daily-paper-push-writing(wo image)

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

157 stars

Best use case

daily-paper-push-writing(wo image) is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

Teams using daily-paper-push-writing(wo image) should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/daily-paper-push-writing(wo image)/SKILL.md --create-dirs "https://raw.githubusercontent.com/InternScience/DrClaw/main/drclaw/agent_hub/templates/paper-push/skills/daily-paper-push-writing(wo image)/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/daily-paper-push-writing(wo image)/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How daily-paper-push-writing(wo image) Compares

Feature / Agentdaily-paper-push-writing(wo image)Standard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# daily-paper-push-writing — Agent Skill Reference

`daily-paper-push-writing` 是一个写作技能,提供一种生成每日科研论文汇总的规范化写作流程,从而帮助用户高效获取特定领域的最新研究成果和重要信息。

## 写作原则

### 论文筛选原则
- **时效性优先**:优先选择近 1-2 周内发布的论文
- **相关性过滤**:紧扣用户关注的领域和关键词
- **质量排序**:按引用量、作者影响力、实验完整性等综合评估
- **多样性考量**:兼顾不同研究方向和方法论,避免内容过度集中

### 写作风格原则
- **简洁精准**:摘要提炼核心贡献,控制在 100-150 字
- **客观中立**:如实描述论文内容,避免过度主观评价
- **学术规范**:使用规范的学术用语,标题、作者、链接等信息准确无误
- **价值导向**:在"学术价值分析"部分侧重实际应用场景和方法论借鉴意义

### 内容组织原则
- **层次分明**:每篇论文遵循统一的格式模板
- **重点突出**:用加粗或 emoji 标注关键信息(创新点、结论)
- **逻辑连贯**:简报整体按论文重要程度或主题相关性排序

### 读者价值原则
- **降低阅读门槛**:帮助读者快速判断论文是否值得深入阅读
- **提供增量价值**:不仅罗列摘要,还要有对研究趋势的洞察
- **可操作性强**:链接直达,方便读者进一步探索

### 长期运营原则
- **建立运营日志**:由于该skill常用于长期任务,应该在memory中建立日志,记录每次抓取的论文和用户反馈,避免推送重复内容,并根据用户反馈不断优化筛选和写作流程。
- **注重推送质量**:每次推送的论文建议控制在四到八篇,综合考虑论文的质量、相关性和潜在价值,确保每次推送都能为用户提供有价值的信息,避免信息过载。



## 写作模板
📢 **【今日论文速递】20XX年XX月XX日** 📢
---

> 📚 **领域**:XXX | 📊 **关键词**:关键词1、关键词2、关键词3

---

🌟 **No.1** 📄 **论文标题**
>
> 📝 **作者**:[作者列表]
> 📅 **发布时间**:20XX年XX月
> 🔗 **论文链接**:👉 [arXiv/论文链接]
> 🏷️ **arXiv ID**:arXiv:XXXX.XXXXX
> 📋 **摘要**:[论文摘要...]
>
> 📝 **Overview 精华**(由 LLM 从 PDF 文本提取):
> > [LLM 提取的论文核心观点、研究动机、关键贡献...]
>
>
> 💡 **学术价值分析**:简要分析该论文的研究创新点、实验方法、潜在应用价值~

---

🌟 **No.2** 📄 **论文标题**
>
> 📝 **作者**:[作者列表]
> 📅 **发布时间**:20XX年XX月
> 🔗 **论文链接**:👉 [arXiv/论文链接]
> 🏷️ **arXiv ID**:arXiv:XXXX.XXXXX
> 📋 **摘要**:[论文摘要...]
>
> 📝 **Overview 精华**(由 LLM 从 PDF 文本提取):
> > [LLM 提取的论文核心观点、研究动机、关键贡献...]
>
>
> 💡 **学术价值分析**:简要分析该论文的研究创新点、实验方法、潜在应用价值~

---

🌟 **No.3** 📄 **论文标题**
>
> 📝 **作者**:[作者列表]
> 📅 **发布时间**:20XX年XX月
> 🔗 **论文链接**:👉 [arXiv/论文链接]
> 🏷️ **arXiv ID**:arXiv:XXXX.XXXXX
> 📋 **摘要**:[论文摘要...]
>
> 📝 **Overview 精华**(由 LLM 从 PDF 文本提取):
> > [LLM 提取的论文核心观点、研究动机、关键贡献...]
>
>
> 💡 **学术价值分析**:简要分析该论文的研究创新点、实验方法、潜在应用价值~

---

🌟 **No.4** 📄 **论文标题**
>
> 📝 **作者**:[作者列表]
> 📅 **发布时间**:20XX年XX月
> 🔗 **论文链接**:👉 [arXiv/论文链接]
> 🏷️ **arXiv ID**:arXiv:XXXX.XXXXX
> 📋 **摘要**:[论文摘要...]
>
> 📝 **Overview 精华**(由 LLM 从 PDF 文本提取):
> > [LLM 提取的论文核心观点、研究动机、关键贡献...]
>
>
> 💡 **学术价值分析**:简要分析该论文的研究创新点、实验方法、潜在应用价值~

---

🌟 **No.5** 📄 **论文标题**
>
> 📝 **作者**:[作者列表]
> 📅 **发布时间**:20XX年XX月
> 🔗 **论文链接**:👉 [arXiv/论文链接]
> 🏷️ **arXiv ID**:arXiv:XXXX.XXXXX
> 📋 **摘要**:[论文摘要...]
>
> 📝 **Overview 精华**(由 LLM 从 PDF 文本提取):
> > [LLM 提取的论文核心观点、研究动机、关键贡献...]
>
>
> 💡 **学术价值分析**:简要分析该论文的研究创新点、实验方法、潜在应用价值~

