浏览 Erland366 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
5收录技能的仓库 Stars 合计
0仓库 Forks
1平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Turn experiment reports and development notes into summaries and reusable skills. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or requests for lessons...
Plan experiments or development tasks using past knowledge. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or questions like "What should we try next?"
Implement gradient accumulation that produces bit-identical results to standard batching. Use when: comparing GA vs non-GA runs, debugging training reproducibility.
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
Turn experiment reports and notes into summaries and new/updated result skills.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。