统一分析 paper、repo、dataset、blog 与技术笔记 unit；按 kind 路由到既有 evidence-first prepare/Agent-fill/verify 实现，保持历史 owner、偏好与确认回执身份不变。
kb 快捷命令入口（伪 CLI），用于把常用 research 操作统一成 kb 动词形式；当用户运行或对 AI 说 kb help/init/doctor/update/obsidian/status/next/find/add/ingest/review/reject/recall/resume/undo/restore 时使用。
管理 core 研究系统配置，包括资源画像、语言偏好、taxonomy seed、candidate pool policy 与自动化开关。
经验 + skill 演化记忆：capture lightweight learnings, redacted diagnostic summaries, optional private local-detailed records, confirmed habits/gotchas, and confirmation-gated retrospective improvement prompts.
把 paper / repo / dataset / blog source 先做 staging，再做去重与轻量 record 入库，不直接替代深分析。
Archive important technical route discussions into durable per-program notes, including conclusions, tradeoffs, open questions, and next validation actions.
Manage core experiment units, including plans, classified run logs, follow-ups, diagnosis categories, and confirmation-gated experiment conclusions.
负责 core idea unit 的生成、evidence-first analysis、陪练讨论、多候选管理、显式选择与归档。