agentleFS
CHB-learnerCHB-learner/scholarflow-claude-skills/skills/daily-papers/SKILL.md

daily-papers

Skill4 starsChanged 6 months agoMITView on GitHub

每日论文推荐的一句话总入口。用户说"今日论文推荐""过去3天论文推荐""过去一周论文推荐" "最近3天论文""看看这周有啥论文"时使用。

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. huangkiki/dailypaper-skills★ 1.3k12% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Files
SKILL.md

每日论文推荐

这是面向用户的一句话入口。

识别用户意图

  1. 识别时间范围:
    • 今日论文推荐、每日推荐、今日论文 -> 当天
    • 过去3天论文推荐、最近3天论文 -> 3 天
    • 过去一周论文推荐、看看这周有啥论文 -> 7 天
    • 过去两个月 -> 60 天
    • 其他 N 天 -> 用户指定的 N
  2. 识别关键词:
    • 如果用户指定了关键词(如"大模型评测"、"扩散模型"),使用用户提供的
    • 如果用户没有指定,从 daily.keywords 配置获取默认关键词;旧配置 daily_paper_keywords 仍兼容

执行流程

路径契约(必须)

每日论文只能写入一个日期目录:

{DAILY_PAPERS_PATH}/{YYYY-MM-DD}/

例如 Dailypaper/2026-05-20/。禁止创建或写入任何月份/日期混合目录,包括:

  • Dailypaper/5月/0520/
  • Dailypaper/5月/520/
  • Dailypaper/{月份}/{DD}/
  • Dailypaper/{月份}/{MMDD}/

执行前必须显式设置并复用:

DATE_DIR="$(date +%F)"
DAILY_RUN_DIR="{DAILY_PAPERS_PATH}/$DATE_DIR"
META_DIR="$DAILY_RUN_DIR/_meta"
RECOMMENDATION_FILE="$DAILY_RUN_DIR/$DATE_DIR-论文推荐.md"

后续抓取、点评、笔记、图片、_meta 都只能使用这些变量。不要手写 5月、0520、520 这种路径。

如果发现同一天的旧式目录已经存在,先停止写入并迁移到 Dailypaper/{YYYY-MM-DD}/;如果目标目录已有内容,保留目标目录,不要把新内容写回旧式目录。

Step 1: 关键词丰富化

对每个原始关键词进行丰富化(英文 + 中文变体):

原始关键词丰富化关键词
大模型评测LLM evaluation, large language model benchmark, foundation model evaluation, 模型评测, 大模型评估
扩散模型diffusion model, score-based model, diffusion generative model, 扩散生成模型

丰富化逻辑:

  • 每个关键词展开为 4-6 个相关关键词(中英文混合)
  • 英文为主(覆盖 arXiv 检索),保留中文(覆盖中文论文)

Step 2: 多源检索(multi_source_fetch.py)

调用 multi_source_fetch.py,传入丰富化后的关键词。输出保存在当天日期目录的 _meta/ 下,便于复盘:

python3 ~/.claude/skills/daily-papers/multi_source_fetch.py \
  --topic "每日论文" \
  --queries-json '["{丰富化关键词1}", "{丰富化关键词2}"]' \
  --since-year {年份下限} \
  --max-results 100 \
  --sources auto \
  --output "$META_DIR/candidates.json"

输出:

  • _meta/candidates.json:规范化、去重、排序后的候选论文
  • _meta/source_diagnostics.json:各来源请求状态
  • _meta/dedup_stats.json:去重统计
  • _meta/plan.json:本次 topic / queries / source 配置

Step 3: Claude 判断相关性(daily-papers-review)

读取 _meta/candidates.json,Claude 逐一判断每篇论文是否与关键词相关,输出 core / adjacent / exclude 筛选理由并生成推荐点评。

Step 4: 生成笔记(daily-papers-notes)

对推荐中标记为"🔥 必读"的论文,逐篇生成中英双语笔记。

重要约束

  • 不要先要求用户手动跑 跑一下论文抓取 / 点评 / 笔记
  • 这 3 句是内部流水线和调试入口,不是首页主交互
  • 如果用户明确只想跑其中一步,再交给对应 skill

自动化

  • 本 skill 本身是"一步跑完整流水线"的入口
  • 如果用户想做本地定时任务,默认也应该触发这一句

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.