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.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%

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

A highly actionable, well-sequenced workflow with strong verification checkpoints and executable commands. The only real weakness is conciseness: minor preamble and a trigger list that duplicate the description.

Suggestions

Trim the opening paragraph ('Nx generators are powerful tools...') to a single line or remove it, since it explains concepts Claude already knows.

Remove or shorten the 'This skill applies when the user wants to' bullet list, which duplicates the trigger terms already in the frontmatter description.

Tighten step 9's verification guidance by leading with the runnable command and keeping the CI-guidance aside to one sentence.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the opening preamble ('Nx generators are powerful tools that scaffold projects...') and the 'This skill applies when the user wants to' list restate concepts Claude knows and repeat trigger info already in the description.	2 / 3
Actionability	Provides copy-paste-ready commands throughout (npx nx list, --help, --dry-run --no-interactive, npm run format, nx run-many -t build,lint,test,typecheck) plus correct/incorrect --directory code examples.	3 / 3
Workflow Clarity	A clear 9-step sequence with explicit validation checkpoints: dry-run file-placement verification (step 6) and a format-then-verify step (step 9) with a 'if verification fails...' fix-and-escalate recovery loop.	3 / 3
Progressive Disclosure	A single, self-contained SKILL.md organized into clear headed sections with no nested references; no bundle files exist, so the well-structured single-file overview is appropriate.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, specific description that explicitly covers capabilities, natural trigger terms, and invocation timing. Its main weakness is a slightly imperative, padded tone ('INVOKE IMMEDIATELY', 'ALWAYS use this BEFORE') that adds words without adding scoring value.

Dimension	Reasoning	Score
Specificity	Names the domain ('Generate code using nx generators') and lists multiple concrete actions including 'creating apps/libs', 'scaffolding', and 'setting up project structure'.	3 / 3
Completeness	Clearly answers both 'what' (generate code via nx generators) and 'when' ('INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs...').	3 / 3
Trigger Term Quality	Explicit 'Trigger words' list (scaffold, setup, create a ... app, create a ... lib, project structure, generate, add a new project) covers natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear nx-generator niche with distinct triggers; the 'BEFORE calling nx_docs' directive scopes it apart from a docs skill, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 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: leboncoin/spark-web
Path: .cursor/skills/nx-generate/SKILL.md
Commit: 9f4792e

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.