ns-create

Create NeuroScript neuron definitions from natural language descriptions.

Updated Nov 25, 2025
One-click install
npx skills add https://github.com/severeon/neuroscript-rs --skill ns-create
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ns-create
Source: https://github.com/severeon/neuroscript-rs/tree/main/.claude/skills/ns-create
Command: npx skills add https://github.com/severeon/neuroscript-rs --skill ns-create

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It streamlines authoring NeuroScript neurons by turning natural-language specifications into well-formed .ns neuron definitions, ensuring correct shape signatures, appropriate context bindings, and reuse of stdlib components so developers avoid repetitive manual DSL coding and common shape errors.

Core Features & Use Cases

  • Templates & Patterns: Provides templates for primitives, composites, residuals, match-based routing, and recursive neurons to accelerate consistent neuron creation.
  • Validation Workflow: Includes a validate_neuron.sh script and guidance to parse, type-check, and compile neurons before committing them.
  • Best-practice Guidance: Advises on impl reference formats, match exhaustiveness, variadic shape rules, and when to reuse stdlib vs inline patterns.
  • Output Destinations: Targets examples/ for demos, stdlib/ for reusable library neurons, or project src/ for package-specific integrations.

Quick Start

Describe the neuron (purpose, input/output shapes, parameters, and desired pattern) and request generation into stdlib/ or examples/ and then run the provided validation script to parse, validate, and compile the new neuron.

Frequently Asked Questions about ns-create

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate NeuroScript neurons from natural language descriptions?

Generate NeuroScript neurons by describing the purpose, input/output shapes, and parameters, then targeting examples/ or stdlib/ to produce .ns definitions with YAML frontmatter and correct shape signatures.

What is the best way to validate NeuroScript neuron definitions before committing?

Validate NeuroScript neurons by running the included validate_neuron.sh script to parse, type-check, and compile .ns definitions, ensuring correct shape signatures and catching common shape errors before commit.

Does NeuroScript support templates for match-based routing and recursive neurons?

NeuroScript supports templates for primitives, composites, residual blocks, match-based routers, and recursive neurons, accelerating consistent neuron creation across examples and stdlib.

Can I reuse stdlib components when authoring composite NeuroScript neurons?

You can reuse stdlib components when authoring composite NeuroScript neurons, applying best-practice guidance for impl reference formats and variadic shape rules to avoid repetitive manual DSL coding.

When should I not use inline patterns for NeuroScript neuron creation?

Avoid inline patterns when stdlib components already provide the desired functionality, reusing existing library neurons to prevent common shape errors and repetitive manual DSL coding.

Why do my generated NeuroScript neurons fail to compile?

NeuroScript neurons fail to compile due to incorrect shape signatures, missing YAML frontmatter, or invalid impl references; run the validation script to parse, type-check, and identify exact compile errors.