Claude Skills by brycewang-stanford

Run the proofreading protocol on manuscript files. Checks grammar, typos, overflow, consistency, and academic writing quality. Produces a report without editing files.

Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset.

Run the Julia code review protocol on Julia scripts. Checks code quality, type stability, parallel computing patterns, and scientific computing standards. Produces a report without editing files.

Comprehensive manuscript review covering argument structure, identification strategy, econometric specification, citation completeness, and potential referee objections.

Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional standards. Produces a report without editing files.

Comprehensive Stata reference for writing correct .do files, data management, econometrics, causal inference, graphics, Mata programming, and 17+ community packages (reghdfe, estout, did, rdrobust, etc.). Covers syntax, options, gotchas, and idiomatic patterns. Use this skill whenever the user asks you to write, debug, or explain Stata code.

Validate bibliography entries against citations in all manuscript files. Find missing entries and unused references.

End-to-end data analysis workflow in R or Python — from exploration through regression to publication-ready tables and figures. Make sure to use this skill whenever the user wants to run any empirical analysis, write analysis code, or produce output from data. Triggers include: "analyze this data", "run a regression", "write R code for this", "write Python code for this", "I have a dataset", "help me with this regression", "run a DiD", "run an RDD", "event study", "IV regression", "fit a mode...

Find and assess datasets for a research question. Dispatches Explorer agents to search across data source categories, then Explorer-Critic to stress-test each candidate. Produces a ranked list with feasibility grades. Make sure to use this skill whenever the user wants to identify or evaluate data sources — not to search for papers or run analysis. Triggers include: "find data", "what data should I use", "find a dataset for this", "where can I get data on X", "assess datasets", "what datasets...

Deep consistency audit of the entire repository — launches 4 parallel specialist agents to find factual errors, code bugs, broken references, count mismatches, and cross-document inconsistencies, then fixes all issues and loops until clean. Make sure to use this skill whenever the user wants a comprehensive repository-wide check — not a targeted review of a single file. Triggers include: "audit", "deep audit", "find inconsistencies", "check everything", "run a full audit", "are there any brok...

Structured literature review using a parallel fleet of Librarian agents. Searches top journals, working paper repositories (NBER, SSRN, IZA), and traces citation chains from key papers. Make sure to use this skill whenever the user wants to survey existing research on a topic — not to find datasets or write a paper. Triggers include: "review the literature", "find related papers", "what's been done on X", "search for papers on", "do a lit review", "find papers about", "what papers should I ci...

Start a new research project by conducting a structured interview to formalize a research idea, then generates research questions with identification strategies and a project spec. Make sure to use this skill whenever the user wants to develop or document a new research idea — not to search for literature or data. Triggers include: "new project", "start research", "I have an idea", "help me develop this", "I want to study X", "help me formalize this idea", "what's my research question", "what...

Run the proofreading protocol on academic writing — papers or manuscripts. Checks grammar, typos, layout issues, consistency, and academic writing quality. Produces a report without editing files. Make sure to use this skill whenever the user wants surface-level writing errors found — not substantive academic critique. Triggers include: "proofread", "check for typos", "grammar check", "look for errors in my draft", "proofread all", "polish this", "check my writing", "are there any mistakes", ...

Verify that every quantitative claim in the paper is traceable to an analysis output file, and that no important output was omitted. Make sure to use this skill whenever the user wants to check that the paper and analysis are consistent before submission. Triggers include: "run the quality gate", "check the paper matches the analysis", "verify consistency", "does the paper match my results", "check my numbers", "are my tables right", "quality check before submission", "verify my claims", "mak...

Interactive setup wizard that configures a new project for the social-science-research plugin. Asks the user questions about their field, institution, journals, datasets, key researchers, and R color palette, then writes the answers into references/domain-profile.md and CLAUDE.md. Make sure to use this skill first whenever a user is starting fresh or wants to configure the plugin. Triggers include: "set up my project", "configure the plugin", "run setup", "initialize this project", "I just in...

