ericluo04

litreview

Find and synthesize the literature on a topic or research question, returning a ranked reading list with a takeaway per paper. TRIGGER on "lit review", "find papers on X", "what is the literature on Y", "recent work on Z", "who has studied W", "find references for my intro", or a topic plus a scope phrase ("since 2022", "Marketing Science only"). One paper the user already has is reading-papers.

bibcheck

Audit an existing .bib entry by entry against Crossref, OpenAlex, arXiv, and Zotero for wrong years, mis-cited authors, wrong venue or volume, dead DOIs, and hallucinated entries. TRIGGER on "/bibcheck", "audit my .bib", "verify my references", "check my bibliography", "are any of these citations fake", "did Claude hallucinate a citation", or a pre-submission bib audit.

council

Five independent critic subagents in parallel on an idea, plan, design, R&R strategy, grant, or SKILL.md, then a synthesis pass that ranks findings by how much of the argument rests on them, never by vote count. TRIGGER on "council", "spawn critics", "parallel critique", "kitchen cabinet", "panel review", "stress-test this", "poke holes in this", "what would five experts say". A complete manuscript goes to review-paper.

rdd

Design, estimate, validate, and write up a regression discontinuity analysis, in both the continuity and local-randomization frameworks, with the full falsification battery and a refusal rule for designs that fail validation. TRIGGER on "regression discontinuity", "RDD", "running variable", "cutoff", "rdrobust", "bandwidth", "McCrary test", "density test", "fuzzy RD", "regression kink", or any setting where treatment switches at a known score threshold (loyalty tiers, spend thresholds, ranking cutoffs, algorithmic triggers, eligibility scores, age or tenure rules).

synthetic-control

Design, estimate, validate, and write up a synthetic control analysis, including synthetic difference-in-differences, augmented and penalized variants, and factor-model/matrix-completion relatives for panel counterfactuals. TRIGGER on "synthetic control", "synthetic DiD", "SDID", "donor pool", "comparative case study", "geo holdout", "CausalImpact", "matrix completion", "interactive fixed effects", "gsynth", or any setting where one or a few aggregate units (a state, market, DMA, category, platform region) got treated and untreated units must form the counterfactual. Many treated units with staggered timing belong to did; choosing treatment markets prospectively to field-experiment.

preregister

Draft a registry-ready preregistration or preanalysis plan for AsPredicted, OSF, or the AEA RCT Registry. TRIGGER on "preregister", "draft a preregistration", "AsPredicted form", "OSF prereg", "AEA RCT registry", "PAP", "preanalysis plan", or before launching a vignette, conjoint, MTurk/Prolific, or field experiment. Refuses to write one for analyses already run on data already seen.

compile-latex

Compile a .tex with latexmk and report ranked errors with file:line attribution across \input'd files, plus a diff against the last compile. TRIGGER on "compile this", "build my paper", "build the beamer deck", "why won't this compile", "what are the latex errors", "did my edit add warnings", or any request to build or debug a LaTeX document. TRIGGER also on polishing or debugging a TikZ or pgfplots figure whose labels overlap or that "looks wrong" (the --figures loop). Quarto .qmd decks belong to research-talk and teaching-lecture.

referee-response

Draft an R&R response letter to a journal decision, sectioned by Senior Editor, Associate Editor, and each reviewer, and check a finished letter before resubmission. TRIGGER on "respond to the referees", "draft the R&R response", "write the R2R", "address the reviewer comments", "respond to the AE", "continue the R2R", "check the R2R letter", or when the user pastes reviewer comments or a decision letter.

replication-package

Assemble a journal-ready replication archive for a quantitative-marketing paper, scanning for secrets, PII, and absolute local paths before the zip is built. TRIGGER on "/replication-package", "build a replication package", "data availability statement", "zip up the code and data for submission", a data-editor email asking what to send, or any "gather everything a replicator would need" request.

causal-design

Triage a causal question to the identification strategy the data can support, then hand off to the owning method skill. Owns the selection-on-observables branch (overlap, doubly robust estimation, double ML, causal forests, policy learning, sensitivity analysis), plain panel fixed effects, and the inference rules shared across designs (clustering, multiplicity, interference routing). TRIGGER on "identification strategy", "which causal method", "research design", "endogeneity", "quasi-experiment", "natural experiment", "selection on observables", "unconfoundedness", "propensity score", "doubly robust", "double machine learning", "causal forest", "policy learning", "sensitivity analysis", "Oster bounds", "overlap", "panel fixed effects", "strict exogeneity", "surrogate index", "mediation", or "how do I estimate the effect of X on Y" with no design chosen yet. Once a design is named, its method skill owns it.

teaching-lecture

Author a Quarto reveal.js lecture deck for a class meeting. TRIGGER on "build a lecture", "slides for my class", "teaching deck", "lecture on X", "course slides", "make a lecture for week 3", "add a discussion slide". Conference and seminar decks are research-talk, the site around the decks is course-site, auditing an existing deck is slide-review.