Skip to content

LedgerHQ/lumen / .claude/skills/nx

Nx workspace commands and guidelines for running tasks, generators, and using Nx MCP tools

Nx

This is an Nx 22.5.3 monorepo using npm. Prefer the Nx MCP server over guessing about the workspace — it reflects the live project graph and config.

Use the MCP server first

  • nx_workspace — understand the project graph / architecture, and surface project-graph or config errors, before answering workspace questions.
  • nx_project_details — inspect a single project's targets and config.
  • nx_docs — fetch up-to-date Nx docs for any configuration/best-practice question instead of assuming.
  • nx_visualize_graph — show task/project dependencies.
  • nx_current_running_tasks_details / nx_current_running_task_output — inspect tasks already running in the user's terminals; rerun with nx run <taskId> so it executes in the same Nx context. Don't offer to rerun a continuous task.

Generators

When scaffolding, drive it through the MCP flow rather than hand-writing files: nx_generators to list, nx_generator_schema for options, then nx_open_generate_ui and read back nx_read_generator_log. Keep options minimal; use nx_available_plugins if no generator fits.

Commands

  • Run anything with nx run <project>[:target]; targets live in each project's project.json (or are inferred from config).
  • The canonical common commands (test / lint / typecheck / build / storybook) and the package↔lib mapping live in the Commands and Libraries sections of AGENTS.md — not duplicated here.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall