Project overview
Oscar adds one of five politeness levels to Claude Code prompts, with an optional matching reply style or clean output. It also includes a benchmark scaffold for testing the cited paper’s method, while clearly noting that the original evidence came from a small GPT-4o multiple-choice study and may not generalize.
Repository facts
- Primary language
- Not detected
- License
- MIT
- Repository updated
- Apr 28, 2026
- Default branch
- main
Resource types
General skill
Use cases
Writing and editing
Platforms
Claude Code, Codex, and more