llama-cpp

70 / 100 · Review before installing

Check before installing.

By Tommy-yw/RunbookHermes (GitHub) · other · 513 stars · scanned at commit 7fd2b9a

llama.cpp local GGUF inference + HF Hub model discovery.

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 9 places.

skills/mlops/inference/llama-cpp/SKILL.md, line 60brew install llama.cpp
skills/mlops/inference/llama-cpp/SKILL.md, line 109`pip install llama-cpp-python` (CUDA: `CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python --force-reinstall --no-cache-dir`; Metal: `CMAKE_ARGS="-DGGML_ME
skills/mlops/inference/llama-cpp/references/server.md, line 81RUN apt-get update && apt-get install -y git build-essential

Show 6 more

skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 22sudo apt install nvidia-cuda-toolkit
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 37pip install cmake scikit-build-core
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 40CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python --force-reinstall --no-cache-dir
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 43CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python --force-reinstall --no-cache-dir
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 55CUDACXX=/usr/local/cuda/bin/nvcc CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 367CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python --force-reinstall

Runs commands on your computer

The author does not mention this.

Found in 8 places.

skills/mlops/inference/llama-cpp/SKILL.md, line 60brew install llama.cpp
skills/mlops/inference/llama-cpp/SKILL.md, line 64winget install llama.cpp
skills/mlops/inference/llama-cpp/SKILL.md, line 68git clone https://github.com/ggml-org/llama.cpp

Show 5 more

skills/mlops/inference/llama-cpp/SKILL.md, line 77llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0
skills/mlops/inference/llama-cpp/SKILL.md, line 81llama-server -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0
skills/mlops/inference/llama-cpp/SKILL.md, line 89llama-server \
skills/mlops/inference/llama-cpp/SKILL.md, line 98curl http://localhost:8080/v1/chat/completions \
skills/mlops/inference/llama-cpp/references/advanced-usage.md, line 165result = subprocess.run(

Sends data to these websites: api.openai.com

The author does not mention this.

Found in 6 places.

skills/mlops/inference/llama-cpp/SKILL.md, line 98curl http://localhost:8080/v1/chat/completions \
skills/mlops/inference/llama-cpp/references/server.md, line 52curl http://localhost:8080/v1/chat/completions \
skills/mlops/inference/llama-cpp/references/server.md, line 67curl http://localhost:8080/v1/chat/completions \

Show 3 more

skills/mlops/inference/llama-cpp/references/server.md, line 99curl http://localhost:8080/metrics
skills/mlops/inference/llama-cpp/references/server.md, line 102curl http://localhost:8080/health
skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 333from openai import OpenAI

Can call paid AI services billed to you

This is disclosed by the author in the skill's SKILL.md or README.

Found in 1 place.

skills/mlops/inference/llama-cpp/references/troubleshooting.md, line 333from openai import OpenAI

Safer alternatives

Low-risk skills in the same category (other) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'llama-cpp' ] || [ -L ~/.agents/skills/'llama-cpp' ]; then echo 'A skill folder named llama-cpp already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Tommy-yw/RunbookHermes' "$d" && git -C "$d" checkout --quiet '7fd2b9a75cf4930491e9af46a93bf4e5b3f3871e' -- 'skills/mlops/inference/llama-cpp' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/mlops/inference/llama-cpp' ~/.agents/skills/'llama-cpp' && 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/'llama-cpp' ~/.claude/skills/'llama-cpp' (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

The badge for Tommy-yw/RunbookHermes shows the score of its lowest-scoring skill.

SkillTrust badge for Tommy-yw/RunbookHermes

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Tommy-yw/RunbookHermes.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Tommy-yw/RunbookHermes/)

Score history

Date	Version	Score
2026-11-14	`7fd2b9a`	70