菜单
SkillsMP 已收集 muratcankoylan/book-training 中的 4 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 4 / 4 个已收集 Skill。
End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text extraction, intelligent segmentation, synthetic instruction generation, Tinker-compatible output, LoRA training, and validation.
原文语言：英语
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
原文语言：英语
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
原文语言：英语
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.
原文语言：英语