token-alignment
Debug token-level penalty alignment issues. Use when banned tokens aren't being penalized correctly or when investigating tokenizer edge cases.
Browse published AI skills maintained by brightlikethelight. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
2Repository stars across indexed skills
2Repository forks
0Average repository stars per indexed skill
1Repository stars may repeat across skills from the same repository.
Debug token-level penalty alignment issues. Use when banned tokens aren't being penalized correctly or when investigating tokenizer edge cases.
Implement token-level rewards in TRL's GRPOTrainer. Use when modifying reward computation or debugging reward tensor shapes.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.