DSH Plugins Marketplace

DSH Plugins

Plugins

/

Tools & Capabilities

/

dsh-ross-ai-assistant

d

dsh-ross-ai-assistant

Manifest valid

Unofficial DSH fork of the AMD Ross AI Assistant. Upstream skills snapshot 2026.10.1; adds the DeepSeek Harness bundle, Settings page, and install docs.

UI (client)hasBundlePatch

AMD Ross

AMD Ross™ Agentic AI Assistant

Agent Skills GitHub Copilot Cursor Claude Code OpenAI Codex DeepSeek Harness License: MIT AND Apache-2.0

Agent skills for AMD FPGA/SoC development.

DSH fork. This repository adds DeepSeek Harness support to Xilinx/ross-ai-assistant. The DSH wrapper is 0.1.0; the bundled skills are the upstream 2026.10.1 snapshot. It is not an AMD release.

New here? Start with the Getting Started guide. See docs for FAQ, MCP reference, and support.

Quick Start

We recommend cloning this repository locally. It includes not only skills, but also docs and examples. In the install commands below, replace /path/to/ross-ai-assistant with the path to your local clone.

Prerequisites

Install one of the following from the AMD Ross Agentic AI Assistant download page:

ComponentDescriptionFollow-up installation
Vivado AI Extension (VS Code / Cursor)Includes the Vivado MCP server, the skills in this repository, and the amd-doc-search MCP configurationNone
Vivado MCP Server (Linux or Windows)The Vivado MCP server: Tcl command execution, project management, and synthesis/implementationConfigure the amd-doc-search MCP server, then install the skills in this repo as a plugin or individually

Use the MCP server for CLI clients, or the VS Code / Cursor extension for IDE setups — not both.

Install the amd-doc-search MCP server

The amd-doc-search MCP server searches AMD FPGA and Adaptive SoC documentation: user guides and device collaterals, and tool usage for Vivado, Vitis, embedded system software, and related products.

The Vivado AI Extension already includes this configuration. With the standalone Vivado MCP Server, add the server yourself.

For detailed installation instructions, see https://ross.amd.com/chat#setup.

Local knowledge base. If you want documentation search to stay on your own machine, use the local knowledge base instead of the hosted amd-doc-search service.

Install as a plugin

This repository is also an agent plugin: your local clone can be installed as a plugin, which adds every skill in one step. Updating is then a git pull of the clone.

DeepSeek Harness installs this fork as the @hidden-seed/dsh-ross-ai-assistant bundle from its Plugins page. The repository's package.json is the bundle manifest, and .dsh-plugin/ registers the skills/ directory with the Harness skill catalog. Open Settings → AMD Ross to configure the Vivado and documentation MCP servers.

Once installed, invoke the skills by name, for example /hls-optimize, and they call each other by those same names. Some clients list them under the plugin's name, amd-ross-agentic-ai-assistant; DeepSeek Harness registers this fork as @hidden-seed/dsh-ross-ai-assistant.

Choose one install method. If you install the plugin, do not also install the skills with npx skills add or by copying them. Every skill would then be loaded twice.

The plugin contains skills only. The Vivado MCP Server or the Vivado AI Extension from Prerequisites is still installed separately.

See Install as a plugin for the steps in your AI client and how to update.

Install skills (interactive)

Install Node.js to use the npx skills commands below.

Point npx skills add at your local clone (or an extracted release package):

npx skills add /path/to/ross-ai-assistant

This installs skills into the current workspace. Add --global to install into your home directory (~/.claude/skills/) so they are available across all workspaces.

Install all skills

npx skills add /path/to/ross-ai-assistant --all

Install all skills globally

npx skills add /path/to/ross-ai-assistant --all --global

Install a specific skill

npx skills add /path/to/ross-ai-assistant --skill hls-optimize

List available skills

npx skills add /path/to/ross-ai-assistant --list

Manual installation (no Node.js)

Copy desired skill folders to your agent's skills directory:

cp -r /path/to/ross-ai-assistant/skills/hls-optimize ~/.claude/skills/

Skills

Vivado

These skills require the Vivado MCP Server for live Vivado interaction.

