implement-mock

Standardize silicon API mocks in the tt-emule emulator with strategy selection and verification.

4|1|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/tenstorrent/tt-emule --skill implement-mock
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: implement-mock
Source: https://github.com/tenstorrent/tt-emule/tree/main/.claude/skills/implement-mock
Command: npx skills add https://github.com/tenstorrent/tt-emule --skill implement-mock

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill addresses the complexity of adding faithful silicon API mocks to the tt-emule runtime, ensuring that host-side code and kernels run correctly without requiring actual Tenstorrent hardware.

Core Features & Use Cases

  • Standardized Workflow: Provides a structured, step-by-step process for identifying, implementing, and verifying mocks.
  • Strategy Selection: Offers clear guidance on choosing between stubbing, patching, or semantic rewriting based on the kernel API layer.
  • Verification: Includes built-in steps for regression testing and sentinel validation to prevent collateral damage.

Quick Start

Invoke the implement-mock skill followed by the name of the silicon function or concept you need to mock to receive the implementation strategy and workflow steps.

Frequently Asked Questions about implement-mock

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

FAQPage Schema
How do I mock silicon APIs for kernel emulation without physical hardware?

Mock silicon APIs by standardizing implementation strategies like header stubbing, per-op patching, and semantic rewrites to ensure host-side code and kernels run correctly without actual hardware.

What is the best way to choose a mocking strategy for tt-emule runtime compatibility?

Choose a mocking strategy based on the kernel API layer, selecting between header stubbing, per-op patching, or semantic rewrites to achieve the required level of compatibility.

How do I verify mocked silicon APIs to prevent regression in the software stack?

Verify mocked silicon APIs through sentinel testing and regression analysis against the tt-metal software stack to prevent collateral damage and ensure faithfulness.

Does the implement-mock skill require actual Tenstorrent hardware to run kernels?

No, the implement-mock skill facilitates mocking silicon APIs within the tt-emule emulator, allowing host-side code and kernels to run correctly without requiring actual Tenstorrent hardware.

When do I need semantic rewrites instead of header stubbing for kernel API mocking?

Semantic rewrites are needed when kernel-level compatibility requires deeper logic translation than simple header stubbing or per-op patching can provide within the emulator runtime.