20分钟捅出一篇能投顶刊的论文，这事儿现在真不是吹牛批。

https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills…

以前做实证有多熬人你们心里都有数：选题、扒文献、洗数据、因果识别、稳健性检验、画表、写正文，一套流程干下来俩仨月就没了，还得防着referee挑刺、防着期刊反AI，博士生直接被卷到抑郁边缘。

现在斯坦福REAP联手copaper把这套东西给开源了，23000+个专业Agent技能，横扫经济、政治、社会、心理等8大社科领域，顶尖研究员的方法论全被打包成能直接调的Skill，从选题到投稿一气呵成全自动。

https://copaper.ai

卷王时代，趁手工具不在身边，是真的会被淘汰出局。

brycewang-stanford/Auto-Empirical-Research-Skills

Source: https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills

Auto-Empirical Research Skills (AERS)

🌐 Language: English | 简体中文 | 繁體中文 | 日本語 | 한국어

Stanford REAP × CoPaper.AI · An academic–industrial AI toolkit for empirical research
_{Built by Stanford’s empirical-methodology team — the full pipeline from data cleaning to top-journal submission}

All 69 skill collections at a glance

Open the repo → see the whole library. All 69 collections · 1,145 skills, numbered 00 → 69, every one vendored into this repo (not just linked out) and tracked in catalog/skills.json. Click any row to open its folder. ⭐ = first-party skills built by the Stanford REAP × CoPaper.AI team; everything else is curated, security-audited community work.

Theme key — 🚀 full-pipeline & orchestrators · 🎯 causal inference & econometrics · 📚 literature & research design · ✍️ writing, editing & de-AIGC · 📑 citation, replication & peer review · 🛠️ data, tooling & infrastructure

⭐ The spine we built ourselves: StatsPAI (the causal engine) · the explicit Python / Stata / R full-pipeline ports · AER-skills (top-5 submission stack) · chinese-de-aigc · Paper-WorkFlow (meta-orchestrator). These are the spine of AERS — full comparison in The flagship pipeline skills ↓. Prefer to browse by purpose? See the same 69 grouped by what they do ↓.

The empirical-research specialist’s agent-skills distribution. Not a marketing list — 1,145 skills vendored and cataloged in this repo, wrapped in a numeric benchmark, an eval harness, a security audit, and CI, plus a curated map of 23,000+ skills across 119 repositories in the wider ecosystem.

AERS is two things at once: (1) a small set of first-party flagship skills that run the full empirical pipeline — data cleaning → identification → estimation → robustness → tables/figures → submission-ready draft — and (2) a curated, security-aware catalog of the empirical-research skill ecosystem, organized by research-workflow stage. The differentiator is not the count; it is that the flagship behavior is verified against known answers, not asserted.

Renamed. This project was formerly Awesome Agent Skills for Empirical Research. GitHub redirects the old URL automatically; please update your remote:

git remote set-url origin https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git

Contents

• All 69 skill collections at a glance (the full 00 → 69 index)
  • The 69, grouped by what they do
• What you actually get (the numbers, precisely)
• Verify it yourself in 2 minutes
• Why trust this — three layers
• The flagship pipeline skills
• Start here — pick a skill in 30 seconds
• What makes this more than a 23K-skill dump
• Browse the landscape
  • By research stage
  • Comprehensive skill suites
  • Anti-AIGC detection & de-AI academic writing
  • Tools catalog (tools/)
  • Multi-agent systems · MCP servers · platforms · learning
• Security
• Changelog
• Contributing & citation

The 69, grouped by what they do

Same 69 collections · 1,145 skills as the sequential index at the top ↑ — re-sorted here by research purpose so you can scan to the stage you’re working on. ⭐ = first-party (Stanford REAP × CoPaper.AI); everything else is curated, security-audited community work.

🚀 Full-pipeline flagships & orchestrators — one call, the whole empirical loop

🎯 Causal inference & econometrics — the methodological core of AERS

📚 Literature, reading & research design — from question to evidence base

✍️ Writing, editing & de-AIGC — draft, polish, and pass AI-detection

📑 Citation, replication & peer review — make it verifiable and reproducible

🛠️ Data, tooling & infrastructure — the plumbing under the pipeline

What you actually get (the numbers, precisely)

Numbers in this README are kept honest and disambiguated. “Vendored” means the files live in this repo and are tracked in a generated catalog; “cataloged ecosystem” means curated links to external repositories.

The security audit covered the original 52-collection / 2,940-file baseline (52/52 CLEAN). Skills vendored after that baseline are tracked in catalog/provenance.json, docs/LICENSE_AUDIT.md, and docs/SKILL_AUDIT.md; run make audit before relying on them in high-trust contexts.

