读论文不是做学术,是猎取思想。把别人的发现拆解成自己能用的认知。
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionljg-paperExecute the skills CLI command in your project's root directory to begin installation:
Fetches ljg-paper from lijigang/ljg-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate ljg-paper. Access via /ljg-paper in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
1
total installs
1
this week
2.8K
GitHub stars
0
upvotes
Run in your terminal
1
installs
1
this week
2.8K
stars
读论文不是做学术,是猎取思想。把别人的发现拆解成自己能用的认知。
*bold*(单星号),禁止 **bold*** 开始,不跳级所有图表用纯 ASCII 字符。允许:+ - | / \ > < v ^ * = ~ . : # [ ] ( ) _ , ; ! ' " 和空格。禁止 Unicode 绘图符号。
输出结构依据 references/template.org。禁止参考 ~/Documents/notes/ 中已有论文文件的章节结构——旧文件可能使用过期模板。
date +%Y%m%dT%H%M%Sdate "+%Y-%m-%d %a %H:%M"{时间戳}--paper-{简短标题}__paper.org~/Documents/notes/#+title: paper-{简短标题}
#+date: [{YYYY-MM-DD Day HH:MM}]
#+filetags: :paper:
#+identifier: {YYYYMMDDTHHMMSS}
#+source: {URL 或来源描述}
#+authors: {作者列表}
#+venue: {发表场所/年份}
文件写入后报告路径。
四条核心原则,决定文章是"活人在说话"还是"机器在汇报":
讲解论文时可以拿的工具,没有哪个是必须的:
确保拿到:标题、作者、摘要、核心方法、结果。
如果论文有一张承载全文核心思路的总览图(overview / architecture diagram,通常是 Figure 1),提取并保存到 ~/Documents/notes/images/,文件名 {identifier}--paper-{简短标题}-overview.png。
判断标准:这张图让人一看就抓住论文在做什么。不是所有论文都有——没有就跳过,不要硬找。
提取方法:
arxiv.org/html/...),找到图片 URL,WebFetch 下载找到那个真实的困境——某件事做不到、某个现象解释不通、某条路走不下去。用一段话讲清来龙去脉。
不是「本文提出了一种新的 XXX 框架」,是「大模型明明很聪明,为什么一问具体事实就开始胡说?」
把论文的核心想法讲到一个不懂这个领域的聪明人能跟上。形式自由——类比、图、例子、递进讲解,选最适合这篇论文的方式。
开头先立锚点:找到一个具象的中心隐喻或画面,在翻译的第一段就亮出来。后面所有概念围绕这个锚点生长,不是并列罗列。
推理带着读者走:不要直接给结论。模拟"一步步想明白"的过程——"既然X是这样,那Y能不能也这样?"让读者觉得结论差一步就是自己想到的。
需要覆盖:
费曼翻译部分的子标题按内容需要组织,不必固定。
挑出论文中最关键的 1 至 3 个概念(方法名、架构组件、数学对象、新定义……),逐个拆解。
每个概念:
选概念的标准:读者如果不懂这个,后面的洞见和审稿就跟不上。已经在「翻译」里讲透的不重复选。
整篇论文最值钱的往往就一个点——作者真正找到的那颗新结晶。
用一句话把它说出来。这句话应该让读者觉得「这个想法我可以带走」,而不是「哦,论文说了这么个事」。
检验标准:把这句话单独抽出来,脱离论文上下文,它还有没有力量?如果只是在复述论文结论,那不是洞见。洞见是你读完之后自己看到的那个东西——论文里未必直说,但逻辑指向它。
说不出来就重读第三步。如果论文确实没有思想火花,直说「这篇论文是工程改进,没有认知层面的新发现」。不要硬挤。
换身份:这个方向上带了二十年研究生的博导。学生拿着论文来找你,你判断这东西值不值得认真对待。
用白话说,像在办公室跟学生聊:
好的说好,差的说差在哪儿。
落点在"能用",不在"能想"。给出"这意味着你可以___",而非"这让我们重新思考___"。
用三个视角试探连接,命中展开,没命中跳过,全没命中说「没有」:
逐条扫红线。额外检查:
列修改清单确认后生成文件。
按 Denote 规范获取时间戳,读 references/template.org,写入 ~/Documents/notes/。
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
davila7/claude-code-templates
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
Useful defaults in ljg-paper — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend ljg-paper for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for ljg-paper matched our evaluation — installs cleanly and behaves as described in the markdown.
ljg-paper is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
ljg-paper reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: ljg-paper is the kind of skill you can hand to a new teammate without a long onboarding doc.
Registry listing for ljg-paper matched our evaluation — installs cleanly and behaves as described in the markdown.
ljg-paper is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
ljg-paper reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: ljg-paper is the kind of skill you can hand to a new teammate without a long onboarding doc.
showing 1-10 of 43