skills/mlx-brain/SKILL.md
MacBook MLX local LLM orchestration skill for running lightweight on-device models via command line. Use when you need local inference, private/offline generation, model routing (qwen/coder), or remote invocation on MacBook Pro nodes. Triggers on MLX, local LLM, on-device inference, qwen, coder model, and MacBook model execution workflows.
npx skillsauth add kjaylee/misskim-skills mlx-brainInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
# venv 이미 생성됨: $HOME/mlx-env
# MLX 이미 설치됨
# 테스트
$HOME/mlx-env/bin/python3 $WORKSPACE/misskim-skills/mlx-brain/run.py "안녕?"
# 맥북에서 LLM 실행
clawdbot nodes invoke --node "MacBook Pro" --command "system.run" \
--params '{"command":"$HOME/mlx-env/bin/python3 $WORKSPACE/misskim-skills/mlx-brain/run.py \"안녕?\""}'
# JSON 입력
echo '{"prompt":"안녕?","model":"qwen"}' | \
clawdbot nodes invoke --node "MacBook Pro" --command "system.run" \
--params '{"command":"$HOME/mlx-env/bin/python3 $WORKSPACE/misskim-skills/mlx-brain/run.py --json"}'
qwen: Qwen2.5-7B-Instruct-4bit (메인)coder: Qwen2.5-Coder-7B-4bit (코딩)testing
게임 아이디어를 검토해 와우 팩터 5개를 추가하고, 스펙→TC→구현→QA→런칭까지 한 번에 밀어붙이는 일일 게임 런칭 써클. 기존 자동 게임 파이프라인을 대체/승격할 때 사용.
data-ai
Advanced YouTube analysis, transcripts, and metadata extraction.
development
Modern web design engineering skills including design tokens, advanced UI/UX methodologies, accessibility, and game-specific UI patterns. Use for building commercial-grade, performant, and accessible web interfaces.
development
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".