Paper Sprint Review
PaperSprint is a Scrum-inspired academic paper agent workflow for conference or journal drafts. Use when Codex needs to clarify paper direction, estimate likely sprint count, set sprint goals and focus areas, assess venue fit, organize reviewer or editor lenses, convert critique into a prioritized revision backlog, drive amendment increments, or keep a process log across repeated review loops for `.docx`, `.tex`, `.md`, PDF, thesis, and response-letter materials.
Install
npx skills add RichradsY/PaperSprint --skill paper-sprint-reviewgit clone --depth 1 https://github.com/RichradsY/PaperSprint.git /tmp/PaperSprint
mkdir -p ~/.claude/skills
cp -r /tmp/PaperSprint/. ~/.claude/skills/paper-sprint-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# PaperSprint Use this skill as PaperSprint, a Scrum-inspired paper agent. Start by clarifying the direction and constraints, estimate the likely sprint path, then run one increment at a time: plan, review, amend, log, adapt, repeat. ## Run An Intake - Ask only for the missing facts that determine the workflow. Do not front-load a long questionnaire. - Clarify the target venue or decision context. - Clarify the manuscript stage: idea, outline, early draft, full draft, revision, rebuttal, or camera-ready. - Clarify the sprint goal: contribution shaping, theory fit, method defense, empirical rigor, structure, writing quality, venue alignment, or response-to-reviewers. - Clarify which materials are available now: manuscript files, thesis chapters, appendices, prior reviews, call for papers, author guidelines, sample papers, or reviewer comments. - Clarify whether current editors, editorial boards, deadlines, or scholar profiles should be researched online. - State any assumptions explicitly when the user does not provide enough detail and the assumption is safe. - If the venue is unknown, run a discovery increment first and delay named editor or reviewer research. ## Draft A Starter Prompt - If the user needs a starting prompt, give a ready-to-send template with placeholders. - Use this default form:
Details
- Skill name
paper-sprint-review- Repository
- RichradsY/PaperSprint
- License
- MIT
- Repo updated
- 10 March 2026
FAQ
What does the Paper Sprint Review skill do?
PaperSprint is a Scrum-inspired academic paper agent workflow for conference or journal drafts. Use when Codex needs to clarify paper direction, estimate likely sprint count, set sprint goals and focus areas, assess venue fit, organize reviewer or editor lenses, convert critique into a prioritized revision backlog, drive amendment increments, or keep a process log across repeated review loops for `.docx`, `.tex`, `.md`, PDF, thesis, and response-letter materials.
How do I install the Paper Sprint Review skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add RichradsY/PaperSprint --skill paper-sprint-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Paper Sprint Review popular?
It lives in RichradsY/PaperSprint, which has 39 GitHub stars and 5 forks.
Related skills
Industry Research
33geekjourneyx/industry-research
行业调研——researcher CLI + 多 Agent 对抗式研究引擎。输入一个行业/赛道/商业机会的模糊需求, 输出一份有据可依、经过证据校验和红蓝对抗检验的战略调研报告。内置国民经济行业分类映射、 MECE/PESTLE/波特五力等咨询框架、事前验尸法和黑格尔辩证法合题引擎。 支持精简/标准/深度三种报告深度。 触发方式:/industry-research、「行业调研」、「行业分析」、「赛道研究」、「市场调研」 Use when the user asks for industry research, sector analysis, market study, competitive landscape analysis, investment thesis research, or any request involving structured industry investigation. Also trigger when user mentions 调研报告, 行业研究, 赛道分析, 商业机会分析, 投资逻辑梳理, or similar phrases. Even casual requests like "帮我看看 XX行业怎么样" or "XX赛道值不值得做" should trigger this skill.
Bettersearch
40ry0narushima/bettersearch
Web research with DeepSeek's Search & Fetch APIs. Use whenever the user asks to research something, look up or look into a topic, search the web, find sources, check current facts, numbers or prices, compare options with up-to-date info, fact check a claim, or do deep research / write a research report. Quick mode answers in chat with numbered citations; advanced (deep) mode runs a planner, researchers, fact-checker, reviewer and writer and builds a self-contained HTML report.
Zju Literature Downloader
35baihe26/zju-literature-downloader
Use this skill whenever the user wants to use their own logged-in Zhejiang University Library, WebVPN, CAS SSO, 求是学术搜索, Summon, ScienceDirect, publisher, or Chrome session to legally search, download, organize, retry, and read academic PDFs and supporting information. Trigger on requests like “用浙大图书馆下载文献”, “WebVPN 下载 PDF”, “CAS 认证失败后重试下载”, “ScienceDirect 人机验证后继续”, “自动下载补充材料”, “读取全文和 supporting information”, “批量整理文献到项目文件夹”, or “导入 Zotero 后帮我读全文”.
Suoha Serenity Skill
43suoha888/suoha-serenity-skill
Research stocks and supply-chain chokepoints using a framework distilled from Serenity's public posts. Use for evidence-first company health checks across A-shares, Hong Kong and US equities, live data packs, company-name resolution and falsifiable, source-cited research reports. Distinguish an industry bottleneck from a company's value capture and market expectations. Reports do not represent Serenity's own views; research only, no trade execution or promised returns.
Phdtaketaketake
33powerofjinbo/phdtaketaketake
Score a PhD applicant's profile and rank candidate advisors using a connection-first 4.0-scale scoring system. Best-supported for physics / HEP and materials science (MSE), with the scoring engine extensible to chemistry, biology, CS, math, EE, ChemE, earth science (each with field-specific caveats — see references/journal_tiers.md). Use when the user wants to evaluate their PhD application chances, find matching advisors at top US programs, score a CV for graduate school, or compare candidate professors. Also triggers when the user mentions phdtaketaketake or its connection-first philosophy o
Remote GPU Trainer
42Hanyuyuan6/remote-gpu-trainer
AutoDL/vast.ai/RunPod/Lambda/Paperspace远程GPU启动、调试、监控、续训、并行、停止及卡住/OOM/NaN/全零指标排查;可验证状态/selection-best checkpoint/拉回结果。释放实例销毁机器及数据盘,不等同关机。长期镜像/恢复→mirror-research-artifacts。
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.