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'.
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the NX monorepo tooling domain, lists concrete actions, and provides explicit trigger phrases. The one minor issue is the use of second person ('when you say') instead of third person, which per the rubric guidelines should penalize the specificity score, but the phrasing is borderline since it's addressing Claude's selection behavior. Overall it effectively differentiates itself and would enable accurate skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: run/generate NX targets, configure project.json, and visualize dependency graphs. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (run/generate NX targets, configure project.json, visualize dependency graphs) and 'when' with explicit trigger phrases via the 'Use when you say:' clause. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'run affected tests', 'nx generate a library', 'configure project.json', 'show dependency graph'. These closely match real user language for NX monorepo workflows. | 3 / 3 |
Distinctiveness Conflict Risk | NX is a specific monorepo build tool with distinct terminology (nx generate, affected tests, project.json, dependency graph). This is unlikely to conflict with generic build or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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-structured, highly actionable NX workspace skill. It excels at conciseness by avoiding unnecessary explanations and providing copy-paste ready commands. The phased code generation workflow with validation checkpoints and the MCP tool reference table are particular strengths. The only notable weakness is that referenced files (REFERENCE.md, project.instructions.md) cannot be verified since no bundle files were provided.
| 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 fully copy-paste ready with concrete syntax patterns. The code generation workflow provides specific executable commands (e.g., `yarn nx generate <generator-name> <options> --dry-run --no-interactive`), and the MCP tool table gives precise tool names with clear usage triggers. | 3 / 3 |
Workflow Clarity | The Code Generation Workflow has clear phased sequencing (Discover → Understand → Execute → Post-Generation) with explicit validation checkpoints (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 feedback loops. | 3 / 3 |
Progressive Disclosure | References to REFERENCE.md and project.instructions.md are well-signaled, but REFERENCE.md is not provided in the bundle, making it impossible to verify the reference is valid. The self-improvement skill link is a nice touch but points to a relative path that can't be verified. The MCP tool table is inline but appropriately so given its size. | 2 / 3 |
Total | 11 / 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
7a69a05
- 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.