Verify it yourself in 2 minutes

The most persuasive thing here is not a number — it is that the flagship pipeline’s behavior is checkable without an API key or paid model. Just Python 3:

git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
cd Auto-Empirical-Research-Skills
make check        # repo validation + unit tests + eval lint + numeric benchmark

The benchmark is the convincing part: it recomputes the gold answer from the raw dataset on every run, so a passing score cannot be faked by hard-coding a number. Out of the box it recovers:

• LaLonde (1986) / Dehejia–Wahba (1999) — the naive observational comparison gets the wrong sign (−635); covariate adjustment flips it positive (≈ +1,548) toward the experimental benchmark (≈ +$1,794).
• Card (1995) — IV return to schooling (0.131) exceeds OLS (0.075), with the first-stage F (13.3) reported rather than hidden.
• Plus staggered-DID (TWFE bias vs. group-time truth), sharp RDD, and a bad-control / post-treatment-bias trap.

A pipeline passes only if it surfaces the trap, refuses to headline the misleading number, and matches the recomputed truth. See benchmark/ and the full trust overview in docs/TRUST.md.

💡 Want it hosted and end-to-end? Skip the assembly — copaper.ai runs the empirical pipeline for you, built alongside this catalog by the same Stanford methodology team.

Why trust this — three layers

The flagship pipeline skills

Four parallel implementations of the same 8-step empirical loop — data cleaning → variable construction → descriptives → diagnostics → estimation → robustness → mechanism/heterogeneity → publication-ready tables & figures — plus the submission and de-AIGC stacks. Each uses progressive disclosure: a thin canonical-call spine in SKILL.md, with deep per-step reference manuals loaded only on demand. They coexist; pick by stack and use case.

Why a DSL and explicit ports? Reach for StatsPAI when you trust the one-shot DSL; reach for 00.1/00.2/00.3 when you are teaching, auditing, or must swap every diagnostic by hand. AER-skills then takes a correct analysis to acceptance threshold — these solve different problems and compose.

Start here — pick a skill in 30 seconds

More ways in:

• Not sure which skill? → docs/CHOOSING_A_SKILL.md · faceted search: docs/search.html
• First 10 minutes, end to end → docs/GETTING_STARTED.md
• Copy-paste a full workflow → docs/GOLDEN_WORKFLOWS.md
• Install into a runtime / use without installing → docs/INSTALL.md
• Machine-readable index → catalog/skills.json · taxonomy: docs/TAXONOMY.md · full catalog: docs/SKILL_CATALOG.md
• FAQ → docs/FAQ.md

What makes this more than a 23K-skill dump

Public-skill counts are easy to inflate, and recent studies show large skill indexes are often redundant and occasionally unsafe. AERS competes on verifiable quality, not raw count. Every layer below runs locally via make check and in CI.

make catalog     # regenerate catalog, provenance, audit, enrichment
make validate    # freshness + link / frontmatter checks
make check       # full gate: validate + Python compile + unit tests + eval lint + benchmark

The trust surface is necessary, not sufficient — regex rubrics don’t certify prose and a small benchmark doesn’t cover every design. It is built to fail fast on known high-cost mistakes. Read the honest scope in docs/TRUST.md and docs/QUALITY_GATE.md.

Browse the landscape

📚 The full 69-collection directory ↑ is at the top of this README — this section drills into the ecosystem by theme.

By research stage

Topic Ideation → Lit Search → Deep Reading → Research Design → Data Collection
      │              │             │              │                │
      ▼              ▼             ▼              ▼                ▼
     01             02            03             01               04

Data Cleaning → Statistical Analysis → First Draft → Revision → Typesetting
      │              │                    │            │            │
      ▼              ▼                    ▼            ▼            ▼
     04             05                   06           07           08

Replication → Submission → Peer Review Response → Defense
      │           │              │                   │
      ▼           ▼              ▼                   ▼
     09          10             10                  10

Per-stage skill notes (bilingual): 01 Topic & design · 02 Lit review · 03 Paper reading · 04 Data & cleaning · 05 Causal inference · 06 Writing · 07 Revision · 08 Citation & typesetting · 09 Replication · 10 Review response

Comprehensive skill suites

The pain point AERS exists to fix: ask an AI to “run a DID” and it gives the baseline regression and stops. “Parallel trends?” — it adds one. “Placebo?” — another. Every time, like squeezing toothpaste. A skill is a methodology playbook for the agent: it already knows a complete DID means parallel-trends → baseline → robustness battery → heterogeneity → mechanism, with a defined output at each step.

Anti-AIGC detection & de-AI academic writing

One of 2026’s sharpest pain points: papers failing AIGC detection (Turnitin, GPTZero, CNKI) can be rejected outright. The skills below are the most complete open-source solutions — all MIT, all locally archived (skills/44-48).

Combos: 🇨🇳 Chinese (CNKI/Wanfang/VIP) → chinese-de-aigc · 🇬🇧 English → humanizer_academic · need an audit trail → avoid-ai-writing · general prose → stop-slop.

