Agent skill

Paper Explainer

科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。

Apache-2.0Auto-check passedResearch & Science

Install Paper Explainer

skills CLI

$ npx skills add ZJU-REAL/Easel --skill paper-explainer -a claude-code

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

GitHub CLI

$ gh skill install ZJU-REAL/Easel paper-explainer --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/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/paper-explainer .claude/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .claude/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer

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 ZJU-REAL/Easel --skill paper-explainer -a codex

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

GitHub CLI

$ gh skill install ZJU-REAL/Easel paper-explainer --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/openclaw/paper-explainer .agents/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .agents/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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 ZJU-REAL/Easel --skill paper-explainer -a cursor

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

GitHub CLI

$ gh skill install ZJU-REAL/Easel paper-explainer --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/openclaw/paper-explainer .cursor/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .cursor/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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/ZJU-REAL/Easel.git --path skills/openclaw/paper-explainer

--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 ZJU-REAL/Easel --skill paper-explainer -a gemini-cli

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

GitHub CLI

$ gh skill install ZJU-REAL/Easel paper-explainer --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/ZJU-REAL/Easel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/openclaw/paper-explainer .gemini/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .gemini/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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 ZJU-REAL/Easel paper-explainer

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 ZJU-REAL/Easel --skill paper-explainer -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/openclaw/paper-explainer .github/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .github/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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 ZJU-REAL/Easel --skill paper-explainer -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 ZJU-REAL/Easel paper-explainer --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/openclaw/paper-explainer .opencode/skills/paper-explainer && 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-explainer" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/paper-explainer into .opencode/skills/paper-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-explainer", 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-explainer
GitHub stars: 3.3k
Token cost: ~1.4k tokens
SKILL.md length: 287 words
Files: 11 (incl. scripts, references)
Skills in repo: 113
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。

Works in 2 steps: 取原文 + 解析 → 结构化提炼（你来做，核心）
Tasks that involve Academic paper search
SKILL.md covers 输入, 产物结构（outputs/论文简称/）, 执行步骤 and Profile 感知, plus 2 more sections
Runs Python scripts from its folder; calls python and pip; needs MINERU_API_TOKEN

What it does

Paper Explainer is an agent skill from ZJU-REAL/Easel. 科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts and reference files (for example `EASEL-META.md`, `references/explain-methodology.md` and `references/paper-distill-schema.md`).

It sits in Research & Science, covering Academic paper search and PDF. It works with arXiv and pypdf. The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

When your agent uses it

Tasks that involve Academic paper search
Tasks that involve PDF

Example prompts

“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”
“/paper-explainer”

Requirements

Python 3
A credential in MINERU_API_TOKEN

Workflow steps

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

取原文 + 解析
结构化提炼（你来做，核心）

What it can do on your machine

Read from SKILL.md and the folder at commit 5e0ccc1. 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 2 files in scripts/ (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:
- MINERU_API_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper Explainer loads about 1.4k tokens when it runs, and up to ~8.5k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~47
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~8.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 5e0ccc1, republished under its Apache-2.0 licence (© ZJU-REAL). 287 words, ~1,416 tokens.

Download SKILL.mdSave it as .claude/skills/paper-explainer/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.

name: paper-explainer
description: 科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。
layer: produce

科研论文解读（论文 → 视频 / 图文）

把一篇论文讲成普通人/同行都爱看的视频号视频或图文。核心中间产物是一份 结构化 asset library（一次解析+提炼，视频与图文两条产线共用，不重复调 LLM）。确定性 IO（拉论文/解析 PDF/骨架）走 scripts/paper_ingest.py；提炼与分镜脚本由你 LLM 完成——这是本 SKILL 的核心价值。

视频转图文（反向）见 video-to-article；纯格式转换见 doc-convert；只做图表见 chart-visualization / infographic；发视频号见 skill-channels-upload。

输入

字段	必填	说明
论文	是	arxiv id（2401.12345）/ arxiv 链接 / 本地 PDF 路径（没给就问）
目标形态	否	视频（默认，视频号/B站）/ 图文（知乎/公众号）/ 两者都要
视频画幅	视频时必填	用户或上游任务未明确横版/竖版（或 16:9/9:16/具体分辨率）时，进入视频制作前必须追问并等确认；不得按平台、Profile 或默认值静默推断，已明确则不重复问
受众深度	否	大众科普（默认）/ 同行向（更专业）
时长	否	视频默认 2–4 分钟（视频号中视频）

