Agent skill
nx-tools
Queries Nx monorepo metadata via Python CLI: workspace projects, affected detection, dependency graphs, project.json configs, generator schemas. Use when analyzing monorepo structure, optimizing CI via affected projects, or inspecting workspace topology.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/nx-tools
SKILL.md
[H1][NX-TOOLS]
Dictum: Uniform interfaces eliminate invocation ambiguity.
Query Nx workspace with unified Python CLI. Wraps pnpm exec nx commands.
[IMPORTANT] Nx 22 features: Terminal UI, continuous tasks, pnpm catalog support, AI agent configuration, Vitest 4 atomizer. All commands run with NX_DAEMON=false for deterministic output.
[1][COMMANDS]
| [CMD] | [ARGS] | [PURPOSE] |
|---|---|---|
| workspace | -- | List all projects |
| path | -- | Get workspace root path |
| generators | -- | List available generators |
| project | <name> |
View project configuration |
| run | <target> |
Run target across projects |
| schema | <generator> |
View generator schema |
| affected | [base] |
List affected projects (default: main) |
| graph | [output] |
Generate dependency graph |
| tokens | [path] |
Count tokens in file/directory |
| docs | [topic] |
View Nx command documentation |
[2][USAGE]
# Zero-arg commands
uv run .claude/skills/nx-tools/scripts/nx.py workspace
uv run .claude/skills/nx-tools/scripts/nx.py path
uv run .claude/skills/nx-tools/scripts/nx.py generators
# Required-arg commands
uv run .claude/skills/nx-tools/scripts/nx.py project @parametric-portal/types
uv run .claude/skills/nx-tools/scripts/nx.py run build
uv run .claude/skills/nx-tools/scripts/nx.py run typecheck
uv run .claude/skills/nx-tools/scripts/nx.py schema @nx/react:component
# Optional-arg commands (defaults shown)
uv run .claude/skills/nx-tools/scripts/nx.py affected # base=main
uv run .claude/skills/nx-tools/scripts/nx.py affected HEAD~5
uv run .claude/skills/nx-tools/scripts/nx.py graph # output=.nx/graph.json
uv run .claude/skills/nx-tools/scripts/nx.py graph custom.json
uv run .claude/skills/nx-tools/scripts/nx.py tokens # path=.
uv run .claude/skills/nx-tools/scripts/nx.py tokens CLAUDE.md
uv run .claude/skills/nx-tools/scripts/nx.py docs # topic=general
uv run .claude/skills/nx-tools/scripts/nx.py docs affected
[3][ARGUMENTS]
workspace: (no arguments)
- Returns list of all project names in workspace
path: (no arguments)
- Returns workspace root path from
CLAUDE_PROJECT_DIRorcwd
generators: (no arguments)
- Returns list of available Nx generators (plugins + local)
project: <name>
name— Project name (required, e.g.,@parametric-portal/types)- Returns full project.json configuration as JSON
run: <target>
target— Target to run (required, e.g.,build,typecheck,test)- Executes
pnpm exec nx run-many -t <target>
schema: <generator>
generator— Generator name (required, e.g.,@nx/react:component)- Returns generator help with all available options
affected: [base]
base— Git ref to compare against (default:main)- Returns JSON array of affected project names
graph: [output]
output— Output file path (default:.nx/graph.json)- Generates workspace dependency graph
tokens: [path]
path— File or directory to count (default:.)- Uses
tools/scripts/count-tokens.tsvia tsx
docs: [topic]
topic— Nx command to get help for (default: general help)
[4][OUTPUT]
Commands return: {"status": "success|error", ...}.
| [INDEX] | [CMD] | [RESPONSE] |
|---|---|---|
| [1] | workspace |
{projects: string[]} |
| [2] | path |
{path: string} |
| [3] | generators |
{generators: string} |
| [4] | project |
{name: string, project: object} |
| [5] | run |
{target: string, output: string} |
| [6] | schema |
{generator: string, schema: string} |
| [7] | affected |
{base: string, affected: string[]} |
| [8] | graph |
{file: string} |
| [9] | tokens |
{path: string, output: string} |
| [10] | docs |
{topic: string, docs: string} |
[5][ENVIRONMENT]
| [VAR] | [REQUIRED] | [DESCRIPTION] |
|---|---|---|
CLAUDE_PROJECT_DIR |
No | Override workspace root for path cmd |
NX_DAEMON |
No | Force-set to false by script |
[6][ERROR_HANDLING]
- Nx errors print
[ERROR] <message>and exit 1 - Project not found:
[ERROR] Cannot find project '<name>' - Target not found:
[ERROR] Cannot find target '<target>'for the project - Graph generation failure: verify Nx workspace configuration is valid
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?