nx-workspace

Run and generate NX targets, configure project.json, and visualize dependency graphs. Use when you say: 'run affected tests', 'nx generate a library', 'configure project.json', or 'show dependency graph'.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, highly actionable NX skill body with executable commands and clear forbidden-pattern guidance. Workflow sequencing is strong but a post-generation retry loop and a bundled reference file would round it out.

Suggestions

Add an explicit feedback loop after 'lint/test/build the affected projects' — e.g., if checks fail, fix and re-run until green — to satisfy the destructive/batch validation expectation.

Provide the referenced project.instructions.md (or note it lives outside the bundle) so the one-level reference is verifiable rather than dangling.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse directives, a compact MCP tool table, and executable code blocks with no over-explanation of NX concepts — assuming Claude's competence throughout.	5 / 5
Actionability	Provides copy-paste-ready commands ('yarn nx run <project>:<target>', 'yarn nx affected -t <target>', 'yarn nx generate ... --no-interactive') plus a precise when-to-use table for each MCP tool.	5 / 5
Workflow Clarity	The generation flow is sequenced with a --dry-run preview checkpoint and a post-generation lint/test/build verification step, but it lacks an explicit fix-and-retry loop after verification failure.	4 / 5
Progressive Disclosure	Clean, well-organized sections for a sub-50-line skill with one-level pointers (docs URL, project.instructions.md), but the referenced project.instructions.md is not present in a bundle and the MCP table is dense inline content.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that pairs concrete capabilities with explicit, natural trigger phrases and a clearly bounded NX niche. Only minor synonym/extension coverage in the trigger terms keeps it from a perfect score.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'Run and generate NX targets', 'configure project.json', 'visualize dependency graphs' — providing comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (the three NX actions) and 'when' (an explicit 'Use when you say:' clause with concrete trigger phrases), matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Trigger phrases like 'run affected tests', 'nx generate a library', 'configure project.json', 'show dependency graph' are natural user utterances, but coverage lacks synonyms and additional file-extension variants that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	NX-specific niche with distinct, tool-bound triggers ('nx generate', 'dependency graph', 'project.json') that make overlap with unrelated skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: monkilabs/opencastle
Path: src/orchestrator/plugins/nx/SKILL.md
Commit: fa0c341

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.