SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

skillsamd/skills

Provides an AMD-maintained skill catalog for AI agents, so agents can call officially vetted AMD hardware knowledge when…

No ratings yet Rate this skill
Stars411
Forks40
Watchers411
Open Issues51

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/amd/skills.git

OverviewOverview

Key Features

Provides an AMD-maintained skill catalog for AI agents, so agents can call officially vetted AMD hardware knowledge when doing model inference, performance tuning, and code generation on AMD GPUs and the ROCm software stack. Key capabilities include: 1. AMD hardware adaptation knowledge injection: packages AMD GPU architecture, ROCm runtime, and acceleration library usage points into agent-loadable skill entries, so generated code targets AMD platforms instead of generic CUDA patterns; 2. Official skill catalog distribution: organizes AMD official skills in a unified catalog that agents can search and activate on demand, avoiding guesswork on hardware parameters and interfaces; 3. Inference and tuning workflow guidance: covers the steps to get model inference running on AMD platforms, locate performance bottlenecks, and adjust runtime parameters, reducing trial and error.

Use Cases

Deploying and tuning AI inference services on AMD GPU/ROCm, configuring AMD official skill packs for AI agents, writing training and inference scripts targeting AMD hardware, troubleshooting operator and VRAM issues on AMD platforms.

Target Roles

AI / Algorithm Engineer, DevOps / Operations Engineer, Backend Developer, Full-stack / Indie Developer.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID2096
Data sourceGitHub
Repositoryamd/skills
CategoryAI & Agent Skills / AI Infrastructure & Hardware Acceleration
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1204992108
Node IDR_kgDOR9K4bA
Rank#1510 (position within the source ranking)
Site-wide popularity rank#1706 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-252026-10-112026-09-25 · 3762026-10-11 · 411
  • Now411
  • Previous point · 09-25 376
  • vs previous point +35
  • 2 data points 16 days
0102030402026-09-252026-10-112026-09-25 · 372026-10-11 · 40
  • Now40
  • Previous point · 09-25 37
  • vs previous point +3
  • 2 data points 16 days

TimelineTimeline

Repository created2026-04-08 14:27:567 months ago
Data last updated2026-10-26 12:15:2723 days ago
Last commit2026-10-09 16:06:491 months ago

CommitLatest commit

Version [latest] committed by amd-lalithnc. Update Category: Codebase Iteration & Routine Maintenance. Commit details: Federate `serving-llms-on-epyc` from `amd/ZenDNN-pytorch-plugin` (#234). This update updates core functional modules and advances project iteration.

880babb vlatest amd-lalithnc 2026-10-09