ai-asset-pricing

Create a new empirical research project: generates projects/<name>/ with latex, code, scripts, results, literature, and guidance subfolders plus README.md and project-level CLAUDE.md.

Publication-ready figure conventions for empirical finance and economics. Covers matplotlib styling, color palettes, export settings, and common figure types (time series, decile bars, coefficient plots, event studies). Auto-apply when creating any figure, plot, or visualization.

Agent-driven cold-start onboarding. Use the repo shell entrypoint to find or install Python 3.11+, then run the shared bootstrap audit/plan/apply flow and configure WRDS only if the user has it.

Create and compile Beamer presentations following the Rhetoric of Decks philosophy. Use when making seminar or conference slides.

Compile LaTeX to PDF using pdflatex + bibtex cycle

Creates new Claude Code skills, auto-apply skills, or auto-trigger rules, or audits existing ones for quality and effectiveness.

Clean and fix .tex files -- strip comments, fix compilation errors, verify section markers

Draft response letter text and LaTeX edits for referee points, or generate a complete reply document

Fast batch/single portfolio sort on Dickerson bond data. Bypasses orchestrator agent — runs directly via Bash. Use for known workflows on real data. Examples: /run batch cs ytm bbtm, /run batch cs ytm --wfs, /run single cs --nport 10

Scaffolds a new academic paper from the LaTeX boilerplate template. Copies template files, replaces placeholder tokens with user-provided title, authors, and affiliations, writes [REMOVE]-tagged filler content with Fama-French citations, and compiles a test PDF. Use when starting a new paper or creating a fresh LaTeX project.

Detect documentation drift and propose updates to docs/ai/, AGENTS.md, and CLAUDE.md. Use when session-start warnings flag stale docs, after significant code changes, or periodically to keep context current.

Use this skill when the user needs to query WRDS data via PostgreSQL from the local machine. Covers psql connection using .pgpass credentials, query execution patterns, CSV/parquet export, and best practices for large extractions. Invoke when the user wants to pull data from WRDS (CRSP, OptionMetrics, Compustat) via SQL.

Write a new section or subsection of an empirical finance paper following academic writing rules

Adversarial research idea generator for empirical asset pricing. Surveys literature via Perplexity, stress-tests hypotheses, maps WRDS data feasibility, and compiles a research plan skeleton. Use when brainstorming new paper ideas, sharpening existing hypotheses, or resuming a prior ideation session.

Rules and gotchas for CRSP, Compustat, and financial panel data: safe lagging/leading with date gap checks, look-ahead bias prevention, CCM linking, book equity construction, and missing value conventions. Auto-apply when working with CRSP, Compustat, or financial panel data.

Audit all table and figure captions for language, notation, and formatting consistency

Adversarial audit of mathematical proofs, derivations, and formal environments

Deep audit of a single section -- style, factual accuracy, citations, logical flow

Generate guidance/paper-context.md from user-provided .tex, .md, or .pdf files

Fast cross-section consistency scan for numbers, terminology, and references

Show diff between current and proposed text with change rationale

Revise an existing section for style, clarity, and correctness

Extract a section from main.tex by key name

Audit the entire paper -- cross-section consistency, all citations, all style issues

Analyze paper structure — section balance, word counts, Cochrane-principle compliance

Search for academic papers, references, and methodology literature using Perplexity MCP

Download, split, and deeply read academic PDFs with adaptive chunking. Splits into optimally-sized chunks based on paper length, reads in controlled batches, and produces structured extraction notes tailored for empirical finance papers.

Audit citations in LaTeX files -- check all \cite keys exist in .bib and verify via Perplexity

Reference for the Dickerson corporate bond dataset: column mappings between WRDS and PyBondLab, rating encoding, return definitions, signal clusters, and data gotchas. Auto-apply when loading bond data for PyBondLab analysis.

Creates new Claude Code agent configuration files or audits existing ones in .claude/agents/. Validates frontmatter, routing keywords, body-frontmatter alignment, ecosystem integration, and cross-agent consistency using a 17-point checklist.

Look-ahead bias prevention and portfolio formation rules for cross-sectional asset pricing factors. Covers signal timing, portfolio sorts, return alignment, and rebalancing conventions. Auto-apply when constructing factors, sorting stocks into portfolios, or computing long-short returns.

Mechanical error scan -- typos, LaTeX formatting, punctuation, spacing

Generates structured results reports after PyBondLab portfolio formation runs. Auto-apply when running StrategyFormation, BatchStrategyFormation, BatchWithinFirmSortFormation, or any portfolio sorting with PyBondLab.

Creates new .claude/rules/ files following best practices, or audits existing rules for quality and effectiveness.

Analyze LaTeX text for violations of academic writing standards

Pre-submission checklist for JF, RFS, JFE, or other target journals

Use this skill at the start of a session when working with WRDS data (CRSP, OptionMetrics, Compustat, TAQ). It pre-loads schema knowledge — table names, column names, join keys, data types, and common gotchas — so you can write correct queries without exploratory round-trips. Invoke when the user mentions WRDS, OptionMetrics, CRSP, or structured product / options analysis.

This skill should be used when the user needs to connect to WRDS servers, run SAS code on WRDS, execute SQL queries on WRDS PostgreSQL, submit batch jobs to WRDS, or transfer files to/from WRDS. Use this skill whenever WRDS server access is required for data extraction, processing, or analysis.