nx-workspace
Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 with excellent trigger term coverage and completeness. The explicit 'USE WHEN' clauses with concrete examples make it very clear when this skill should be selected. The main weakness is that the core capability statement ('Explore and understand') could be more specific about the concrete actions performed.
Suggestions
Replace the vague 'Explore and understand' opener with specific actions like 'List projects, inspect configurations, show dependency graphs, and debug task failures in Nx workspaces'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Nx workspaces) and mentions actions like exploring projects, tasks, targets, configuration, and dependencies, but the core verb 'Explore and understand' is somewhat vague. It doesn't list concrete actions like 'list projects', 'show dependency graph', or 'inspect project configuration'. | 2 / 3 |
Completeness | Clearly answers both 'what' (explore and understand Nx workspaces, check available targets/configuration) and 'when' with explicit 'USE WHEN' clauses and concrete examples of triggering queries and error scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'workspace', 'projects', 'tasks', 'targets', 'configuration', 'depends on', 'nx command fails', 'debug nx task failure', 'Cannot find configuration for task'. These are terms users would naturally use when working with Nx. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Nx workspaces specifically. The trigger terms like 'nx command', 'targets', 'workspace', and Nx-specific error messages make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with excellent concrete examples and real command-line syntax throughout. Its main weakness is redundancy — project configuration and target inspection commands appear in multiple sections, inflating the token cost. The structure would benefit from consolidating overlapping sections and moving the detailed example outputs to a reference file.
Suggestions
Consolidate the 'Target Information', 'Common Exploration Patterns', and 'Programmatic Answers' sections to eliminate redundant jq commands that appear multiple times (e.g., `.targets | keys`, `.targets.build`).
Move the detailed example JSON outputs (project details, project graph) into a separate reference file (e.g., references/EXAMPLES.md) to reduce the main skill's token footprint while preserving discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has significant redundancy — many jq commands for project details appear in both 'Target Information' and 'Programmatic Answers' sections. The 'Common Exploration Patterns' section largely repeats earlier content. Some sections like 'Key nx.json sections' add minor filler. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Every section provides concrete, copy-paste-ready bash commands with real flags and jq filters. Example JSON outputs are included for key commands (show projects, show project, graph --print), making it fully executable and specific. | 3 / 3 |
Workflow Clarity | For a read-only exploration skill, the workflows are clear and well-sequenced. Common patterns like 'What's in this workspace?' and troubleshooting flows ('Cannot find configuration') provide logical step sequences. Since this is non-destructive (read-only), validation checkpoints aren't critical, and the troubleshooting section provides appropriate error recovery guidance. | 3 / 3 |
Progressive Disclosure | There is one reference to 'references/AFFECTED.md' for affected projects, which is good progressive disclosure. However, the main file is quite long (~200 lines) with redundant sections that could be split out. The 'Programmatic Answers' section with full example outputs could be a separate reference file, and the content between 'Target Information' and the later programmatic section overlaps significantly. | 2 / 3 |
Total | 10 / 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
- Ensono/stacks-nx-plugins
- Commit
e887790
- 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.