---

## 论文素材获取

每篇论文需要获取:
1. **PDF 文本** → 供 LLM 提取 Overview 精华内容


### 工作流程

```
┌─────────────────────────────────────────────────────────────┐
│  Step 1: 下载 PDF (一次下载,后续复用)                       │
│  python scripts/pdf_download.py <arxiv_id> [output_dir]    │
└─────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────┐
│  Step 2: PDF 转文本 (供 LLM 读取 Overview)                 │
│  python scripts/pdf_to_text.py <pdf> <output.txt>          │
└─────────────────────────────────────────────────────────────┘
```

### 脚本 1:PDF 下载

```bash
python scripts/pdf_download.py <arxiv_id> [output_dir]
```

**示例:**
```bash
# 下载到默认 ./pdfs/ 目录
python scripts/pdf_download.py 1706.03762

# 下载到指定目录
python scripts/pdf_download.py 1706.03762 ./my_pdfs/

# 强制重新下载
python scripts/pdf_download.py 1706.03762 --force
```

---

### 脚本 2:PDF 转文本

```bash
python scripts/pdf_to_text.py <arxiv_id|pdf_path> <output_path> [options]
```

**示例:**
```bash
# 转换为完整文本(通过 arXiv ID - 会自动下载)
python scripts/pdf_to_text.py 1706.03762 paper.txt

# 使用本地 PDF(更快)
python scripts/pdf_to_text.py ./pdfs/1706.03762.pdf overview.txt

# 只提取 Overview/Introduction 部分
python scripts/pdf_to_text.py ./pdfs/1706.03762.pdf overview.txt --section overview

# 只提取前 5 页
python scripts/pdf_to_text.py ./pdfs/1706.03762.pdf output.txt --pages 5
```

**可选参数:**
- `--section, -s`:提取特定章节(overview, method, experiment)
- `--pages, -p`:提取前 N 页

**用途**:将文本提供给 LLM,让模型提取 Overview 精华内容,写入推送文档。

---


### 依赖说明

所有脚本都依赖以下 Python 包:
- `requests`:下载 PDF
- `pymupdf` (fitz):解析 PDF

```bash
pip install requests pymupdf
```

### 注意事项

- **推荐工作流**:先 `pdf_download` 下载一次,然后所有操作都使用本地 PDF 路径


---

## 最终输出文件格式
<date>-paper_push.md

**注意**:任务完成后请删除 PDF 文件,不在本地缓存。

**注意**:Overview 内容由 LLM 从 PDF 文本提取,直接写入 Markdown

## 工作流程

1. **获取论文列表**:先调用 `arxiv-watcher` skill 获取目标领域的最新论文
2. **筛选论文**:根据时效性、相关性、质量等原则筛选 4-8 篇论文
3. **下载 PDF**:对每篇论文调用 `pdf_download.py` 下载 PDF 到本地
4. **提取文本**:对每篇论文调用 `pdf_to_text.py` 获取文本,**将文本提供给 LLM 让其提取 Overview 精华**
5. **撰写正文**:按照写作模板组织内容,每篇论文附带 LLM 提取的 Overview 精华
6. **输出文件夹**:创建以日期命名的文件<date>-paper_push.md
7. **清理 PDF**:任务完成后**删除 pdfs/ 目录及其内容**,不缓存 PDF 文件

Related Skills

generate-image

157
from InternScience/DrClaw

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

scientific-writing

157
from InternScience/DrClaw

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

daily-paper-push-writing

157
from InternScience/DrClaw

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

today-paper-summary

157
from InternScience/DrClaw

Retrieves papers the user browsed today, downloads PDFs, generates summaries, and returns an enriched list. Use when the user asks what papers they read today, wants a summary of today's papers, or asks about their recent reading activity.

acpx

157
from InternScience/DrClaw

Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.

ui-ux-pro-max

157
from InternScience/DrClaw

[Frontend] Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks. Triggers on ui design, ux design, design system, color palette, typography, glassmorphism, claymorphism, neumorphism, bento grid, font pairing, ui-ux-pro-max, stunning interface, beautiful ui.

fetch

157
from InternScience/DrClaw

Fetch metadata and links from arXiv for a given query.

web_literature_mining

157
from InternScience/DrClaw

Scientific Literature Mining - Mine scientific literature: PubMed search, arXiv search, web search, and Tavily deep search. Use this skill for scientific informatics tasks involving pubmed search search literature search web tavily search. Combines 4 tools from 2 SCP server(s).

uniprot_deep_analysis

157
from InternScience/DrClaw

UniProt Deep Protein Analysis - Deep UniProt analysis: entry data, UniRef clusters, UniParc cross-references, and gene-centric view. Use this skill for protein science tasks involving get uniprotkb entry by accession get uniref cluster by id get uniparc entry by upi get gene centric by accession. Combines 4 tools from 1 SCP server(s).

synthetic_biology_design

157
from InternScience/DrClaw

Synthetic Biology Design - Design synthetic biology construct: gene lookup, codon optimization, protein property prediction, and structure prediction. Use this skill for synthetic biology tasks involving get sequence id DegenerateCodonCalculatorbyAminoAcid calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 4 SCP server(s).

structural_homology_modeling

157
from InternScience/DrClaw

Structural Homology & Evolution Analysis - Analyze protein evolution: get gene tree from Ensembl, find homologs, compare sequences, and predict structure. Use this skill for evolutionary biology tasks involving get homology symbol get genetree member symbol calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 3 SCP server(s).

proteome_analysis

157
from InternScience/DrClaw

Proteome-Level Analysis - Analyze at proteome level: get proteome from UniProt, gene-centric view, functional annotation from STRING. Use this skill for proteomics tasks involving get proteome by id get gene centric by proteome get functional annotation. Combines 3 tools from 2 SCP server(s).