cb.fabric-backend-boundaries

Name: cb.fabric-backend-boundaries
Availability: InStock
Author: Softmax

Enforce Fabric CUDA backend ownership boundaries during code edits.

Updated Aug 27, 2026

Search Tags:#backend #ownership #review #guardrail #cuda #fabric

Ready to run

npx skills add https://github.com/Metta-AI/cortical --skill cb-fabric-backend-boundaries

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cb.fabric-backend-boundaries
Source: https://github.com/Metta-AI/cortical/tree/main/skills/cb.fabric-backend-boundaries
Command: npx skills add https://github.com/Metta-AI/cortical --skill cb-fabric-backend-boundaries

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use of this skill to enforce architecture guardrails when modifying Fabric CUDA backend execution, fabric.cuda.nn declarations, physical operators, or anything that risks mixing Fabric cell semantics with backend scheduling/execution ownership.

Core Features & Use Cases

Enforces a strict separation between cell-level semantics and backend execution to prevent cross-domain ownership issues.
Guides engineers through the required review paths, design contracts, and verification steps before touching low-level backend code.
Provides discoverable references to relevant docs and code paths to ensure parity, safety, and maintainability.

Quick Start

Analyze and adhere to the Fabric backend boundaries before touching CUDA backend execution or related operators.

Frequently Asked Questions about cb.fabric-backend-boundaries

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

FAQPage Schema

How do I enforce Fabric backend boundaries when modifying CUDA backend execution?▼

To enforce Fabric backend boundaries, apply architecture guardrails that separate Fabric cell semantics from backend execution. This prevents cross-domain ownership issues when modifying CUDA lowering, planning, or runtime components.

What is the separation between Fabric cell semantics and backend execution?▼

The separation between Fabric cell semantics and backend execution is an architecture design contract. It ensures changes to physical operators and CUDA backend code remain well-scoped and traceable across ownership domains.

Do I need a design contract before editing fabric.cuda.nn declarations?▼

Yes, you need a design contract before editing fabric.cuda.nn declarations. The contract guides required review paths and verification steps to ensure low-level backend code changes do not cross ownership boundaries.

How do I discover live owners for Fabric CUDA backend components?▼

You discover live owners for Fabric CUDA backend components by following the discover-live-owners steps provided by the guardrails. This ensures changes to physical operators are properly scoped and reviewed before implementation.

When should I use Fabric backend boundary guardrails for CUDA work?▼

You should use Fabric backend boundary guardrails whenever changes risk crossing ownership boundaries in CUDA lowering, planning, or runtime. This includes modifying Fabric CUDA backend execution and physical operators.

What are the limitations of modifying Fabric CUDA backend execution without guardrails?▼

Modifying Fabric CUDA backend execution without guardrails risks mixing cell-level semantics with backend scheduling ownership. This creates cross-domain ownership issues, making changes poorly scoped and difficult to trace during reviews.