daily-papers-fetch

daily-papers-fetch is a skill for Claude Code, Codex from huangkiki/dailypaper-skills. It costs 118 tokens per session (1,621 once invoked), scanned A, original, Apache-2.0.

A paper-finding workflow that collects recent research papers from arXiv and Hugging Face, scores and enriches them, removes duplicates, and saves the results for later steps.

In plain words
What is it for?
Use it to fetch papers from today or a chosen number of recent days, filter them using shared keywords and categories, and produce a ranked list for a daily research digest.
Why use it?
It avoids manually searching several research sources and sorting through papers that may not match your configured interests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python3 ../daily-papers/fetch_and_score.py > /tmp/daily_papers_top30.json.

Good fit Use it to fetch papers from today or a chosen number of recent days, filter them using shared keywords and categories, and produce a ranked list for a daily research digest.

Compare 6 skills from other repositories ↓
About the project

dailypaper-skills is a collection of agent skills that automates a research-paper reading workflow. It finds recent papers from sources such as Hugging Face and arXiv, ranks them by the user’s interests, and creates structured notes in Obsidian, with optional Zotero support. The catalogue skills are the project’s own workflow components for coding agents.

huangkiki/dailypaper-skills · 1,220 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/huangkiki/dailypaper-skills
agentmods
npx agentmods add skills/huangkiki/dailypaper-skills/daily-papers-fetch

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for daily-papers-fetch

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-fetch/github.svg)](https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-fetch)
Your own site
<a href="https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-fetch"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-fetch/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for daily-papers-fetch

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-fetch"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01621
Opus 5 $0.00059 $0.00811
Sonnet 5 $0.00024 $0.00324
Haiku 4.5 $0.00012 $0.00162

Measured 13d ago against content hash 817c252718f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

daily-papers-fetch scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

用 `enrich_papers.py` 脚本一次性富化所有论文。脚本使用 `asyncio` + `curl` 子进程并发请求,纯 regex 解析 HTML,无需 WebFetch。
skills/daily-papers-fetch/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

开始前: 先说一声 "开始抓取论文 🐕" 并告知今天日期。如果是多天模式,告知抓取范围。

论文抓取 (Fetch + Score + Enrich)

你是 用户的论文抓取系统(3 步流水线的第 1 步)。抓取最新论文 → 打分筛选 → 富化信息 → 保存到临时文件。

Step 0: 读取共享配置

先读取 ../_shared/user-config.json,如果 ../_shared/user-config.local.json 存在,再用它覆盖默认值。

显式生成并在后续统一使用这些变量:

  • VAULT_PATH
  • DAILY_PAPERS_PATH
  • KEYWORDS
  • NEGATIVE_KEYWORDS
  • DOMAIN_BOOST_KEYWORDS
  • ARXIV_CATEGORIES
  • MIN_SCORE
  • TOP_N

其中:

  • DAILY_PAPERS_PATH = {VAULT_PATH}/{daily_papers_folder}
  • 所有关键词、分类、阈值都以共享配置为准

后续统一以共享配置和上面的变量为准。

解析天数

从用户输入中解析 --days N 参数。匹配规则:

  • "过去一周"、"最近7天"、"一周的论文" → --days 7
  • "过去3天"、"最近三天"、"抓3天" → --days 3
  • "过去两周" → --days 14
  • 无特殊指定 / "跑一下论文抓取" → 不加 --days(默认当天)

将解析出的天数存为变量 DAYS_ARG,在后续脚本调用中使用。

配置来源

  • 默认配置在 ../_shared/user-config.json
  • 个人覆盖配置放在 ../_shared/user-config.local.json
  • 如果两者都存在,以 local 为准

工作流程

Phase 1+2: 抓取 + 打分 + 合并去重(纯 Python 脚本)

fetch_and_score.py 一步完成 HF + arXiv 抓取、打分、合并去重、历史去重、选 Top 30。零 token 消耗。

# 默认:当天
python3 ../daily-papers/fetch_and_score.py > /tmp/daily_papers_top30.json

# 多天模式(将 N 替换为解析出的天数)
python3 ../daily-papers/fetch_and_score.py --days N > /tmp/daily_papers_top30.json

根据前面解析的 DAYS_ARG,如果用户指定了天数就加 --days N,否则不加。

脚本自动完成:

  • 并行抓取 HuggingFace Daily + Trending API 和 arXiv API
  • 关键词打分(正向/负向/领域加分/trending 加分)
  • 按 arXiv ID 合并去重
  • 读取 .history.json 跨天去重(含周末模式放宽规则)
  • 不足 20 篇时从历史回填
  • 按 score 降序取 Top 30

进度日志输出到 stderr,JSON 结果输出到 stdout。

检查输出:确认 /tmp/daily_papers_top30.json 存在且包含有效 JSON 数组。如果为空数组或文件不存在,检查 stderr 诊断问题。

Phase 3: 批量富化(enrich_papers.py 脚本)

enrich_papers.py 脚本一次性富化所有论文。脚本使用 asyncio + curl 子进程并发请求,纯 regex 解析 HTML,无需 WebFetch。

先把 Phase 2 的 Top 30 结果保存到临时文件,然后运行:

python3 ../daily-papers/enrich_papers.py /tmp/daily_papers_top30.json /tmp/daily_papers_enriched.json

注意:使用两个文件路径参数(输入 + 输出),避免 sandbox 环境下 stdout/stderr 混淆。脚本会把第一个 .json 参数当作输入路径、第二个当作输出路径;如果只传一个 .json 它会被当作输入路径,结果走 stdout。

脚本自动完成以下工作(Semaphore(10) 限制并发,单篇超时 30 秒):

  • 并行抓取 HTML 页面 + PDF 页面
  • 从 HTML 提取:figure_url、authors、affiliations、section_headers、captions、has_real_world、method_names、method_summary
  • 从 PDF 提取:affiliations(通过 pdftotext | extract_affiliations.py
  • 如果 HTML authors 为空,fallback 到 abs 页面 <meta> 标签提取 authors/affiliations
  • 合并优先级(脚本内部处理):
    • figure_url: HTML curl
    • affiliations: PDF > HTML > abs fallback > Phase 1 data
    • authors: HTML > abs fallback > Phase 1 data
    • 其他字段: HTML regex 提取

Read the full file on GitHub · 132 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 132 lines · 118 tokens per session scan A 817c252718f5

Subscribe to this mod's changes

daily-papers-fetch is a skill published in the GitHub repository huangkiki/dailypaper-skills (1,220 stars, last pushed 20d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,621 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens