Skill comparison

Compare agent skills before installing.

Put high-signal skills side by side and inspect quality, adoption, freshness, install readiness, use-case fit, and warnings in one place.

Comparing 2 skills

Use this as a shortlist, then open the skill detail page before adopting.

Add more skills

Decision summary

Pmetal is the strongest overall pick here because it has a 70/100 readiness score and fits Local desktop.

Strongest overall

Pmetal

Prototype with this skill first; keep a fallback candidate ready.

Fastest prototype

quark-torch-llm-ptq

Best first install candidate based on install readiness and adoption.

Freshest repo

quark-torch-llm-ptq

Most recent maintenance signal among this shortlist.

SignalPmetal

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

quark-torch-llm-ptq

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request execution approval, and produce a quantized model. Applies to Llama, Qwen, Mistral, and similar transformer LLM requests involving FP8, INT4, or another Quark scheme. Does not handle .onnx model inputs or ONNX PTQ.

Quality
71/100
Strong
67/100
Promising
Decision verdict
70/100
Prototype first

Prototype with this skill first; keep a fallback candidate ready.

66/100
Prototype first

Prototype with this skill first; keep a fallback candidate ready.

Adoption297 stars
Verified outcomes are shown on each skill page
395 stars
Verified outcomes are shown on each skill page
FreshnessJun 5, 2026Oct 7, 2026
Use-case fit
Workflow fit
Platform hintsRust, Machine Learning, Claude CodeClaude Code
WarningsNo OpenAgentSkill engagement data yetNo OpenAgentSkill engagement data yet
Best forLocal desktop workflows · Claude Code teams · builders willing to evaluate younger projectsRAG and knowledge workflows · Claude Code teams · builders willing to evaluate younger projects
Not ideal forteams that need a vendor-supported SLA · high-compliance environments without internal security reviewteams that need a vendor-supported SLA · high-compliance environments without internal security review
OpenAgentSkill engagement0 views
0 install copies
0 views
0 install copies
Install
$ npx skills add Epistates/pmetal
$ npx skills add amd/skills --skill quark-torch-llm-ptq