产物结构（`outputs/论文简称/`）

article.md               图文版（知乎/公众号）
final.mp4                成片
assets/                  paper.pdf / parsed/ / asset-library.json / script.md
  slide-plan.json        结构化分页（页面唯一输入，口播与屏幕文字分离）
  slides/                稳定渲染的逐页 PNG + HTML + audit report
  slides-contact-sheet.jpg  整套视觉复核图

脚本（相对项目根）：paper_ingest.py（解析）+ render_slides.py（分页校验/渲染/审计）。

执行步骤

1. 取原文 + 解析

环境自检：python skills/openclaw/paper-explainer/scripts/paper_ingest.py check （看 pdfplumber / MinerU token / 代理；缺 pdfplumber 则 pip install pdfplumber）。
拉论文：paper_ingest.py fetch --paper <id/url/本地pdf> -o outputs/论文简称/assets/paper.pdf。
解析：paper_ingest.py parse -i outputs/论文简称/assets/paper.pdf -o outputs/论文简称/assets/parsed/ （有 MINERU_API_TOKEN 走 MinerU 含公式/图表结构化，否则 pdfplumber 纯文本 + 尽力抽图）。

2. 结构化提炼（你来做，核心）

生成骨架：paper_ingest.py skeleton -o outputs/论文简称/assets/asset-library.json。
读 assets/parsed/content.*，按 references/paper-distill-schema.md 填满 assets/asset-library.json： one_liner（一句话讲清干了啥）、problem/prior_gap、contributions（≤3 条）、 method（含通俗类比 analogy）、key_figures（挑 2–4 张关键图，每张写 plain 大白话解释）、 results（含关键数字）、limitations、takeaway、terms（术语通俗表）。 通俗化方法见 references/explain-methodology.md（公式/图表→大白话、类比法、避免堆术语）。
忠于原文：不夸大、不编造结论；拿不准的地方标注，别臆测（学术内容错了会被同行抓）。

3A. 视频产线（视频号/B站）

分镜脚本：按 references/video-storyboard.md 结构（钩子→问题→已有不足→贡献→方法一图讲清→结果→意义）把 asset-library 写成 assets/script.md。分镜/留存/口播节奏复用 video-script 的方法（喂论文语境）。可选双人问答口播（主持人提问+讲解者回答）比单人旁白更抓耳——用双人时把口播写成逐行 lines.json（{speaker,text,emotion}，speaker=主讲/提问）。
视觉素材盘点 + 配图：先列出每页的视觉角色（证据图/重绘图/概念线稿/字体图形/motif），再写 slide-plan。论文原图从 assets/parsed/figures/ 选用；复杂原图先裁关键区域，方法流程/结果图用 infographic / chart-visualization 重绘。封面/概念页缺图时，主动找或制作与主题直接相关的线稿、局部图或符号素材，不用随机机器人/blob 填空。图中文字在目标分辨率不可读就不得直接使用。
稳定 slide 产线（强制，不得在 outputs 临时写 make_slides 脚本）：先读 card-design 的设计原则和 references/slide-design.md，把 script 写成 assets/slide-plan.json。把用户/Profile/参考图的原始风格意图原样写入 style，再分别选 base_style、treatment、theme、motif 和视觉素材来实现；不得把用户风格强行归为某个预设，也不得因没有同名预设而拒绝。迁移的是可观察特征（氛围、配色、线条、纹理、构图、角色/物件素材），不是穷举风格名。未指定风格时用 editorial，但默认也必须有明确的编辑网格、纸张层次、章节锚点和图片框法，不得交付“素底 + 字”。整套锁定一个设计立场，页面骨架与审计门保持稳定。运行：
bash
```
python skills/openclaw/paper-explainer/scripts/render_slides.py validate --plan outputs/<项目>/assets/slide-plan.json
python skills/openclaw/paper-explainer/scripts/render_slides.py render --plan outputs/<项目>/assets/slide-plan.json --out-dir outputs/<项目>/assets/slides
python skills/openclaw/paper-explainer/scripts/render_slides.py audit --plan outputs/<项目>/assets/slide-plan.json --slides-dir outputs/<项目>/assets/slides --contact-sheet outputs/<项目>/assets/slides-contact-sheet.jpg
```
任一非 0 退出必须改 plan 后重渲；validate 会按页面职能拦截“只有口号、缺少解释”的低信息页，并检查合并主题后所有正文色在实际背景上的对比度；明亮 accent 可继续用于装饰，文字会使用可读的语义前景色。render 会硬拦文字/元素越界、重叠、组内不对齐、卡内文字左边漂移与结构页过度空洞。脚本全过后当前 Agent 必须肉眼查看 contact sheet 和至少 3 张原尺寸 slide，检查暂停/静音时页面能否独立读懂、论文图可读、文字是否和所属元素对齐、留白是否有叙事作用、视觉素材是否相关、节奏是否重复；只过脚本不等于合格。不要把 narration 整段搬上屏。只有论文图本身承载主要信息时才可在该页设 density: visual，不得把它当作跳过内容提炼的开关。
成片（配音+字幕+合成，缺一不可）：从 slide-plan 的 narration 生成口播——单人用 tts-voiceover，双人用 multi-voice-dubbing；同步 SRT，缺则跑 auto-subtitle。把 assets/slides/slide_*.png、配音和字幕写入 auto-short-video storyboard 后合成，必须设顶层 "image_motion": "static"；slide/图表禁用 Ken Burns，不得缩放、平移或裁掉边缘。页面停留时长按对应 narration 音频/字幕分段，不均分整轨。不能只交静态图或无声视频。
用 manifest.py meta 登记 final.mp4 或 article.md 为 deliverable；中间解析、slide 和音频只放 assets/。
发布：交 skill-channels-upload（视频号）/ B站 biliup。

