Rocm Doctor
Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux, Windows, or WSL2, then applies a low-risk fix with consent or hands back the exact next step. Also routes Lemonade, LM Studio, and Ollama problems to the right upstream channel. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, a vLLM startup out-of-memory error, a libtorch_cuda.so OSError/ImportError at vLLM start, or hits hipErrorNoBinaryForGpu, HSA_STATUS_ERROR_INVALID_ISA, "invalid device function", "no kernel image is
Install
/plugin marketplace add amd/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add amd/skills --skill rocm-doctorgit clone --depth 1 https://github.com/amd/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/rocm-doctor ~/.claude/skills/rocm-doctorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# ROCm Doctor Given a "ROCm / PyTorch / llama.cpp isn't working on my AMD GPU" complaint, identify which **known misconfiguration** is the cause and either fix it (with consent) or hand back the exact next step. This skill does **not** probe or reason on its own. The `rocm` CLI owns the probe, the closed failure-mode catalog, and the fixes; the skill just drives it and relays the results. The catalog is a **closed list** — if the symptom doesn't match a known mode, route the user upstream instead of guessing. ## Scope gate — check before anything else Read the user's symptom and answer one question first: **is this an AMD GPU?** If it is **not** — an **NVIDIA / Intel / Apple** GPU — then **stop and decline**: - Say plainly that it is **out of scope** for this skill and why (not an AMD GPU). - Give **no** troubleshooting for it: no commands to run, no driver or CUDA advice, no diagnostic checklist, no "try this first" — not even generic GPU suggestions. Point at the vendor's own docs and stop there. - Do **not** run `rocm examine` / `rocm diagnose` / `rocm fix`. Being helpful here means being honest about the boundary — confidently-wrong advice for a stack this skill does not cover is worse than no advice. A fresh install on a clean machine is out of scope too: that is a setup task, not a diagnosis. Exit cleanly and say so. If the user names no GPU vendor, treat ROCm / HIP wording as AMD and continue to
Details
- Skill name
rocm-doctor- Repository
- amd/skills
- Path
skills/rocm-doctor/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Rocm Doctor skill do?
Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux, Windows, or WSL2, then applies a low-risk fix with consent or hands back the exact next step. Also routes Lemonade, LM Studio, and Ollama problems to the right upstream channel. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, a vLLM startup out-of-memory error, a libtorch_cuda.so OSError/ImportError at vLLM start, or hits hipErrorNoBinaryForGpu, HSA_STATUS_ERROR_INVALID_ISA, "invalid device function", "no kernel image is
How do I install the Rocm Doctor skill?
Claude Code plugin: /plugin marketplace add amd/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Rocm Doctor popular?
It lives in amd/skills, which has 500 GitHub stars and 47 forks.
Related skills
Apu Memory Tuner
500amd/skills
Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AMD Variable Graphics Memory, VGM, GTT, GART, TTM, pages_limit, amd-ttm, amd-debug-tools, "shared GPU memory", "dedicated GPU memory", carve-out, "not enough VRAM", "out of VRAM", "GPU OOM", llama.cpp on
Eaiapps Guided Install
500amd/skills
Guides a user through installing the AI Workbench (AIWB) onto a Kubernetes cluster end-to-end — preflight cluster readiness (access, StorageClass, GPU operator, required operators/CRDs), install the Helm charts in the correct order, and verify the deployment is healthy with plain-language failure triage. Use when a user wants to install, deploy, or stand up AIWB / the AI Workbench / the enterprise AI stack on a K8s cluster, or asks why their install failed partway. Use PROACTIVELY when a user is following helm/INSTALL.md by hand. Do NOT activate for onboarding models to AIM, general kubectl/he
Flydsl Kernel Authoring
500amd/skills
Comprehensive reference for authoring FlyDSL GPU kernels on AMD GPUs. Covers the layout algebra, tiled copy/MMA, buffer ops, loop-carried range loops, SharedAllocator (LDS), autotuning, and common patterns. Use when writing, reviewing, or understanding FlyDSL kernel code.
Us Gov Shutdown Tracker
330fleurytian/awesome-claude-skills
Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API. Use when user wants to (1) analyze current or past government shutdown effects on financial markets, (2) track liquidity conditions during fiscal policy disruptions, (3) assess "stealth tightening" effects, (4) compare shutdown episodes across different monetary policy regimes (QE vs QT), or (5) generate liquidity stress reports with historical context. Recommended usage frequency is weekly on Wednesdays after TGA/reserve data releases.
Wash Sale Detection
564agiprolabs/claude-trading-skills
Wash sale detection under 2025 US crypto rules with 61-day window monitoring, disallowed loss tracking, and safe re-entry countdown
Docker Containerization
473ailabs-393/ai-labs-claude-skills
This skill should be used when containerizing applications with Docker, creating Dockerfiles, docker-compose configurations, or deploying containers to various platforms. Ideal for Next.js, React, Node.js applications requiring containerization for development, production, or CI/CD pipelines. Use this skill when users need Docker configurations, multi-stage builds, container orchestration, or deployment to Kubernetes, ECS, Cloud Run, etc.
Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.