Skill of Skills
📄 skillActiveCuratedmedium

raullenchai/Rapid-MLX

by raullenchai

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Supported Platforms

🤖 Claude Code

Stars

2.7k

Skill Type

📖 Library & API Reference

Quality Score

142/200

License

Apache-2.0

Forks

338

Last Updated

Jun 11, 2026

Discovered

May 6, 2026

Validation

Passed

github.com/raullenchai/Rapid-MLX

Quality Breakdown

142/ 200

Content Signals

✓Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
â—‹Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
â—‹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.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

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

Risk Assessment

  • Repository contains .claude/ directory with custom commands and skills configuration, indicating Claude-specific persistent configuration modification
  • Presence of automation scripts (run_all_models.sh, run_eval.py) that could execute arbitrary code during benchmarking/evaluation
  • GitHub Actions workflows (ci.yml, publish.yml) that could potentially execute code during CI/CD pipeline
  • Multiple shell scripts in examples/ and evals/ directories that perform system-level operations
  • Setup and installation automation through Makefile and pre-commit hooks that modify system state