Comprehensive manuscript review covering argument structure, econometric specification, citation completeness, and potential referee objections. Make sure to use this skill whenever the user wants substantive academic feedback on a paper — not just surface edits. Triggers include: "review my paper", "give me feedback on this draft", "what would a referee say", "anticipate referee objections", "act as a referee", "check my identification strategy", "is my argument convincing", "review this man...

Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional standards. Produces a report without editing files. Make sure to use this skill whenever the user wants their existing R code evaluated or audited — not when they want new analysis written. Triggers include: "review my R script", "check my R code", "is my code replication-ready", "audit this R file", "does this code follow conventions", "will this reproduce", "check my analy...

Validate bibliography entries against citations in all source files. Find missing entries and unused references. Make sure to use this skill whenever the user has any concern about bibliography completeness or citation keys. Triggers include: "validate my bib", "check my citations", "find missing references", "I'm getting undefined citation errors", "are all my citations in the bib file", "check for unused references", "my bibliography is broken", "missing bib entries", "citation not found", ...

Draft a full academic paper manuscript from analysis outputs, project spec, and lit review. Make sure to use this skill whenever the user wants to turn completed analysis into a written paper — not to run analysis or review existing writing. Triggers include: "write the paper", "draft the manuscript", "write up the results", "start the paper", "turn my results into a paper", "write the introduction", "draft the empirics section", "I have my results, now write the paper", "help me write this u...

End-to-end data analysis dispatching Coder and Data-engineer for implementation, coder-critic for review. Supports R, Stata, Python, Julia. Replaces /data-analysis.

Discovery phase combining research interviews, literature search, data discovery, and ideation. Routes to appropriate agents based on arguments. Replaces /interview-me, /lit-review, /find-data, /research-ideation.

Full research pipeline from idea to paper. Orchestrates all phases — discovery, strategy, analysis, writing, peer review, and submission. Use when starting a new research project from scratch.

All quality reviews — routes to appropriate critics based on target file type and flags. Replaces /paper-excellence, /proofread, /econometrics-check, /review-r, /review-paper.

R&R cycle — classify referee comments and route to appropriate agents. Replaces /respond-to-referee.

Design identification strategy or pre-analysis plan. Dispatches Strategist (proposer) and strategist-critic (validator). Replaces /identify and /pre-analysis-plan.

Submission pipeline — journal targeting, replication package, audit, and final gate. Replaces /submit, /target-journal, /audit-replication, /data-deposit.

Create and audit presentations (Beamer or Quarto RevealJS). Combines talk creation, visual audit, and compilation. Replaces /create-talk, /visual-audit, /compile-latex (for talks).

Utility commands — commit, compile, validate-bib, journal, context-status, deploy, learn. Replaces individual utility skills.

Draft academic paper sections with notation protocol, anti-hedging, and humanizer pass. Replaces /draft-paper and /humanizer.

Guide for creating DAAF agent definition files. Covers 12-section template, hook registration, skills-in-frontmatter, integration checklist. Use when adding or revising agents. For SKILL.md files, use skill-authoring instead.

Operational framework for the DAAF orchestrator. Defines engagement modes, confirmation protocol, subagent dispatch, context budget, and reference-loading. Loaded exclusively by the orchestrator — not for subagents or user questions.

Data science methodology for Python research: EDA, validation, causal inference (IV, DiD, RD, synthetic control), clustering/PCA/UMAP, supervised ML, geospatial, visualization. Method selection guidance. For syntax, load tool-specific skills.

Interpretation guidance for Urban Institute Portal datasets. Coded values (-1/-2/-3), year definitions, grade encoding, suppression, licensing, cross-source joins. Use when interpreting Portal data before analysis. Routes to source-specific skills.

Discovers education data from Urban Institute Portal: endpoints, variables, year coverage, join keys (CCD, IPEDS, CRDC, Scorecard, SAIPE). Use to map questions to data. Load before education-data-query — discovery here, download there.