3B. 图文产线（知乎/公众号）

用同一份 asset-library 写 article.md：标题（钩子）+ 用大白话讲清 problem→method→results→takeaway，配 assets/ 的图。平台适配见 references/platform-adapt.md（知乎逻辑链、公众号成文起承转合）。排版/长图交 doc-convert；发布交 skill-zhihu-publisher / skill-wechat-publisher。

Profile 感知

有 Profile：platforms.md 定主平台并给出形态/画幅/时长建议，但视频画幅仍须用户确认；audience.md 定受众深度（大众 vs 同行）；style.md 定讲解调性；identity.md 定领域垂类（AI/生物/材料…影响类比取材）。
无 Profile：默认视频号 2–4 分钟中视频、大众科普深度，先问领域与受众。

规则

忠于原文：不夸大贡献、不编造数字/结论；术语拿不准先查原文，别臆测。
一次提炼、两处复用：asset-library.json 是唯一真相源，视频与图文都从它出，避免重复提炼与口径不一。
通俗但不失真：用类比降低门槛，但类比不能扭曲原意；关键术语给一句通俗解释而非回避。
图优先：论文靠图讲方法/结果，视频/图文尽量用图（原图或重绘信息图）承载信息。
刻意不做：数字人讲座（太重）、依赖 LaTeX 源（从 PDF 入覆盖更广）。
页面不是口播稿，也不是口号板：一页一个中心结论，但必须用解释、证据或数字口径让页面在暂停/静音时也能独立读懂；细节留给 narration，不得靠缩小字号容纳过量文字。

参考来源

见 EASEL-META.md。流程沉淀自 QuZhan51496/paper2anything（本身即 Claude Skills：parse_pdf/MinerU + 提炼方法论外置 references + 多形态扇出）、 showlab/Paper2Video（按内容块切段、字幕先行）、Paper2Poster（结构化 asset library 中间产物）、 Azzedde/paper_to_podcast（双人问答口播）、OpenDCAI/Paper2Any（一次解析扇出多形态）。

Files

SKILL.md and 10 other files (scripts, references) in skills/openclaw/paper-explainer of ZJU-REAL/Easel.

SKILL.md
EASEL-META.md
references/explain-methodology.md
references/paper-distill-schema.md
references/platform-adapt.md
references/slide-design.md
references/slide-plan.example.json
references/slide-plan.style-transfer.example.json
references/video-storyboard.md
scripts/paper_ingest.py
scripts/render_slides.py

Open the folder on GitHubat commit 5e0ccc1

Compare with similar skills

Paper Explainer 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 Explainer compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Paper Explainer this skillZJU-REAL/Easel	3.3k	—	~1.4k	Automated safety check: Pass	Apache-2.0	today
Paper ReadingEdwardxlai/easyread	871	—	~567	Automated safety check: Pass	MIT	today
Ref Downloaderltczding-gif/ref-downloader	139	—	~5.9k	Automated safety check: Pass	MIT	4 mo ago
Paper Readingsodalone/paper-reading-skill	142	—	~1.3k	Automated safety check: Pass	None	2 mo ago
Summaryalaliqing/claude-paper	343	—	~2k	Automated safety check: Notes	MIT	1 mo ago
Paper Readingvoidful/academic-skills	134	—	~1.4k	Automated safety check: Pass	MIT	6 mo ago

