skills.rest
amd
amdOFFICIAL
Explore all skills by this author →
WebsiteGitHub

quark-torch-eval-runner

Verify Quark skill routing, planning, artifact, and recovery outputs.

154|27|Updated Jun 19, 2024
Search Tags:#workflow#routing#validation#skills#quantization#smoke test#quark
One-click install
npx skills add https://github.com/amd/Quark --skill quark-torch-eval-runner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quark-torch-eval-runner
Source: https://github.com/amd/Quark/tree/main/.claude/skills-impl/meta/torch/quark-torch-eval-runner
Command: npx skills add https://github.com/amd/Quark --skill quark-torch-eval-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps maintainers confirm that the Quark Agent Skills system still behaves correctly after changes, upgrades, or release prep, so broken routing or workflow regressions are caught before users are affected.

Core Features & Use Cases

  • Routing Verification: Checks that natural-language prompts invoke the correct downstream skill.
  • Planning Validation: Confirms that quantization plans are internally consistent and match the requested scheme.
  • Artifact and Recovery Checks: Verifies that generated manifests satisfy schema expectations and that known error patterns are diagnosed correctly.
  • Use Case: A maintainer updates multiple skills and needs a structured manual smoke test to confirm routing, planning, artifact generation, and recovery still work as expected.

Quick Start

Use the quark-torch-eval-runner skill to manually verify the Quark skill system after a skill change or before a release.

Frequently Asked Questions about quark-torch-eval-runner

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

FAQPage Schema
How do I verify Quark agent skill routing after updating skills?▼

You can validate routing by running manual smoke tests that check natural-language prompts against skill files to confirm correct downstream routing. This structured validation ensures prompt invocations reach the correct skills before release.

What is quantization planning validation in a smoke test?▼

Quantization planning validation is a smoke test step confirming generated quantization plans are internally consistent and match the requested scheme. It checks planning outputs against contract schemas to prevent workflow regressions.

How do I validate manifest artifacts and error recovery in the Quark skill stack?▼

Validate manifest artifacts and error recovery by applying coordinated manual checks against contract schemas and example prompts. This verifies generated manifests meet expectations and known error patterns are diagnosed correctly across the stack.

Can I use a manual smoke test for release prep across all four Quark contract categories?▼

Yes, a manual smoke test for release prep confirms behavior across all four Quark contract categories. It requires coordinated checks against skill files, contract schemas, and example prompts to validate routing, planning, artifacts, and recovery.

Why does my Quark skill workflow produce invalid planning outputs after an upgrade?▼

Invalid planning outputs after an upgrade usually indicate a workflow regression caught by skipping planning validation. Running smoke tests confirms quantization plans are internally consistent and match requested schemes to diagnose the issue.

Related Skills

Explore More Software Engineering Skills→
kungfuaikungfuai
12

verify-inference-example

Verifies CVlization inference examples build, run, and produce outputs correctly.

Official
Advanced
amdamd
154

quark-onnx-eval-runner

Verify Quark ONNX skill routing, planning, artifacts, and recovery checks.

Official
Advanced
amdamd
154

quark-torch-router

Route AMD Quark user intents to the correct downstream skill or workflow.

Official
Advanced
ThalesGroupThalesGroup
19

agilab-testing

Execute targeted AGILAB tests across unit, smoke, and regression suites.

Official
Advanced