E
ericluo04/claude-academic-workflow
Academic research workflow for Claude Code: 20 skills covering causal inference (DiD, RDD, IV, synthetic…
★ 26·更新 2026-11-17
在 GitHub 查看 ↗链接已于 2026-11-17 核查 · HTTP 200 · 打开的是厂商自己的官网
- ★ 数取值
- 26 ★ · ericluo04/claude-academic-workflow · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-17 · 最近见到 2026-11-20 · 共见到 4 次 · 被 2 个来源列出
- 评分构成
- 综合分 203 · 26 ★ · 2 个来源 · repo
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: 开源项目。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
ericluo04/claude-academic-workflow;我们收录于 2026-11-17;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
# claude-academic-workflow
以下摘录自该仓库的 README(片段)
An academic-research workflow for Claude Code: skills for reading papers, running literature reviews, auditing bibliographies, designing and analyzing causal-inference studies (difference-in-differences, regression discontinuity, instrumental variables, synthetic control, randomized experiments), checking drafts before submission, writing R&R responses, assembling replication packages, compiling LaTeX, iterating TikZ figures, and a Quarto reveal.js slide system with render-time quality gates. It was built for quantitative marketing and economics; most of it transfers to any empirical field.
Everything in this repository, including the two example decks and their figures, is AI-generated with Claude Code, as a proof of concept for what an agent-built research workflow looks like. Generated content is the responsibility of whoever uses it: verify citations, numbers, and claims before relying on them, the same way you would verify a research assistant's first draft.
Four pages worth reading before adapting any of this: Anthropic's prompting best practices and its companion for prompting Claude Fable 5.1, the Claude Code best practices, and the post on getting the most out of Claude Code sessions. The configuration in this repository is checked against them.
## Quickstart
bash
git clone https://github.com/ericluo04/claude-academic-workflow
cd claude-academic-workflow
mkdir -p ~/.claude/skills ~/.claude/agents ~/.claude/assets ~/.claude/output-styles
cp -R skills/ ~/.claude/skills/
cp agents/tikz-reviewer.md ~/.claude/agents/
cp -R slide-tooling ~/.claude/assets/quarto-yale
cp output-styles/concise-research.md ~/.claude/output-styles/
Then read SETUP.md: it names every path and helper the skills assume (the Crossref contact address, the PDF helper, the Overleaf glob) and how to adjust each one. CLAUDE.md is the author's working global configuration, shared as an example. The three style/house.md files in the slide skills are stubs for your own taste: author line, closing-slide wording, palette rationale, density calibration. docs/mirror-notes.md records how these files were genericized from the author's private copies, and where this repository deliberately diverges from them.
## The global CLAUDE.md
CLAUDE.md is what Claude Code loads into every session as standing instructions; this one carries the author's voice rules (how prose should read) and working style (parallel subagents by default, decisions through the option picker, judgment calls raised before acting), which shape every skill's output without being repeated in any of them. If you adapt this repo, add your own standing context here: quants will want a computing-grid section (cluster login, Slurm citizenship rules, where storage lives), plus anything else Claude should know in every session, like data locations or preferred stacks. What belongs there rather than in an output style is further down.
## Skills
| Skill | What it does |
| reading-papers | Looks up and reads a specific paper from a link, DOI, title, or vague description, across marketing, economics, psychology, and CS venues. |
| litreview | Finds, ranks, and synthesizes the literature on a topic across Semantic Scholar, OpenAlex, and arXiv, then reads the top hits with parallel subagents. |
Everything in this repository, including the two example decks and their figures, is AI-generated with Claude Code, as a proof of concept for what an agent-built research workflow looks like. Generated content is the responsibility of whoever uses it: verify citations, numbers, and claims before relying on them, the same way you would verify a research assistant's first draft.
Four pages worth reading before adapting any of this: Anthropic's prompting best practices and its companion for prompting Claude Fable 5.1, the Claude Code best practices, and the post on getting the most out of Claude Code sessions. The configuration in this repository is checked against them.
## Quickstart
bash
git clone https://github.com/ericluo04/claude-academic-workflow
cd claude-academic-workflow
mkdir -p ~/.claude/skills ~/.claude/agents ~/.claude/assets ~/.claude/output-styles
cp -R skills/ ~/.claude/skills/
cp agents/tikz-reviewer.md ~/.claude/agents/
cp -R slide-tooling ~/.claude/assets/quarto-yale
cp output-styles/concise-research.md ~/.claude/output-styles/
Then read SETUP.md: it names every path and helper the skills assume (the Crossref contact address, the PDF helper, the Overleaf glob) and how to adjust each one. CLAUDE.md is the author's working global configuration, shared as an example. The three style/house.md files in the slide skills are stubs for your own taste: author line, closing-slide wording, palette rationale, density calibration. docs/mirror-notes.md records how these files were genericized from the author's private copies, and where this repository deliberately diverges from them.
## The global CLAUDE.md
CLAUDE.md is what Claude Code loads into every session as standing instructions; this one carries the author's voice rules (how prose should read) and working style (parallel subagents by default, decisions through the option picker, judgment calls raised before acting), which shape every skill's output without being repeated in any of them. If you adapt this repo, add your own standing context here: quants will want a computing-grid section (cluster login, Slurm citizenship rules, where storage lives), plus anything else Claude should know in every session, like data locations or preferred stacks. What belongs there rather than in an output style is further down.
## Skills
| Skill | What it does |
| reading-papers | Looks up and reads a specific paper from a link, DOI, title, or vague description, across marketing, economics, psychology, and CS venues. |
| litreview | Finds, ranks, and synthesizes the literature on a topic across Semantic Scholar, OpenAlex, and arXiv, then reads the top hits with parallel subagents. |
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/ericluo04-claude-academic-workflow/)
- 来源
- github · https://github.com/ericluo04/claude-academic-workflow
- 按领域浏览
- 开源项目
- Traction
- 26 ★
- 收录来源
- 2 个独立来源
- 收录于
- 今天
更多条目
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。