auto-empirical-research-skills

Auto-Empirical Research Skills Router

Use this root skill when the full AERS repository has been installed as a single skill folder. Treat it as a router and catalog, not as a request to load every vendored SKILL.md.

The catalog holds 1,108 skills across 78 vendored collections. Never read them all — route to one, then load only that skill's SKILL.md.

Workflow

1. Classify the user's empirical-research task by stage, then load the single best-matching skill:

   • Full pipeline or orchestration: start with skills/69-Paper-WorkFlow/ or the skills/00* flagship analysis skills — skills/00-Full-empirical-analysis-skill_StatsPAI/ (StatsPAI), skills/00.1-Full-empirical-analysis-skill_Python/ (Python), skills/00.2-Full-empirical-analysis-skill_Stata/ (Stata), skills/00.3-Full-empirical-analysis-skill_R/ (R). Note the StatsPAI flagship has no dot in its prefix, so a skills/00.* glob misses it.
   • Causal inference and econometrics: pick by method from the table below, or search catalog/skills.json / docs/TAXONOMY.md.
   • AER or top economics journal work: start with skills/50-brycewang-aer-skills/.
   • Replication, citation, or peer review: use docs/SKILL_CATALOG.md and docs/GOLDEN_WORKFLOWS.md to choose a focused skill.
   • Academic de-AIGC (English or Chinese) or academic rewriting: start with skills/48-de-AIGC-skills/ or nearby writing skills in the catalog.

2. Read only the selected child skill's SKILL.md, then follow its progressive-disclosure instructions for references/, scripts/, assets/, or templates.

3. If no child skill clearly matches, run the ranked catalog search first — it takes English or Chinese task text:

   python3 scripts/find-skill.py "staggered difference-in-differences event study"
   python3 scripts/find-skill.py "降低中文论文 AIGC 率" -k 5
   

   It ranks by relevance, then by the routing tier in catalog/curation.json: first-party core skills first, a single preferred copy for each duplicated name (the other copies are folded away), and natural-science / CS guides (out-of-domain) last unless the query names them. Take the top result unless its description clearly misfits, then read only that SKILL.md. Its accuracy is measured by python3 scripts/check-routing.py against evals/routing-cases.json.

   If you need raw data instead, catalog/skills.json has path, name, description, line_count, and a globally-unique qualified_name; catalog/skills-enriched.json adds tier, tags, quality_score, license, and commercial_use. Avoid broad recursive reads of skills/.

   • Both catalog JSON files are large (roughly 1 MB / 20k lines each) — query them instead of reading them whole. Example:

     python3 -c "import json; [print(s['qualified_name'], '->', s['path']) for s in json.load(open('catalog/skills.json'))['skills'] if 'synthetic control' in (s['name'] + ' ' + s['description']).lower()]"
     

     A plain grep -in "synthetic control" catalog/skills.json works too when a rough match is enough.

4. For installation help, use INSTALL.md: method 0 when the user hands you this folder's local path and asks you to install it, section 2C for Codex (~/.agents/skills/), method 1 for Claude Code marketplace/plugin installs. docs/INSTALL.md has the short copy-install reference.

5. If editing this repository, keep parent and nested repos separate. In particular, inspect git status inside skills/69-Paper-WorkFlow/ (a git submodule) before touching it.

Method → where to start

Match the user's identification strategy or task to a starting collection, then confirm against catalog/skills.json.

This table is a shortcut to the most common starting points, not a complete index — it names fewer than half of the vendored collections, and the rest are reachable only through catalog/skills.json. A task missing from this table is not a task without a skill: fall through to step 3 and search the catalog before concluding nothing matches.