Similar skills

Paper Reading
Edwardxlai/easyread
论文共读：用 EasyRead（E:\CursorProject\easyread）这个本地工具读论文。用户给一篇 PDF 或 arXiv 编号时，导入文献库、翻译成中文（后台引擎或对话里的 agent 亲自译）；之后边读边讨论，agent 读用户在页面上的笔记和提问，把回答、解释、原文核对提示追加到对应段落旁。用于…
871 GitHub stars~567 tokensUpdated today
Research & ScienceAuto-check passed
Ref Downloader
ltczding-gif/ref-downloader
A skill your agent uses when the user asks to batch-download academic PDFs with ref-downloader — either ALL references of one paper (Mode A: DOI or PDF input), OR a custom batch of papers (Mode B…
139 GitHub stars~5.9k tokensUpdated 4 mo ago
Research & ScienceAuto-check passed
Paper Reading
sodalone/paper-reading-skill
系统阅读、解释和批判性分析单篇 arXiv AI / 机器人论文，并生成一份主线清楚、核心内容不缺失、审稿证据可追溯的自包含 Markdown 报告。适用于 arXiv 链接、ID 或其 PDF 的精读、方法/理论/系统讲解、完整 Claim 审查、实验/证明/协议/代码证据核对、相关文献定位和复现或验证判断；默认执行完整精读，仅在用户明确要求速读时缩减覆盖范围。当前流水线不支持无法解析出…
142 GitHub stars~1.3k tokensUpdated 2 mo ago
Research & ScienceAuto-check passed
Summary
alaliqing/claude-paper
Use this for a quick summary of a research paper's core ideas and key points.
343 GitHub stars~2k tokensUpdated 1 mo ago
Research & ScienceAuto-check: notes
Paper Reading
voidful/academic-skills
太奶讀論文 — 一位百歲阿嬤用繁體中文、生活比喻和動漫梗，帶你讀懂學術論文。當使用者提供論文 PDF、arXiv 連結、或貼上論文文字，並想理解論文內容時，一定要使用此技能。觸發詞包括：讀論文、解釋論文、看不懂、幫我理解這篇、這篇在說什麼、paper reading、explain this paper。適用於任何學術論文的直觀導讀。
134 GitHub stars~1.4k tokensUpdated 6 mo ago
Research & ScienceAuto-check passed
Paper Researcher
wpsnote/wpsnote-skills
学术论文全流程助手：搜索论文、下载 PDF、存入 WPS 笔记、精读分析。当用户说"搜论文"、"找论文"、"下载论文"、"读论文"、"帮我找 paper"、"搜一下 XXX 相关的论文"、"把这篇论文存到笔记"、"分析这篇论文"、"帮我做文献调研"时触发。支持 arXiv 和 OpenAlex 两个数据源，自动完成搜索→下载→转文本→写入 WPS 笔记→分析的完整闭环。
179 GitHub stars~970 tokensUpdated 4 mo ago
Research & ScienceAuto-check passed

Questions about Paper Explainer

What does Paper Explainer do?

科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。. Paper Explainer is an agent skill from ZJU-REAL/Easel.

When should I use Paper Explainer?

Paper Explainer fits situations like: tasks that involve Academic paper search; tasks that involve PDF.

How do I install Paper Explainer in Claude Code?

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

How do I install Paper Explainer in Codex?

Run `npx skills add ZJU-REAL/Easel --skill paper-explainer -a codex`. Or copy the skill folder (skills/openclaw/paper-explainer in ZJU-REAL/Easel) into .agents/skills/paper-explainer in your project. Codex loads it when a task matches its description.

Can I use Paper Explainer 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 ZJU-REAL/Easel --skill paper-explainer -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-explainer, .gemini/skills/paper-explainer, .github/skills/paper-explainer and .opencode/skills/paper-explainer in your project.

What does Paper Explainer need to run?

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

Does Paper Explainer 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 Explainer 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Paper Explainer use?

Paper Explainer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Explainer use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.1k tokens, read only when the agent opens those files.

What are the alternatives to Paper Explainer?

Skills that share tags, products or a category with Paper Explainer: Paper Reading (Edwardxlai/easyread, 871 stars), Ref Downloader (ltczding-gif/ref-downloader, 139 stars), Paper Reading (sodalone/paper-reading-skill, 142 stars) and Summary (alaliqing/claude-paper, 343 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Explainer?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,310 GitHub stars. The repository holds 113 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel 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 Explainer

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

科研论文解读（论文 → 视频 / 图文）

输入

产物结构（outputs/论文简称/）

执行步骤

1. 取原文 + 解析

2. 结构化提炼（你来做，核心）

3A. 视频产线（视频号/B站）

3B. 图文产线（知乎/公众号）

Profile 感知

规则

参考来源

Files

Compare with similar skills

Similar skills

More from ZJU-REAL/Easel

Related

Questions about Paper Explainer

产物结构（`outputs/论文简称/`）