SkillDescriptionExamples
vivado-simulate-rtlRun and diagnose RTL simulation across XSim and supported third-party simulators-
vivado-rtl-lintRun Vivado's RTL linter and report design issues with prioritized, code-level fixesmulti-violation
vivado-timing-methodology-checksRun timing methodology checks and analyze violationsmulti-violation
vivado-revision-controlManage Vivado project files under revision controlexport-ipi-project
vivado-ip-configuratorConfigure one Vivado IP cell from a natural-language descriptionisp-skill-comparison

Vitis HLS

SkillDescriptionExamples
hls-matlab-to-cppConvert MATLAB sample-based code to synthesizable C++ for HLSedge-detection, matlab-kernel-gemm, matlab-kernel-svd
hls-architectConvert input code to multi-stage HLS dataflow architecture—
hls-optimizeIteratively optimize HLS kernel against target performance/resource criteriaglobaltonemapping

These three skills are the primary entry points for HLS development. Each skill automatically invokes specialized helper skills (dataflow checks, burst inference, array partitioning, report extraction, etc.) as needed — you don't need to install or invoke helpers separately.

Build skill: hls-run-flow runs the HLS compilation pipeline (csim, csynth, cosim, implementation) and is called by the core skills above or can be invoked directly. Example: intro-matmul.

Vitis

This skill is beta. Run it in the Vitis IDE, or in another AI coding agent. The coding agent invokes Vitis with vitis -s.

SkillDescriptionExamples
vitis-embeddedCreate an embedded platform, application, and boot imageplatform, application, boot image

Hardware Debug

These skills debug live FPGA/SoC hardware via Vivado Hardware Manager Tcl.

SkillDescriptionExamples
hw-ila-debugInteract with ILA debug cores on live hardware: trigger, capture, and export waveform dataaxi-protocol-capture
hw-vio-debugRead input probes and drive output probes on live hardware via VIOaxi-register-rw

Vitis AI

These skills compile and optimize ONNX models for AMD NPU hardware with the VAIML compiler. Start with an orchestrator skill and let it load implementation skills and worker subagents as needed.

SkillDescriptionExamples
vai-quantization-guideMixed-precision quantization for AMD NPU (VINT8, BF16, hybrid)resnet50-quantize-vint8-bf16, vit-encoder-full-offload
vai-flag-configurationIteratively tune vitisai_config.json compiler flags—
vai-custom-opOrchestrate parallel custom AIE operator developmentmulti-input-multi-node-custom-op

Helper skills (vai-custom-op-implementation, vai-fe-args, vai-perf-analysis, and the other vai-* folders) are invoked by those orchestrators and by the workers in agents/.

Versions

Latest versionPublishedSize
0.1.0——

Comments

Loading…

Similar plugins

dsh-mattpocock-skills

by MAOLEIJIN

DSH bundle that vendors the full mattpocock/skills tree, preserves upstream invocation policies, and applies an exact-match DSH semantic overlay checked during automatic upstream synchronization.

Manifest valid

★ 0

MIT

JavaScript

Sep 17, 2026

dsh plugin --profile web add @maoleijin/dsh-mattpocock-skills

by NinjaSln-labs

DeepSeek Harness 插件:Cursor-as-subagent 提供方——一次本地 @cursor/sdk one-shot 运行、摘要优先结果、可无人值守的 Profile Bundle

Manifest valid

★ 0

↓ 353/wk

MIT

TypeScript

Oct 2, 2026

dsh plugin --profile web add dsh-subagent-cursor

by andrepontesmelo

The DSH productivity suite: plugins + agent skills for the DeepSeek Harness, installable in one command.

Tools & CapabilitiesManifest valid

★ 0

MIT

JavaScript

Sep 11, 2026

dsh plugin --profile web add @andrepontesmelo/dsh-suite

by qkycir-123

Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.

Tools & CapabilitiesManifest valid

★ 109

↓ 442/wk

MIT

TypeScript

Nov 15, 2026

dsh plugin --profile web add dsh-run2skill

by lau4tin1

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the

Manifest valid

★ 0

NOASSERTION

TypeScript

Oct 1, 2026

dsh plugin --profile web add dsh-skill-router

by MichengAI

DSH Skills Manager — 在 DeepSeek Harness 中统一加载并安全管理本机 Agent Skills · Load and safely manage local Agent Skills in DSH

Tools & CapabilitiesManifest valid

★ 582

↓ 50.9k/wk

Apache-2.0

JavaScript

Nov 18, 2026

dsh plugin --profile web add @michengai/dsh-skills-manager