{"skill":{"slug":"test-time-compute-guide","displayName":"Test Time Compute Guide","summary":"Learn to enhance LLM performance using test-time compute with parallel sampling, sequential revision, and process reward models for better reasoning.","tags":{"ai":"1.0.0","latest":"1.0.0","llm":"1.0.0","reasoning":"1.0.0","test-time-compute":"1.0.0"},"stats":{"comments":0,"downloads":101,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775054353502,"updatedAt":1775055709973},"latestVersion":{"version":"1.0.0","createdAt":1775054353502,"changelog":"Initial release of test-time-compute-guide skill.\n\n- Introduces core concepts of test-time compute (TTC) and chain-of-thought (CoT) reasoning for LLMs.\n- Includes explanations of parallel sampling, sequential revision, process reward models, and self-consistency strategies.\n- Provides practical guidance on when to use different reasoning approaches based on question difficulty.\n- Features Python code examples demonstrating prompting, best-of-N sampling, and process-reward-guided beam search.\n- Lists required dependencies for implementation.","license":"MIT-0"},"metadata":null,"owner":{"handle":"robinyves","userId":"s17462cenv9g9acdcd8fj842ns840dyy","displayName":"Robinyves","image":"https://avatars.githubusercontent.com/u/262183440?v=4"},"moderation":null}