Task / method	Start here
Full paper pipeline (orchestrator)	skills/69-Paper-WorkFlow/
Data → full Word .docx manuscript (one run: analysis + writing + assembled deliverable)	skills/69-Paper-WorkFlow/ — pick manuscript.format = markdown at its Stage 0 when the deliverable is Word; Stage 9 assembles 09_submission/main.docx (body + tables + figures + references) and gates it
Markdown / LaTeX → .docx conversion only (no analysis)	skills/67-econfin-workflow-toolkit/md-to-docx/, skills/08-ndpvt-web-latex-document-skill/
Agent-native causal analysis (one call runs DiD / RD / IV / SCM / DML with automatic robustness gates)	skills/00-Full-empirical-analysis-skill_StatsPAI/
DiD / staggered DiD / event study	skills/50-brycewang-aer-skills/, skills/10-Jill0099-causal-inference-mixtape/, skills/13-scunning1975-MixtapeTools/
Instrumental variables (IV)	skills/50-brycewang-aer-skills/, skills/40-py-econometrics-pyfixest/
Regression discontinuity (RDD)	skills/50-brycewang-aer-skills/, skills/10-Jill0099-causal-inference-mixtape/
Synthetic control (SCM)	skills/50-brycewang-aer-skills/, skills/13-scunning1975-MixtapeTools/
Panel fixed effects	skills/40-py-econometrics-pyfixest/, skills/39-vincentarelbundock-marginaleffects/
Specification search / multiverse / p-hacking audit, honest p-values, p-curve, pre-registration	skills/73-brycewang-p-hacking-skills/ (start at skills/00-phack-router/; teaching & audit only)
Questionnaire / survey SEM in SPSS + AMOS — reliability, EFA, CFA (CR / AVE / HTMT), structural model, bootstrap mediation, multi-group, PROCESS (结构方程 / 问卷 / 信效度)	skills/74-brycewang-spss-amos-sem/
Matching / propensity scores	skills/10-Jill0099-causal-inference-mixtape/, skills/11-James-Traina-compound-science/
Structural estimation	skills/11-James-Traina-compound-science/, skills/14-luischanci-claude-code-research-starter/
Time series / forecasting	skills/17-DAAF-Contribution-Community-daaf/, skills/43-wentorai-research-plugins/
Text as data / NLP	skills/43-wentorai-research-plugins/
Spatial / GIS analysis	skills/17-DAAF-Contribution-Community-daaf/, skills/43-wentorai-research-plugins/
Experiments / RCT design	skills/11-James-Traina-compound-science/, skills/25-HosungYou-Diverga/
Survey / questionnaire design	skills/43-wentorai-research-plugins/, skills/25-HosungYou-Diverga/
DML / CATE / causal forests	skills/00.1-Full-empirical-analysis-skill_Python/, skills/63-tondevrel-scientific-agent-skills/
Bayesian modeling	skills/23-Learning-Bayesian-Statistics-baygent-skills/, skills/51-pymc-labs-CausalPy/
Python analysis (full pipeline)	skills/00.1-Full-empirical-analysis-skill_Python/, skills/40-py-econometrics-pyfixest/
Stata analysis	skills/00.2-Full-empirical-analysis-skill_Stata/, skills/32-dylantmoore-stata-skill/, skills/64-tmonk-mcp-stata/
R analysis	skills/00.3-Full-empirical-analysis-skill_R/, skills/55-ab604-claude-code-r-skills/
Game theory / theory papers	skills/65-game-theory-paper-writer/
Qualitative / thematic analysis	skills/53-keemanxp-thematic-analysis-skill/
Data acquisition (Kaggle, SEC filings, open data)	skills/72-kaggle-research/, skills/57-dgunning-edgartools/, skills/59-shiquda-openalex-skill/
Literature review	skills/36-taoyunudt-literature-review-skill/, skills/52-keemanxp-slr-prisma/, skills/59-shiquda-openalex-skill/
Lit-review tool selection / PDF→Markdown / cited Q&A over PDFs / PRISMA screening runners	skills/71-brycewang-lit-review-agent-tools/
Citation checking	skills/62-PHY041-claude-skill-citation-checker/
Manuscript writing / proofreading	skills/04-K-Dense-AI-claude-scientific-writer/, skills/38-peternka-academic-proofreader/
Peer review / referee reports / referee responses	skills/21-claesbackman-AI-research-feedback/, skills/12-pedrohcgs-claude-code-my-workflow/, skills/67-econfin-workflow-toolkit/
LaTeX / Quarto compilation, slides	skills/08-ndpvt-web-latex-document-skill/, skills/60-regisely-superpapers/, skills/12-pedrohcgs-claude-code-my-workflow/
De-AIGC / humanize	skills/48-de-AIGC-skills/, skills/45-stephenturner-skill-deslop/, skills/47-conorbronsdon-avoid-ai-writing/
Chinese SSCI/CSSCI journal polishing	skills/70-ssci-polish/, skills/49-voidborne-d-humanize-chinese/
Replication	skills/28-maxwell2732-paper-replicate-agent-demo/, skills/29-quarcs-lab-project20XXy/
Open science / reproducibility	skills/54-scdenney-open-science-skills/, skills/29-quarcs-lab-project20XXy/
Grant proposals / funding	skills/42-wanshuiyin-ARIS/, skills/43-wentorai-research-plugins/
Conference posters / post-acceptance	skills/42-wanshuiyin-ARIS/, skills/33-Galaxy-Dawn-claude-scholar/

