omh-inference-serving
90 / 100 · Low risk
Fine to try.
[omh] Self-hosted LLM serving on GPUs: choose the serving engine and quantization from decision tables, prepare deployment as an idempotent runbook with observed-only verification, and measure the endpoint with the standard TTFT/TPOT/goodput protocol. Use when the user says: inference-serving, inference serving, serve this model, serve the model, model serving, serving endpoint, vllm, llama.cpp.
What this skill can do
Changes files outside its own folder
Other copies in this repository
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'omh-inference-serving' ] || [ -L ~/.agents/skills/'omh-inference-serving' ]; then echo 'A skill folder named omh-inference-serving already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/rlaope/oh-my-hermes' "$d" && git -C "$d" checkout --quiet '55c802b39cd9e41794d6d0946f314e4de3d0504e' -- 'skills/omh-inference-serving' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/omh-inference-serving' ~/.agents/skills/'omh-inference-serving' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'omh-inference-serving' ~/.claude/skills/'omh-inference-serving' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/rlaope/oh-my-hermes/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | 55c802b | 90 |
| 2026-11-08 | b06663c | 90 |
| 2026-11-07 | 0f98267 | 90 |