Agent skill

Paper Review

论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。

Install Paper Review

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/paper-review .claude/skills/paper-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .claude/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/RapidAI/MaClaw/tree/main/paper-review

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/paper-review .agents/skills/paper-review && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .agents/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/paper-review .cursor/skills/paper-review && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .cursor/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/RapidAI/MaClaw.git --path paper-review

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/paper-review .gemini/skills/paper-review && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .gemini/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/paper-review .github/skills/paper-review && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .github/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add RapidAI/MaClaw --skill paper-review -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install RapidAI/MaClaw paper-review --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RapidAI/MaClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/paper-review .opencode/skills/paper-review && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "paper-review" agent skill from https://github.com/RapidAI/MaClaw/tree/main/paper-review into .opencode/skills/paper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-review", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: paper-review
GitHub stars: 148
Token cost: ~1k tokens
SKILL.md length: 212 words
Files: 9
Skills in repo: 1
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 6 steps: 下载 PDF → 全文提取 → LLM 深度解读 → …
Tasks that involve Peer review
SKILL.md covers 架构概览, 环境要求, Step 1: 下载 PDF and Step 2: 全文提取, plus 7 more sections
Runs Python scripts from its folder; calls python and pip; needs OPENAI_API_KEY

What it does

Paper Review is an agent skill from RapidAI/MaClaw. 论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `run.py`, `skill.yaml` and `steps/analyze_paper.py`).

It sits in Documents & Office, covering Peer review, PDF and PowerPoint presentations. It works with OpenAI, Google Gemini, Kimi and MiniMax. The repository describes itself as: 下一代企业级自主进化智能体平台（GUI/TUI/Service/SDK) 。全世界唯一全博士团队开发的开源企业级免费智能体平台。 The licence is MIT.

When your agent uses it

Tasks that involve Peer review
Tasks that involve PDF
Tasks that involve PowerPoint presentations

Example prompts

“/paper-review”

Requirements

Python 3
A credential in OPENAI_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

下载 PDF
全文提取
LLM 深度解读
提取图片素材
生成组会 PPT
生成解读音频

What it can do on your machine

Read from SKILL.md and the folder at commit c936793. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- OPENAI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper Review loads about 1k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 212 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~27
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RapidAI/MaClaw at commit c936793, republished under its MIT licence (© RapidAI). 212 words, ~1,036 tokens.

Download SKILL.mdSave it as .claude/skills/paper-review/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: paper-review
description: 论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。
license: MIT
requires_env: OPENAI_API_KEY
triggers: 论文解读, paper review, paper reading, 组会PPT, 研读论文
required_args: paper_url
metadata.version: 1.0
metadata.category: academic
metadata.author: RapidAI Research - 安妮

Paper Review — 论文深度解读工具

端到端论文解读流程：下载论文 → LLM 深度解读 → 提取图片 → 生成 PPT → 生成 MP3 音频。

架构概览

用户提供论文URL/路径
       │
       ▼
┌──────────────────┐
│  Step 1: 下载PDF  │  (支持 arXiv / DOI / 任意URL)
└────────┬─────────┘
         ▼
┌─────────────────────────┐
│  Step 2: 全文提取 (txt)  │  (PDF→文本，含图片占位标记)
└────────┬────────────────┘
         ▼
┌──────────────────────────────────────────────┐
│  Step 3: LLM 深度解读分析                     │
│   • 解决的问题                               │
│   • 创新点                                   │
│   • 方法本质与核心原理                        │
│   • 详细原理解读                              │
│   • 实验方法与结果分析                        │
└────────┬─────────────────────────────────────┘
         ▼
┌──────────────────┐
│  Step 4: 提取图片 │  (PDF→PNG图片素材)
└────────┬─────────┘
         ▼
┌──────────────────────────────┐
│  Step 5: 生成组会PPT (.pptx)  │  (深度解读内容 + 图片嵌入)
└────────┬─────────────────────┘
         ▼
┌──────────────────────────────┐
│  Step 6: 生成解读音频 (.mp3)  │  (TTS 合成为自然语音)
└────────┬─────────────────────┘
         ▼
      输出文件清单

环境要求

Python 3.8+
依赖安装：pip install requests PyPDF2 python-pptx Pillow pydub
如使用 Edge TTS 音频：pip install edge-tts
(可选) pdf2image + poppler 用于图片提取

