Explore Agent Skills

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

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

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

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

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

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

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.

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.

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

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 up", "write the abstract", or any request to produce academic prose from existing research outputs.

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", or after adding new references from a lit review or before submission.

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 analysis script", "code review", "review-r", or when the user has an existing .R file and wants quality feedback rather than new code.

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 manuscript", "critique my paper", "will this pass review", or any request for deep critique of academic writing beyond typos and grammar.

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 installed the plugin", "set my field", "set my institution", "configure my domain profile", or any request to personalize the plugin for a specific research context.

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", "make sure everything is consistent", "double-check the paper against my output files", or any pre-submission integrity check between paper text and computed results.

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", "proofread before I send this", or when the user wants a clean-up pass rather than feedback on arguments or methods.

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 identification strategy should I use", "write up my project idea", or when the user describes a topic they want to turn into a paper.

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 cite", "who has written about this", "survey the literature", "find prior work on", or any request to locate and summarize academic publications on a topic.

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 broken references", "check the whole repo", "something feels off", "run the audit loop", or after making broad changes across multiple files.

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 exist for", "help me find data", "is there data on this", "what are my data options", "I need data for this project", or any request to locate empirical data sources for a research question.

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 model", "produce a table", "make a figure", "explore my data", or any request involving a dataset path or empirical estimation.

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

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.

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