Tools catalog (tools/) — automated empirical & causal-inference tools

Unlike the skills above, tools/ catalogs the software and services an agent (or researcher) actually invokes — structured, license- and maintenance-aware, and wired into make validate. Source of truth: tools/tools.json; browsable list: tools/CATALOG.md.

335 tools across 6 categories (curated 2026-06):

• Causal-inference / treatment-effect libraries (32) — DoWhy · EconML · CausalML · DoubleML · CausalPy · causallib · grf · CATENets · TMLE family · Mendelian randomization …
• Econometrics / quasi-experimental libraries (170) — panel FE · DiD (incl. modern/staggered) · event study · RDD · IV · synthetic control/SDID · matching & weighting · sensitivity (fixest · did · HonestDiD · rdrobust · synthdid · reghdfe · csdid · sdid · pyfixest · linearmodels …); plus spatial econometrics (spdep · PySAL/spreg · GeoDa), local projections/IRF & (S)VAR (lpirfs · vars · svars), survey weighting/MRP/raking (survey · samplics · balance), and meta-analysis (metafor · meta · netmeta · metan) — across R/Python/Stata/Julia.
• Autonomous research / data-science agents (51) — end-to-end research & data analysis: AI-Scientist · data-to-paper · Agent Laboratory · RD-Agent · AI-Researcher · STORM · PaperQA2 · gpt-researcher · DeepAnalyze · MetaGPT (DI) · Biomni … (⚠️ includes non-OSI / no-LICENSE repos — confirm terms before use).
• MCP servers (48) — stats execution (StatsPAI · stata-mcp · R/Jupyter MCP) + data access (FRED · World Bank · IMF · OECD · Eurostat · Census · BEA · BLS · SEC EDGAR · OpenAlex · Semantic Scholar · PubMed · Zotero · arXiv …).
• Causal discovery / structure learning (25) — causal-learn · Tetrad/py-tetrad · gCastle · CDT · tigramite (PCMCI) · LiNGAM · NOTEARS/DAGMA · pcalg · bnlearn · pgmpy …
• Benchmarks & datasets (9) — causaldata · IHDP/Twins · ACIC competition data · RealCause · JustCause · Tübingen cause-effect pairs · bnlearn network repository …

Full write-up: tools/README.md.

Multi-agent systems · MCP servers · platforms · learning

Security

The original 52 skill collections / 2,940+ files passed a systematic audit — 52/52 CLEAN, zero FLAGGED: no malicious prompts, viruses, reverse shells, or prompt injection. Every “sensitive” hit verified as one of three legitimate categories: defensive security rules, legitimate academic API calls (arXiv / CrossRef / PubMed / FRED / World Bank / OECD / BLS), or standard Claude Code workflow hooks (all local file ops, zero network IO).

Six-phase, defense-in-depth: automated grep across 13 risk categories → 100% manual review of all 6 hook-bearing skills and their 40+ hook scripts (no Bash(*) wildcards anywhere) → three parallel agent content audits → supplemental integrity checks (hidden Unicode, encoding anomalies, HTML injection, network imports).

Key insight: largest ≠ riskiest. The biggest skills all passed; 17-DAAF actually sets the bar for security-conscious design (14 defensive hooks + 32 deny rules + active credential scanning).

Newer vendored additions are tracked in catalog/provenance.json and docs/SKILL_AUDIT.md — run make audit. Full report: SECURITY-SCAN-REPORT.md.

Changelog

The narrative changelog has moved to CHANGELOG.md. Recent highlights:

• 2026-05 — Vendored AER-skills (top-5 economics submission stack, 9 skills) with weekly upstream sync; expanded the numeric benchmark to 5 causal-recovery tasks and the eval harness to 17 scenarios / 95 rubric items.
• 2026-04 — Completed the 52/52 security baseline; shipped the four full-pipeline flagships (StatsPAI + explicit Python / Stata / R); launched the original chinese-de-aigc skill.
• Earlier — Grew from 43 collections to a curated map of 119 repos / 23,000+ skills; added bilingual README, academic data MCP servers, and multi-agent systems.

Contributing & citation

Contributions welcome — see CONTRIBUTING.md and the docs/SKILL_SUBMISSION_GUIDE.md. We especially welcome social-science skills (economics, political science, sociology, psychology, education, public health), new causal-inference implementations, MCP servers for academic/government data, Chinese-friendly skills, and multi-agent case studies. New submissions must declare source, license, and category for the provenance audit.

If AERS helps your work, please cite it (CITATION.cff) and star the repo so more researchers can find it.

AI is an amplifier, not a replacement. It handles the heavy lifting; you keep the core judgment.

_{Stanford REAP × CoPaper.AI · An academic–industrial AI toolkit for empirical research}

Visit copaper.ai

WeChat: CoPaper.AI

20 built-in methodology skills · 20-minute empirical paper · powered by StatsPAI (900+ functions, MIT)

Maintained by CoPaper.AI, incubated at Stanford REAP / SCCEI · AI Assistant for Empirical Research