en un clic
more-news-briefing
more-news-briefing contient 3 skills collectées depuis bingyunjiang, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Create recurring multi-topic news briefings with customizable cadence, topic mix, ranking, verification, source-backed summaries, and optional claim interrogation, insight extension, signal commentary, and cross-run tracking. Use when Codex needs to collect, deduplicate, rank, verify, summarize, or prepare daily, weekly, or custom-cycle digests across general news, AI, politics, business, culture, sports, and user-defined subjects, including requests for deeper interpretation after the news. Default to full mode, which runs the complete collect-sort-verify-write workflow. On a user's first use, resolve the topic contract before search begins, and explicitly help the user choose broad themes or define specialty topics with enough scope, keywords, geography, and watch priorities to support repeatable monitoring. This skill should work as a standalone workflow by default, and only treat other installed skills as optional enhancements.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
Real-time search engine supporting web search, vertical domain search (23 domains), parallel batch search, and URL content extraction.