xiaopaw-v2

Use this skill to search the internet using Baidu when the user asks about recent events, current information, news, prices, people, companies, technical documentation, or any topic that may require up-to-date data beyond the AI's training knowledge. Supports filtering by time range (week/month/semiyear/year) and specific websites. Returns titles, URLs, and content summaries for each result.

Use this skill to persist important information from the conversation to workspace files so it survives across sessions. Activate proactively (without waiting for user to say "remember this") when: - User expresses a preference or habit ("I prefer...", "always...", "don't...") - User corrects Agent behavior and states how it should work instead - A key fact emerges that matters for future sessions (project milestone, decision made, important date, contact info) - User approves an approach ("let's do it this way going forward") Do NOT activate for: one-time tasks, Agent's own reasoning, info already in user.md.

当需要回忆任何历史对话内容时，主动使用此 skill——不需要用户说"去搜索"， 只要话语中隐含对历史信息的依赖，就立即触发： - 用户引用过去的结论或操作（"上次你说的"、"之前的分析"、"上周五操作时的结论"、"根据我们之前讨论的"） - 用户询问过去做过的事（"上次那个航班"、"之前帮我查的 XX"、"你还记得吗"） - 需要找到用户在历史对话中产生的临时结论（分析结论、操作决策、临时状态、项目进展） - 用户说"复盘"、"回顾"、"对比上次"等需要历史上下文才能回答的请求 - 回答"该不该 XX"类决策问题，且所需背景（历史分析结论、历史操作记录等）未在当前对话出现，且不是稳定事实（稳定事实如持仓/成本应在 workspace 文件中，通过 Bootstrap 注入） 支持语义搜索（模糊意图）、关键字搜索（精确词）、混合搜索（推荐）。