Step 1: 下载 PDF

从 arXiv / DOI / 任意 URL 下载论文 PDF。

bash

python "{baseDir}/steps/download_paper.py" --url "{{paper_url}}" --output "{{output_dir}}"

参数：

--url: 论文 URL（arXiv 链接、DOI 链接、或直接 PDF 链接）
--output: 输出目录（可选，默认当前目录）

输出：{{paper_id}}.pdf

Step 2: 全文提取

从 PDF 提取文本内容（含图片标记）：

bash

python "{baseDir}/steps/extract_text.py" --pdf "{{pdf_path}}" --output "{{output_dir}}"

输出：{{paper_id}}_text.txt

Step 3: LLM 深度解读

调用 OpenAI 兼容 API 对论文进行深度解读：

bash

python "{baseDir}/steps/analyze_paper.py" --text "{{txt_path}}" --output "{{output_dir}}"

输出：{{paper_id}}_review.json + {{paper_id}}_review.md

解读结构：

json

{
  "title": "论文标题",
  "problem": "解决的问题",
  "novelty": ["创新点1", "创新点2", ...],
  "method_essence": "方法本质/核心思想",
  "method_detail": "详细原理解读",
  "experiments": "实验方法及结果分析",
  "conclusion": "结论与启示"
}

Step 4: 提取图片素材

从 PDF 中提取图片作为 PPT 素材：

bash

python "{baseDir}/steps/extract_images.py" --pdf "{{pdf_path}}" --output "{{output_dir}}/images"

参数：

--dpi: 图片 DPI（默认 200）
--format: 输出格式（默认 png）

输出：images/page_XX.png 等

Step 5: 生成组会 PPT

基于解读内容和图片生成组会 PPT：

bash

python "{baseDir}/steps/generate_ppt.py" --review "{{review_json}}" --images "{{images_dir}}" --output "{{output_dir}}"

PPT 结构（10-15页）：

封面 — 论文标题 / 作者 / 会议
研究背景与动机 — 为什么做这个工作
要解决的问题 — 问题定义与挑战
核心创新点 — 本文的主要贡献
方法总览 — 整体架构图（含原论文图）
方法详解① — 关键模块/步骤
方法详解② — 更多细节
核心原理剖析 — 为什么有效
实验设置 — 数据集 / 评价指标 / 基线
实验结果 — 主实验结果（含原论文表格）
消融实验 — 各模块贡献分析
可视化分析 — 可视化结果（含原论文图）
讨论与局限性
总结与启示
参考资料 / Q&A

输出：{{paper_id}}_presentation.pptx

Step 6: 生成解读音频

将完整解读文本合成为 MP3 音频：

bash

python "{baseDir}/steps/generate_audio.py" --text "{{review_md}}" --output "{{output_dir}}"

输出：{{paper_id}}_audio.mp3

完整运行

一步到位运行所有步骤：

bash

python "{baseDir}/run.py" --url "{{paper_url}}" --output "{{output_dir}}"

输出文件

文件	说明
`{{paper_id}}.pdf`	原论文 PDF
`{{paper_id}}_text.txt`	PDF 提取的纯文本
`{{paper_id}}_review.md`	LLM 深度解读报告
`{{paper_id}}_review.json`	结构化解读数据
`images/`	提取的论文图片素材
`{{paper_id}}_presentation.pptx`	组会 PPT
`{{paper_id}}_audio.mp3`	解读音频

自定义配置

通过环境变量配置 API：

变量	说明	默认值
`OPENAI_BASE_URL`	API 基础 URL	由 maclaw proxy 自动注入
`OPENAI_API_KEY`	API 密钥	由 maclaw proxy 自动注入
`OPENAI_MODEL`	模型名称	`gpt-4o-mini`
`TTS_ENGINE`	TTS 引擎 (openai/edge)	`edge`
`PPT_LANG`	PPT 语言 (zh/en)	`zh`

Files

SKILL.md and 8 other files in paper-review of RapidAI/MaClaw.

