“machine learning”

Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems.

会话开始或不确定该用哪个笔记技能时触发：先读本技能完成路由，再动手。任何笔记库任务的第一步。

This skill should be used when working with genomic interval data (BED files) for machine learning tasks.

把新材料（课堂记录、截图转写、论文、网页）整理成规范笔记并入库时触发。

出现断链、孤儿笔记、新笔记未入索引，或用户要求梳理笔记间关系时触发。

用户要求润色、校对、统一术语或改善某篇/某批笔记的文字表达时触发。只改语言不动技术结论。

dontbesilent 交互式学习。把一个课题拆成连续学习文章，根据用户在上一篇中的反馈调整下一篇的深度、角度和节奏。 触发方式：/dbs-learning、/dbs-learn、/交互式学习、「带我学一个课题」「继续下一篇」「根据我的反馈写下一篇」 Interactive learning workflow.

Adapt pstack delegation, role configuration, skill paths, verification, and session handling to Claude Code or Codex.

每周定时或用户要求"自迭代/再优化一轮"时触发。全自动：Propose→Probe→闸门→自动采纳/否决→提交→摘要推送，不等人工确认。

Expert data scientist for advanced analytics, machine learning, and statistical modeling.

笔记含公式且要修改正文、或用户报告公式渲染/书写问题时触发。公式是红线资产，先守后改。

用户要求给笔记排序、分优先级、找最值得学/最直观的篇目，或站点数据刷新时触发。全库价值排序 + 教学成果检测。

任何一批改动交付前触发。独立审校：只看 diff 挑错，不参与改写，与执行者分离。

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.

Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…

Explain a subsystem's behavior from source, callers, data structures, and runtime evidence.

Challenge a code change with independent adversarial reviewers and consolidate evidence-backed findings.

Explain how to install, configure, or choose a pstack workflow in Claude Code and Codex.

Check pstack installation and configure role effort and panel size for Codex and Claude Code.

Author or update a portable pstack skill with precise triggers, self-contained resources, and realistic behavioral verification.

Review a branch, working diff, or named files for reachable defects and missing behavioral coverage.

Persist collection evidence and plan unread room windows separately from learned facts.

Email-observation learning — voice-learn and task-completion producers plus learning-digest review tools.

Read, run and grow a persistent skill library of verified, executable sub-task skills that carries what agents learn across sessions and tasks on the same…