Catalogs NeuroScript primitives and composite neurons with signatures, shapes, and parameters.
npx skills add https://github.com/severeon/neuroscript-rs --skill ns-stdlib
Please help me install this Agent Skill. Skill: ns-stdlib Source: https://github.com/severeon/neuroscript-rs/tree/main/.claude/skills/ns-stdlib Command: npx skills add https://github.com/severeon/neuroscript-rs --skill ns-stdlib
NeuroScript developers need a reliable, up-to-date catalog of available primitives and composite neurons, including their signatures, shapes, parameters, and usage context.
Browse available stdlib neurons and view their signatures and categories.
High-intent search queries and answers about installing and using this skill.
You can look up NeuroScript standard library signatures by browsing a catalog of primitives and composite neurons, which provides their definitions, shapes, and usage contexts.
Primitives are foundational standard library neurons, whereas composite neurons combine multiple components to build more complex computational graphs within your neuroscripts.
To find correct parameters for FFN and TransformerBlock neurons, use the standard library catalog to retrieve their specific signatures, shapes, and integration examples for graph building.
Yes, you can use standard library neurons when debugging a neuroscript to quickly verify available components, check their signatures, and ensure correct parameter usage during integration.
The best way to discover available neurons for building complex graphs is to browse a comprehensive listing of primitives and composites, filtering by categories and examples to select the right components.
You need to reference the NeuroScript stdlib catalog when building or debugging neuroscripts to quickly look up available neuron signatures, shapes, parameters, and usage contexts for integration.
jmg2027Verify Lean 4 proof environments for forbidden axioms and external imports.
severeonCreate NeuroScript neuron definitions from natural language descriptions.
NeuroAIHubGuide construction of biologically realistic spiking network simulations with neuron and synapse configuration.
ascend-ai-codingImplement AscendC transformer operator definitions and kernels for FFN, GMM, and MoE.