SKILL.md
run.py
skill.yaml
steps/analyze_paper.py
steps/download_paper.py
steps/extract_images.py
steps/extract_text.py
steps/generate_audio.py
steps/generate_ppt.py

Open the folder on GitHubat commit c936793

Compare with similar skills

Paper Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Paper Review compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Paper Review this skillRapidAI/MaClaw	148	—	~1k	Automated safety check: Pass	MIT	today
01 Paper Reviewagentscope-ai/OpenJudge	871	—	~2.4k	Automated safety check: Pass	Apache-2.0	1 mo ago
Markitdownaipoch/medical-research-skills	1.9k	—	~1.3k	Automated safety check: Pass	MIT	24 days ago
Document ConverterBlackBeltTechnology/pi-agent-dashboard	315	—	~999	Automated safety check: Pass	MIT	yesterday
Paper Auditbrycewang-stanford/Auto-Empirical-Research-Skills	4.6k	—	~3.6k	Automated safety check: Pass	Custom licence	5 days ago
PDFzai-org/ZCode	7.7k	—	~18k	Automated safety check: Notes	Proprietary	today

Similar skills

01 Paper Review
agentscope-ai/OpenJudge
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline.
871 GitHub stars~2.4k tokensUpdated 1 mo ago
Research & ScienceAuto-check passed
Markitdown
aipoch/medical-research-skills
Convert files and Office documents into clean Markdown when you need LLM-friendly, token-efficient text (e.g., for summarization, search, RAG ingestion, or dataset preparation).
1.9k GitHub stars~1.3k tokensUpdated 24 days ago
Documents & OfficeAuto-check passed
Document Converter
BlackBeltTechnology/pi-agent-dashboard
Convert documents bidirectionally via the pi-doc-engine facade: ingest PDF/DOCX/PPTX/XLSX to provenance-stamped Markdown (with OCR), and produce templated DOCX/PDF from Markdown with diagrams, TOC…
315 GitHub stars~999 tokensUpdated yesterday
Documents & OfficeAuto-check passed
Paper Audit
brycewang-stanford/Auto-Empirical-Research-Skills
Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats.
4.6k GitHub stars~3.6k tokensUpdated 5 days ago
Documents & OfficeAuto-check passed
PDF
zai-org/ZCode
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
7.7k GitHub stars~18k tokensUpdated today
Documents & OfficeAuto-check: notes
Reasoning Serialization Tests
tailcallhq/forgecode
Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.
7.6k GitHub stars~1k tokensUpdated today
Testing & QAAuto-check passed

Works with

Questions about Paper Review

What does Paper Review do?

论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。. Paper Review is an agent skill from RapidAI/MaClaw.

When should I use Paper Review?

Paper Review fits situations like: tasks that involve Peer review; tasks that involve PDF; tasks that involve PowerPoint presentations.

How do I install Paper Review in Claude Code?

Run `npx skills add RapidAI/MaClaw --skill paper-review -a claude-code`. Or copy the skill folder (paper-review in RapidAI/MaClaw) into .claude/skills/paper-review in your project. Claude Code loads it when a task matches its description.

How do I install Paper Review in Codex?

Run `npx skills add RapidAI/MaClaw --skill paper-review -a codex`. Or copy the skill folder (paper-review in RapidAI/MaClaw) into .agents/skills/paper-review in your project. Codex loads it when a task matches its description.

Can I use Paper Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RapidAI/MaClaw --skill paper-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-review, .gemini/skills/paper-review, .github/skills/paper-review and .opencode/skills/paper-review in your project.

What does Paper Review need to run?

Going by SKILL.md and its folder, Paper Review needs Python for the scripts in its folder, the command-line tools its instructions call (python and pip) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY.

Does Paper Review access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Paper Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Paper Review use?

Paper Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Review use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Paper Review?

Skills that share tags, products or a category with Paper Review: 01 Paper Review (agentscope-ai/OpenJudge, 871 stars), Markitdown (aipoch/medical-research-skills, 1.9k stars), Document Converter (BlackBeltTechnology/pi-agent-dashboard, 315 stars) and Paper Audit (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Review?

RapidAI (a GitHub organization) maintains it in RapidAI/MaClaw, which has 148 GitHub stars. The repository was last updated on October 10, 2026.

Source: RapidAI/MaClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Paper Review

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Paper Review — 论文深度解读工具

架构概览

环境要求

Step 1: 下载 PDF

Step 2: 全文提取

Step 3: LLM 深度解读

Step 4: 提取图片素材

Step 5: 生成组会 PPT

Step 6: 生成解读音频

完整运行

输出文件

自定义配置

Files

Compare with similar skills

Similar skills

01 Paper Review

Markitdown

Document Converter

Paper Audit

PDF

Reasoning Serialization Tests

Related

Questions about Paper Review