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'.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently covers NX workspace operations with concrete, executable commands and clear multi-phase workflows. The content respects Claude's intelligence by avoiding explanations of basic concepts while providing critical operational details like forbidden commands and the `--no-interactive` flag requirement. The MCP tool reference table and phased code generation workflow are particularly strong, providing actionable guidance with appropriate validation checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what NX is or how monorepos work, assumes Claude's competence, and presents commands and workflows without unnecessary preamble. The 'Forbidden Commands' section is a valuable addition that earns its tokens. | 3 / 3 |
Actionability | Commands are copy-paste ready with concrete syntax (e.g., `yarn nx run <project-name>:test --coverage`). The code generation workflow includes specific flags like `--no-interactive` and `--dry-run` with clear rationale. The MCP tool table provides specific tool names with when-to-use guidance. | 3 / 3 |
Workflow Clarity | The Code Generation Workflow has clear phases (Discover → Understand → Execute → Post-Generation) with explicit validation steps (dry-run preview, verify lint/test/build, format check). Error recovery is addressed ('On failure: read the error, adjust options, and retry'). The Running Tasks Workflow also has clear sequencing with validation via output checking. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references: REFERENCE.md for generator schemas, project.instructions.md for project name mappings, and the self-improvement skill for non-obvious fixes. Content is appropriately split between quick-reference commands and detailed workflows. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
f5c8508
- Reviewed
Table of Contents
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.