Downloads education datasets from configured mirror sources (parquet/CSV) with local Polars filtering. Use when writing fetch scripts or retrieving CCD, IPEDS, CRDC, SAIPE data. Load after education-data-explorer — retrieval here, not discovery.

CSS — annual Clery Act crime/fire safety for Title IV institutions. Portal: hate crimes only (2005-2021); primary offenses, VAWA, arrests, fire safety need ope.ed.gov directly. Use for campus crime analysis. Identified by IPEDS unitid.

CCD — federal universe of all U.S. public K-12 schools (~100K) and districts (~18K). Enrollment, staffing, finance, directory data (1986-present). Use for public school analysis by grade/race/sex. Public only; excludes private and postsecondary.

CRDC — biennial OCR survey of all U.S. public schools (2011-2021). Discipline, course access, harassment, restraint/seclusion by race/sex/disability/EL. Use for civil rights and equity analysis. 2020-21 COVID-impacted; 2011-14 sampled, not universe.

EADA — college athletics gender equity (~2,000+ institutions, 2002-2021). Participation, coaching, salaries, expenses, revenues, athletic aid by gender. Not Title IX compliance data. No sector column; join IPEDS on unitid for institution type.

EDFacts — K-12 outcomes: assessment proficiency, ACGR graduation rates, ESSA accountability at school/district level (2009-2020). Within-state trends and subgroup gaps. Complements CCD with outcome data. Cannot compare across states — use NAEP.

FSA — Title IV aid at institution level (~5,500 institutions, 1999-2021). Pell Grants, Direct/PLUS loans, campus-based aid, financial responsibility scores, 90/10 metrics. Use for aid distribution, loan volume, or for-profit analysis. By unitid.

IPEDS — primary federal postsecondary data (~6,500 institutions, 1980-present): enrollment, completions, graduation rates, finance, aid, admissions, HR. For college/university analysis. Grad rates = first-time full-time; finance needs GASB/FASB care.

MEPS — Urban Institute modeled school-level poverty (% at 100% FPL), from CCD + SAIPE (public schools, 2009-2022, 2-3yr lag). Use when FRPL is unreliable due to CEP. Consistent cross-state measurement. Public schools only.

NACUBO endowment data (~650 institutions, 2012-2022). Portal: 7 columns only (total endowment, per-FTE, YoY change). Use for endowment size/trends. Full investment/spending needs direct NACUBO access. For all-institution coverage use IPEDS finance.

NCCS — Form 990 data for private nonprofit colleges (Portal: IPEDS-matched, 1993-2016). Revenue, expenses, assets, endowment, governance beyond IPEDS. Use when IRS financial depth needed. Portal ends 2016; public institutions excluded (no Form 990).

NHGIS — census geography crosswalks via Portal: links schools (ncessch) and colleges (unitid) to tracts, block groups, CBSAs (1990-2020). Census demographics NOT in Portal — access NHGIS directly. Use for linking education data to census geography.

PSEO — Census data linking graduates to employment via LEHD wage records. Earnings percentiles at 1/5/10 years post-graduation by institution, degree, CIP. Use for graduate earnings analysis. Coverage: ~29% of graduates from ~31 states.

SAIPE — annual Census poverty estimates for school districts (Portal; county/state not in Portal). Use for district poverty, Title I context, or trends. ~18-month lag. No race/ethnicity disaggregation at district level — use ACS 5-year for that.

College Scorecard — post-enrollment outcomes linking aid records to IRS/Treasury earnings. Earnings, loan repayment, debt via six Portal sub-datasets. Use when tax-record-based earnings needed. Tracks only Title IV aid recipients, not all students.

County Presidential Returns 2000-2024 (MIT MEDSL). Vote shares, party trends, turnout by county_fips (joins census/education data). Requires HARVARD_DATAVERSE_API_KEY. Critical: mode='TOTAL' drops ~1K counties post-2020 — use 3-pattern reconstruction