explicit repo form:

npx skills add https://github.com/nrwl/nx-ai-agents-config --skill nx-workspace

Prerequisites¶

Requirement	Details
Node.js + npx	For the skill installer
Nx workspace	An existing monorepo managed by Nx
nx CLI	Available globally or via `npx`/`pnpx`/`yarn` prefix

What It Provides¶

Skill	Installs	Purpose
nx-workspace	31.4K	Read-only workspace exploration: `nx show projects`, project filtering, dependency structure
nx-run-tasks	2.6K	Task execution guidance across targets and projects
nx-generate	2.5K	Code generation with generators and plugins
nx-plugins	2.3K	Plugin configuration and extension patterns
link-workspace-packages	2.2K	Local package linking within the workspace
nx-import	2.0K	Importing external code and libraries
monitor-ci	1.7K	CI pipeline monitoring and interpretation
polygraph / get-latest-ci / await-polygraph-ci	≤3	Nx Cloud Polygraph CI helpers (early content)

The flagship skill's project-filtering syntax (explicit names, globs, tag: references, negation with !project-name) works across nx run-many, nx release, and nx show projects - one syntax for every workspace-scoped command.

Quick Start¶

Install: npx skills add nrwl/nx-ai-agents-config
In the repo root, ask: "explore this Nx workspace and explain the project structure"
The skill runs nx show projects and walks the dependency graph read-only

CorpusIQ Use Cases¶

Use Case	How
Monorepo navigation	Read-only workspace maps reduce agent mistakes in multi-app repos
CI diagnosis	monitor-ci interprets Nx Cloud pipeline failures without manual log spelunking
Task orchestration	Filtering syntax carries over to `nx run-many` for targeted rebuilds

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

Limitations / Verification¶

Security audits on nx-workspace: Gen Agent Trust Hub Pass, Socket Pass, Snyk Pass - all three clean
Publisher-page total verified (44.7K across 10 skills); repo is young (27 GitHub stars as of the sweep)
Read-only exploration only - the skill does not modify workspace configuration
polygraph, get-latest-ci, and await-polygraph-ci are sub-5 installs - early content

npx skills add nrwl/nx-ai-agents-config   # verify install works

Powered by CorpusIQ