Full-pipeline trigger

If the user is asking for a complete empirical paper from idea to submission, route to skills/69-Paper-WorkFlow/. The orchestrator loads the right skill at the right stage and stops for human decisions at the two hard gates (Method Gate after Stage 3, Draft Quality Gate after Stage 7).

Trigger phrases (any one is enough to dispatch to the orchestrator):

• /paper-workflow
• "帮我写一篇实证论文"
• "从选题到投稿"
• "end-to-end empirical paper"
• "完整复现"
• "from proposal to submission"
• "从数据到 docx 论文全文" / "一条龙" / "出一份 Word 版论文"
• "raw data to a finished Word manuscript"

The orchestrator is not the right entry point for a single-task ask (e.g. "fit a DiD", "recode this variable", "write a referee report") — those are listed in the Method → where to start table above.

Coverage Notes

• skills/69-Paper-WorkFlow/ is a git submodule. If its folder is empty, the copy or clone skipped submodules (git submodule update --init fixes a clone); fall back to the skills/00* flagship pipeline skills, which are vendored directly. Those end at publication-ready tables and figures plus a Step 8.5 handoff contract (exhibits_index.md + results_summary.json); pair them with a writing skill for the manuscript itself, since assembling and gating the full .docx lives in the orchestrator.
• The vendored ARIS collection (skills/42-wanshuiyin-ARIS/) also ships its skill set as OpenAI Codex CLI runtime ports (skills-codex* subtrees). Those stay on disk but are excluded from catalog/skills.json (see scripts/skill_discovery.py) — route Claude agents to the primary skills/ tree only.

Install Notes

• Whole-repo imports are supported by this root SKILL.md as a lightweight compatibility entry point.
• Individual skill installs are still preferred when a runtime expects one folder per skill. Copy the folder that directly contains the target SKILL.md.
• Do not copy the repository root into a runtime and expect every child skill to become individually registered unless that runtime explicitly supports recursive skill discovery.
• Do not flat-install the whole catalog (e.g. symlinking every child folder into ~/.claude/skills). Every registered skill's description is loaded at session start — about 64k tokens for all 1,108 here — and runtimes truncate long skill listings, so matching gets worse, not better. Use a plugin, this router, or a handful of copied skills.
• Name collisions: the catalog contains 47 bare names shared across collections (e.g. data-analysis, lit-review, proofread); catalog/curation.json names one preferred copy of each, which scripts/find-skill.py returns. When a runtime registers skills by flat name, install one collection at a time, or disambiguate with the globally-unique qualified_name field in catalog/skills.json (<collection>::<name>, e.g. 12-pedrohcgs-claude-code-my-workflow::data-analysis), or the full skills/<collection>/.../SKILL.md path.

Key Files

• catalog/skills.json: machine-readable list of vendored skills.
• catalog/skills-enriched.json: same list plus tier, tags, quality_score, license, and commercial_use for filtering.
• catalog/curation.json: hand-curated routing tiers (core collections, the preferred copy of each duplicated name, out-of-domain prefixes). Ranking only — nothing is removed.
• scripts/find-skill.py: ranked search over the catalog (the router's search step).
• docs/SKILL_CATALOG.md: human-readable skill index.
• docs/TAXONOMY.md: task and method taxonomy.
• docs/GOLDEN_WORKFLOWS.md: ready-to-use empirical-research prompts.
• docs/INSTALL.md: runtime installation guidance for single-skill and whole-repo use.
• docs/CONTENT_ZH.md and README-zh-CN.md: Chinese-language collection index and entry point. Prefer these when the user is working in Chinese — several collections (de-AIGC, SSCI/CSSCI polishing, Chinese academic writing) are documented there in more detail than in the English docs.