cloco

Sync the overleaf/ folder with the current content of paper/. Copies all LaTeX source, figures, tables, appendix, and bibliography. Puts the model section as overleaf/model.tex (top-level) for easy coauthor access. Run whenever paper/ changes and you want to push to Overleaf.

RA onboarding audit — explore all project folders and code, inspect data files directly, and produce a structured project-state document that enables a clean restart. Use at the start of a project hand-off or when picking up work from multiple prior contributors.

Full bibliography audit for an academic paper. Verifies every citation is (1) structurally correct in the .bib file, (2) actually cited in the paper, and (3) a real publication — author names, year, journal, and title verified via web search. Flags hallucinated or inaccurate references.

Design identification strategy by dispatching the causal-strategist agent (proposer) and identification-critic agent (critic). Produces strategy memo, pseudo-code, robustness plan, and falsification tests. Use when asked to "identify the effect", "design the strategy", or "write the strategy memo".

Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.

Show the current research pipeline status for the active project, or display the pipeline guide for a specific project type. Reads the research spec, research journal, and active plans to determine phase, scores, and next steps.

Validate replication package by dispatching the replication-verifier agent in submission mode (checks 1-10). Runs master script, cross-references tables and figures against paper, verifies README completeness for AEA Data Editor compliance. Use before data deposit or journal submission.

Generate academic presentations (Beamer .tex or Quarto RevealJS .qmd) by dispatching the storyteller agent (creator) and discussant agent (critic). Supports 4 formats — job market, seminar, short, lightning. Derives all content from paper/main.tex.

End-to-end data analysis dispatching Coder (main Claude) for implementation and Debugger agent for code review. Supports R, Stata, Python, and Julia. Produces scripts, tables, figures, and results summary.

Prepare AEA Data Editor compliant replication package by dispatching Coder (main Claude) for package assembly and replication-verifier agent for validation. Generates README, master script, numbered script order, and deposit checklist.

Draft academic economics papers by dispatching the economics-paper-writer agent. Handles section drafting, notation protocol, anti-hedging, and humanizer pass. Use when asked to "draft the paper", "write up the results", or "write the intro".

Causal inference design audit. Dispatches the econometrics-critic agent in standalone mode for 4-phase review (claim, design validity, inference, polish). Covers DiD, IV, RDD, Synthetic Control, and Event Studies. Use when working on empirical papers, strategy memos, or R scripts with causal estimators.

Data discovery and assessment dispatching the explorer agent (finder) and data-quality-surveyor agent (critic). Searches public, administrative, survey, and novel data sources. Scores feasibility and measurement quality.

Strip AI writing patterns from text. Standalone access to the economics-paper-writer agent's humanizer pass. Checks 24 patterns across 4 categories (structural, lexical, rhetorical, formatting) with academic adaptation. Use on any text that reads too "AI-generated".

Interactive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy

Regenerate the research journal timeline from quality reports and git history. Shows chronological record of all agent actions, phase transitions, scores, and decisions. Use to review project history or audit the research process.

Structured literature search dispatching the academic-librarian agent for collection and academic-editor agent for coverage critique. Searches top-5 journals, NBER/SSRN, and field journals. Produces synthesis with gap identification and BibTeX entries.

Full research pipeline from idea to paper. Orchestrates all phases — interview, literature review, data discovery, identification strategy, analysis, paper drafting, and peer review. Use when starting a new research project from scratch.

Multi-agent paper review dispatching econometrics-critic, debugger, academic-proofreader, and replication-verifier in parallel. Computes weighted aggregate score per scoring-protocol.md. Use for comprehensive quality check before submission or major milestones.

Draft pre-analysis plans by dispatching the causal-strategist agent in PAP mode. Covers AEA RCT Registry, OSF, and EGAP standards. Specifies outcomes, subgroups, multiple testing, power calculations, and exclusion rules.

Manuscript proofreading dispatching the academic-proofreader agent. Checks 6 categories — structure, claims-evidence alignment, identification fidelity, writing quality, grammar, and compilation. Produces report without editing files.

Structure point-by-point referee responses using the revision-protocol routing. Classifies comments (NEW ANALYSIS / CLARIFICATION / DISAGREE / MINOR), dispatches appropriate agents, and tracks revisions. Use when asked to "respond to referees" or "draft revision".

Code review dispatching the Debugger agent in standalone mode (categories 4-12 only). Checks code quality, reproducibility, output standards, and professional polish. Use for R, Stata, Python, Julia, or any analysis script.

Full manuscript review dispatching 2 blind blind-peer-referee agents and the academic-editor agent for editorial decision. Produces referee reports and accept/revise/reject recommendation. Use when asked to "review the paper", "get feedback", or "simulate peer review".

Design and implement structural estimation strategies by dispatching the structural-estimation-expert agent. Covers model solution methods, estimation (MLE, GMM, SMM, indirect inference, Bayesian), calibration, and model fit evaluation. Use when asked to "estimate the structural model", "solve the model", "design the GMM moments", or "implement BLP".

Final submission verification gate. Runs replication-verifier in submission mode (10 checks), confirms aggregate score >= 95 with all components >= 80, and generates submission checklist. Use when ready to submit to a journal.

Journal targeting dispatching the academic-editor agent in journal-selection mode. Analyzes paper fit, suggests ranked journal list from domain-profile.md tiers, provides formatting requirements and submission strategy.

Develop formal theoretical models in economics or finance by dispatching the econ-finance-theorist agent. Derives formal frameworks, proofs, equilibrium conditions, and pricing theories. Use when asked to "build a model", "formalize the intuition", "derive equilibrium", or "write the theory section".

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

Visual layout audit of Beamer (.tex) or Quarto (.qmd) slide decks. Dispatches the discussant agent for scored review covering overflow, font consistency, paper fidelity, narrative arc, and compilation. Advisory score — non-blocking.