hello-rocm

hello-rocm is a Local & open models skill for AI agents, published by datawhalechina in the hello-rocm repository on GitHub. Skillspace rates hello-rocm D (66/100) and it passed the safety scan; the rating is based on static analysis only.

hello-rocm 开源教程项目：AMD ROCm 上大模型环境、部署、微调与算子/Infra。 当用户询问 AMD GPU、ROCm、Windows/Linux 上本地 LLM 推理与部署、vLLM/Ollama/LM Studio、 LoRA 微调、HIP/RCCL、hello-rocm 仓库结构、学习顺序或贡献规范时，必须加载并遵循本 Skill。

Grade
D
Quality
66 / 100
Safety
Passed
GitHub stars
143

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubdatawhalechina/hello-rocm

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections
Scope
Repo-internal: written for the repository it lives in. Describes the hello-rocm repo layout, learning path, contribution rules

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Local & open models

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.