claude-code-for-researchers

End-of-data-collection workflow. Exports raw MongoDB data as JSONL, writes a companion README documenting schema + provenance, commits both to the repo, and archives the raw dataset to Zenodo with a permanent DOI. Use when the user says "data collection is done", "freeze the data", "archive the raw data", "post the raw data to Zenodo", "collection is complete", or is closing out a study.

Build a Qualtrics survey from specs using the qualtrics_sdk Python package. Give a description of your survey (questions, blocks, logic, embedded data) and this skill generates and runs a Python script to create it on Qualtrics.

Interact with Google Workspace (Drive, Docs, Sheets, Gmail, Calendar, etc.) using the `gws` CLI. Use this skill when the user wants to read, create, edit, or search Google Docs, Sheets, Drive files, or any Google Workspace resource.

Write an AsPredicted pre-registration for a study. Walk through each field with the user, then produce a complete pre-registration document.

This is default workflow for data analysis. It includes steps for data cleaning, exploration, and visualization.

End-of-session wrap-up — updates todo.md, comms.md, and current_state.md with session summary, commits/pushes if git repo, and creates a handoff briefing for the next session. Use when the user says "log off", "wrap up", "call it a night", "done for today", or is ending a work session.

Send the user an iMessage notification when a long-running task finishes. Use after any multi-step or long-running task, especially one the user has stepped away from.

Search for and rank job openings, grants, prizes, and fellowships relevant to the user's profile. Produce a structured markdown report saved to disk.

Audit a research data-code-output-manuscript pipeline for correctness and consistency. Use this skill whenever the user wants to verify their analysis pipeline, check for bugs in statistical code, find hardcoded numbers in a manuscript, or ensure narrative descriptions match the actual results. Trigger phrases include "check my pipeline", "audit my code", "make sure my results are consistent", "verify my manuscript", "find magic numbers", or any request to do a full review of a research project's code and writeup.

Weekly plate check — pulls from Gmail, Google Calendar, Reclaim, todo.md, and CLAUDE.md to give the user a comprehensive briefing, triage stale tasks, flag conflicts, and generate a visual dashboard. Use when the user wants a status update, weekly review, or says "what's on my plate".

Create a single Quarto HTML document that contains multiple pre-rendered versions of an analysis (e.g. different datasets or model specifications), switchable via client-side JavaScript buttons — no re-render needed.

Scaffold and deploy a full-stack behavioral research survey (React + Express + MongoDB) on Render. Supports between-subjects conditions, phased survey flows, AI-assisted tasks, bot detection, keystroke tracking, and platform integrations (Prolific, CloudResearch Connect, Gallup). User describes conditions, stimuli, and measures; skill generates the complete app.

Fill out Wharton Behavioral Lab (WBL) study submission forms on JotForm. Use this skill whenever the user mentions WBL forms, study submission forms, scheduling a study launch, MKT form, OID form, Wharton Behavioral Lab, or wants to submit a study to the lab. Also trigger when user pastes a filled-in markdown template for either the MKT or OID form.