📄 skillActivePromisinglow

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Supported Platforms

🔧 Generic

Stars

16.4k

Skill Type

📖 Library & API Reference

Quality Score

92/200

License

Apache-2.0

Forks

1.4k

Last Updated

Jun 11, 2026

Discovered

Apr 16, 2026

Validation

Passed

github.com/jundot/omlx

Quality Breakdown

92/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

○Verification/Safety+20

✓Code Examples+15

○Composability+15

Repo Health

✓Recent Activity+15

✓Scripts/Automation+10

✓Real Usage (Issues)+10

✓Single Responsibility+10

✓Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

low

Standard permissions only. Safe for general use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Repository is a legitimate macOS LLM inference application with clear documentation and Apache 2.0 license
No shell/bash/exec system capabilities requested in file structure
No bootstrap scripts, install automation, or elevation mechanisms detected
No multi-agent spawning or orchestration patterns
No persistent configuration modification of AI tool settings (.claude/, MEMORY.md, etc.)
No offensive security, pentesting, or exploit-related content