메뉴
Search and archive significant global events (7-day window). Topics: international conflicts, trade/China policy, and AI/Agent updates. Include entity tracking, semantic dedupe against news.jsonl, and atomic archival via recorder.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
统一记录 knowledge/news/lifelog/agent_kernel_memory/tasks 的通用 JSONL 记录技巧，支持新增/更新/删除（CRUD）、UUID 自动 id 与 auto record 到 lifelog。
在 Windows 中创建/管理定时提醒（通知方式）。适用于用户要求“定时提醒/到点提醒/每天提醒/每周提醒”等，并需在创建计划任务前征求确认。默认使用 BurntToast 通知（当前用户会话）。
在对话中识别可复用流程并提议沉淀为 skill。适用于出现明确步骤、重复任务、或用户表达“以后都这样做/自动化”的场景。
评估、评分并改进 .codex/skills 下的已有技能。适用于用户要求审查、优化或重构 skills 的场景。
| name | news-fetch |
| description | Search and archive significant global events (7-day window). Topics: international conflicts, trade/China policy, and AI/Agent updates. Include entity tracking, semantic dedupe against news.jsonl, and atomic archival via recorder. |
用于一次性抓取“最近7天”的重大国际事件/政策/AI Agent 动态，并落库到 news 模块。
动态日期锚定
确认范围
scope.topics多路并行检索（按 Topic 拆分 Query）
web.run，时间窗限定最近 7 天候选列表 → 精选集合（List + Set）
语义去重（Smart Dedupe）
workspace/records/news/news.jsonl 历史记录dedupe 字段（策略+剔除数量）原子化写入（Atomic Storage）
news 记录（便于检索/RAG）news_digest，仅保留原子化条目recorder 脚本：record_jsonl.py --record-type news--extra 写入结构化内容News Fetch 自用 TODO
workspace/records/news/news-fetch_todo_list.mdworkspace/records/news/news_archive/YYYY/MM/DD/news-fetch_todo.mdList / Set 文件位置
workspace/records/news/staging_candidates.jsonlworkspace/records/news/curated_set.jsonl归档 List / Set（完成任务后）
staging_candidates.jsonl 与 curated_set.jsonl 归档到：
workspace/records/news/news_archive/YYYY/MM/DD/staging_candidates.jsonlworkspace/records/news/news_archive/YYYY/MM/DD/curated_set.jsonl# 1) 初始化/清空 list 与 set
"" | Set-Content -Path "workspace/records/news/staging_candidates.jsonl" -Encoding utf8
"" | Set-Content -Path "workspace/records/news/curated_set.jsonl" -Encoding utf8
# 2) 初始化 TODO
@'
# News Fetch TODO
- 分 Topic 检索
- 语义去重
- 写入 news（原子化）
- 补充 coverage_gap
- 产出摘要（可选）
'@ | Set-Content -Path "workspace/records/news/news-fetch_todo_list.md" -Encoding utf8
{
"date": "YYYY-MM-DD",
"category": "AI 自动判定（可随主题变化）",
"summary": "...",
"tags": ["news", "ai", "agent"],
"sources": [{"name":"...","url":"..."}],
"entities": ["..."],
"source_rank": "official|media|preprint"
}
$extra = @'
{"time_window":{"start":"2026-01-13","end":"2026-01-19","timezone":"local"},"scope":{"topics":["国际冲突","贸易政策","中国政策","AI与Agent"],"entities_watch":["OpenAI","Google/DeepMind","阿里","字节","腾讯","智谱","清华相关实验室","幻方量化"]},"dedupe":{"strategy":"title+source+date","dropped":0}}
'@
python .\\.codex\\skills\\recorder\\scripts\\record_jsonl.py --record-type news --title "单条新闻标题" --summary "单条新闻摘要" --tags "news,ai,agent" --module "news" --source "web" --extra $extra