nx-generate
Generate code using nx generators. INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs, or setting up project structure. Trigger words - scaffold, setup, create a ... app, create a ... lib, project structure, generate, add a new project. ALWAYS use this BEFORE calling nx_docs or exploring - this skill handles discovery internally.
66
79%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.cursor/skills/nx-generate/SKILL.mdQuality
Discovery
82%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 description has strong trigger term coverage and completeness, clearly stating when to invoke the skill with explicit trigger words and priority ordering. However, the specificity of capabilities could be improved by listing concrete actions beyond 'generate code', and some trigger terms like 'scaffold' and 'setup' are generic enough to risk conflicts with other project creation skills. The instruction 'ALWAYS use this BEFORE calling nx_docs' is useful for prioritization but reads more as an internal directive than a description.
Suggestions
List more specific concrete capabilities beyond 'generate code', e.g., 'Creates nx workspace apps and libraries, scaffolds project structures, configures generators for React/Angular/Node projects'.
Narrow generic trigger terms by qualifying them with 'nx' context, e.g., 'nx scaffold', 'nx workspace setup', to reduce conflict risk with other scaffolding tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (nx generators) and the general action (generate code), but doesn't list multiple specific concrete actions like 'create apps, create libraries, scaffold project structure, configure workspaces'. The actions are somewhat implied through trigger words rather than explicitly stated as capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate code using nx generators) and 'when' (explicit trigger words and scenarios listed, plus priority guidance about invoking before other skills). The 'INVOKE IMMEDIATELY when...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'scaffold', 'setup', 'create a ... app', 'create a ... lib', 'project structure', 'generate', 'add a new project'. These are highly natural phrases a user would use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | While 'nx generators' is fairly specific, terms like 'scaffold', 'setup', 'create a ... app', and 'project structure' are generic enough to potentially conflict with other project scaffolding skills (e.g., Yeoman, Create React App, or general project setup skills). The explicit mention of 'nx' helps but the broad trigger words increase overlap risk. | 2 / 3 |
Total | 10 / 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, actionable skill with a well-defined multi-step workflow and concrete CLI examples throughout. Its main weakness is verbosity—some sections explain concepts Claude already knows (what generators are, what buildable vs non-buildable means conceptually) and the document could benefit from splitting detailed reference material into separate files. The workflow clarity is excellent with dry-run validation, verification steps, and clear error recovery guidance.
Suggestions
Remove the opening paragraph explaining what Nx generators are—Claude already knows this. Start directly with 'This skill applies when...' or the Key Principles.
Consider moving the Library Buildability section to a separate reference file (e.g., BUILDABILITY.md) and linking to it, as it's a detailed sub-topic that interrupts the main workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., the opening paragraph explaining what Nx generators are, the detailed buildability table that Claude could infer). The 'Key Principles' section and some step descriptions are reasonably tight, but overall there's room to trim explanatory prose while keeping the actionable content. | 2 / 3 |
Actionability | The skill provides concrete, executable CLI commands at every step (listing generators, dry-run, running generators, formatting, verification). The --directory flag gotcha with correct/incorrect examples is particularly actionable. Commands are copy-paste ready with clear flags explained. | 3 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit validation checkpoints: dry-run before execution (step 6), format and verify after generation (step 9), and a feedback loop for handling failures (fix manageable issues, escalate extensive ones). The workflow also includes a decision point to go back to step 2 if the generator isn't right. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and numbered steps, but it's a fairly long monolithic document (~150 lines of substantive content). The buildability table and the detailed source code reading instructions could be split into referenced files. The reference to 'link-workspace-packages' skill is a good cross-reference, but no bundle files exist to support progressive disclosure. | 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
- leboncoin/spark-web
- Commit
76a3678
- 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.