ワンクリックで
paper-triage
Batch paper screening and classification. Triggers on "筛一下", "triage", "哪些值得看", "帮我筛", "batch screen".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Batch paper screening and classification. Triggers on "筛一下", "triage", "哪些值得看", "帮我筛", "batch screen".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Citation chain exploration. Triggers on "引用链", "谁引了", "citation", "参考文献", "这篇引了谁".
Morning paper reading workflow. Triggers on "start my day", "今天看什么", "morning digest", "每日推荐".
Deep analysis of a single paper. Triggers on "分析这篇", "deep dive", "这篇论文讲了什么", paper ID or arXiv ID input.
Literature survey and review workflow. Triggers on "survey", "综述", "这个方向有什么", "literature review", "related work".
AI research paper intelligence — router skill that detects user intent and delegates to the appropriate workflow. Triggers on paper, arxiv, digest, research, 论文, arXiv IDs, ML method names, or academic research questions.
Research trend analysis and insight generation. Triggers on "趋势", "trend", "这个方向火不火", "research insight", "方向分析".
SOC 職業分類に基づく
| name | paper-triage |
| description | Batch paper screening and classification. Triggers on "筛一下", "triage", "哪些值得看", "帮我筛", "batch screen". |
Context carry-over:
paper_auto_triage(paper_ids=[...])paper_auto_triage(top_n=5)Credibility check: For papers in the "important" bucket, call paper_credibility_batch(important_ids) to add credibility signals.
Present the three buckets as tables:
重要: | # | 标题 | 评分 | 入选理由 | venue | code | 复现风险 | 待读: | # | 标题 | 评分 | 简评 | 跳过: | # | 标题 | 评分 | 跳过理由 | 结论: 为什么这几篇最值得关注,关联用户 profile 说明
[FORK] "这是按你 profile 的分类,同意吗?要调整哪些?"
Move papers between buckets per user's instruction, then:
paper_reading_status(important_ids, "important") for confirmed important paperspaper_reading_status(to_read_ids, "to_read") for to_read papersApply the auto-triage result directly:
After marking, auto-save: call paper_save_report(report_type="triage", content=<report markdown>, filename="{topic}-{YYYY-MM-DD}.md") using triage-template.
[CONTEXT-AWARE FORK] — Based on the triage result, suggest next steps:
If important bucket has papers with PDFs available: "已标记完成,筛选报告已保存至 {path}。\n💡 下一步建议:\n1. 批量下载 {N} 篇重要论文的 PDF\n2. 深入分析 [{top_important_title}]({score}分)\n(说编号或告诉我你想做什么)"
If important bucket has papers but no PDFs: "已标记完成,筛选报告已保存至 {path}。\n💡 下一步建议:\n1. 深入分析 [{top_important_title}]({score}分)\n2. 搜索并下载这些论文的 PDF\n(说编号或告诉我你想做什么)"
If important bucket is empty but to_read has papers: "没有特别突出的论文,但有 {N} 篇值得一读。\n💡 下一步建议:\n1. 看看 [{top_to_read_title}] — 评分最高的待读论文\n2. 换个方向搜索\n(说编号或告诉我你想做什么)"
If all papers are skip: "这批论文跟你方向关联不大。\n💡 下一步建议:\n1. 调整 research profile — 可能关键词需要更新\n2. 换个方向搜索\n(说编号或告诉我你想做什么)"
If user provides specific paper IDs or says "筛这些":
paper_auto_triage(paper_ids=[...]) with the specific IDspaper_auto_triage.