How do I install the Local Dev Amd skill?

Run npx skillmds@latest add tomevault-io/local-dev-amd-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Local Dev Amd safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Local Dev Amd?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Local Dev Amd free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Local Dev Amd?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Local Dev Amd by tomevault-io — Agent Skill

Name: Local Dev Amd
Author: tomevault-io

Local Dev Amd

Builds Docker images, starts local servers, and runs smoke tests for the AMD/ROCm development environment. Use when validating changes locally on AMD hardware, building AMD container images, or running AMD-specific smoke and explicit runtime checks.

tomevault-io Updated Sep 17, 2026

File contents

Local Dev AMD

Trigger

The primary skill needs amd-local build/serve/smoke validation

Required Surfaces

local_smoke

Conditional Surfaces

local_e2e

Stop Conditions

AMD-local smoke cannot be run or platform image mapping is unavailable

Gotchas

Keep real AMD deployment references out of the default context path unless the task actually needs real-model deployment details.

Workflow

Read AMD-local docs and environment config to understand the AMD build setup
Build the AMD image with make agent-dev ENV=amd
Start the local server with make agent-serve-local ENV=amd
Run smoke tests with make agent-smoke-local to validate the build
Verify the default AMD smoke config starts successfully without unexpected fallbacks

Must Read

Standard Commands

make agent-dev ENV=amd
make agent-serve-local ENV=amd
make agent-smoke-local
make agent-serve-local ENV=amd AGENT_SERVE_CONFIG=deploy/recipes/balance.yaml

Acceptance

The default AMD smoke config starts successfully
AMD image/platform behavior does not fall back unexpectedly
When real AMD model deployment is in scope, the agent uses deploy/amd/README.md and deploy/recipes/balance.yaml as the primary reference instead of inventing a new ROCm setup path

Source: vllm-project/semantic-router — distributed by TomeVault.

Frequently asked questions