據 AlphaMoat 統計,截至 2026-09,ResearchMonitor 累計下載 3,183 次、獲 1 個星標,在全部 5,078 個 AI 技能中排名第 3,586 位,在「專業領域」分類(465 個)中排名第 294 位。

累計安裝

288

累計下載

3183

星標

全站排名

#3,586

全站前 71% · 「專業領域」前 64%

平台	累計安裝	累計下載	星標	評論
ClawHub ↗	96	2920	1	-
SkillHub ↗	288	3183	1	—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

工作流：讀取 research_config.json 中的主題與上次檢查日期（無配置則先詢問並用 --add-topic 儲存）；每天檢查一次，當天已查過就不重複打擾；用 search_web 按主題檢索新論文、即將召開的會議與新期刊Issue（可查 arXiv、IEEE Xplore、Google Scholar 等）；用 --check-seen 過濾已見條目；如果沒有重要新內容，就不要打擾使用者；有新內容時輸出簡短報告（標題、來源 URL、一句話相關性摘要），再 --mark-seen 並 --update-date。指令碼支援新增/列出主題、更新檢查日期與已見記錄。

資料釋出於 2026-10-27

可以用來做什麼

按配置的科研主題定期檢索新論文與會議
過濾已見條目避免重複報告
生成帶標題、來源與一句話摘要的簡報

什麼時候用

想持續跟進某個研究方向的新進展時
不想錯過領域內重要會議與期刊更新時
希望每天只收到'有新東西才打擾'的簡報時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

幫我加一個研究主題：diffusion models。

今天領域裡有什麼新論文值得看嗎？

列出我當前配置的所有研究主題。

月度資料趨勢

累計下載3183

星標1

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份	累計下載	環比	星標
2026-09	3183	—	1
2026-08	2867	+2.6%	1
2026-07	2794	+4.8%	1
2026-06	2665	+2.5%	1
2026-05	2599	—	1
2026-03	2296	—	1

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

2.5 KB · ClawHub v0.1.2

---
name: ResearchMonitor
description: Monitors research topics for new papers, conferences, and journals.
---

# ResearchMonitor

This skill helps you keep the user updated on their specific research field.

## Workflow

展開全部(共 51 行)


1.  **Check Configuration**:
    -   Read `research_config.json` in this directory to find the user's research topics and last checked date.
    -   If the file doesn't exist or topics are empty, ask the user what research topics they are interested in and save them using `scripts/daily_briefing.py --add-topic "topic"`.

2.  **Daily Check**:
    -   Get the current date.
    -   Compare with `last_checked` in `research_config.json`.
    -   If already checked today, do nothing unless explicitly asked.

3.  **Perform Search**:
    -   For each topic, use `search_web` to look for:
        -   "new research papers [topic] [current month/year]"
        -   "upcoming conferences [topic] [current year]"
        -   "new journal issues [topic] [current month/year]"
        -   Check specialized platforms like arXiv, IEEE Xplore, Google Scholar (via web search), or X (Twitter) if relevant.

4.  **Filter & Analyze**:
    -   For each potential item found, use `scripts/daily_briefing.py --check-seen "URL or Unique Title"`.
    -   If it returns "true", SKIP IT.
    -   Compare found items with what might have been seen yesterday (this requires some memory or just checking if the publication date is very recent, e.g., last 24-48 hours).
    -   **CRITICAL**: If there is *nothing significantly new* (no new major papers, no new conference announcements), **DO NOT BOTHER THE USER**.

5.  **Report**:
    -   If new items are found, compile a brief markdown report.
    -   Include:
        -   **Title**: News/Paper Title
        -   **Source**: URL/Journal Name
        -   **Summary**: 1-sentence summary of why it's relevant.
    -   Present this to the user.
    -   Mark the items as seen using `scripts/daily_briefing.py --mark-seen "URL or Unique Title"`.
    -   Update the `last_checked` date using `scripts/daily_briefing.py --update-date`.

## Scripts

-   `python scripts/daily_briefing.py --add-topic "topic"`: Adds a new research topic.
-   `python scripts/daily_briefing.py --list-topics`: Lists current topics.
-   `python scripts/daily_briefing.py --update-date`: Updates the last checked timestamp to now.
-   `python scripts/daily_briefing.py --check-seen "ID"`: Checks if an item ID (URL/Title) is already in memory.
-   `python scripts/daily_briefing.py --mark-seen "ID"`: Marks an item ID as seen.