lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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…
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Write an AsPredicted pre-registration for a study. Walk through each field with the user, then produce a complete pre-registration document.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
This is default workflow for data analysis. It includes steps for data cleaning, exploration, and visualization.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Roundtrip a LaTeX manuscript to Google Docs for coauthor feedback and back. Reads the compiled PDF, writes clean text + figures + tables into a Google Doc via gws, and can pull comments/edits back into the LaTeX source.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Reproducible manuscript workflow where scripts generate numbers, tables, and figures that are read into LaTeX. Tables are split so scripts output only the tabular body; LaTeX wraps it in table environments. Iteration happens by rendering and reviewing the compiled PDF.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
End-of-session wrap-up — updates todo.md, comms.md, and currentstate.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.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Search for and rank job openings, grants, prizes, and fellowships relevant to the user's profile. Produce a structured markdown report saved to disk.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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…
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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".
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Build a Qualtrics survey from specs using the qualtricssdk 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.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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.
lirabenjamin/claude-code-for-researchers
Skill Claude Code
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…
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Rules and a checklist for writing clear, concrete, reader-first scientific prose (active voice, strong topic sentences, short sentences, concision, jargon control, narrative structure). Use this skill when drafting or revising research writing such as papers, abstracts, or manuscript sections.
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
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…
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Compute three measures of semantic diversity on a parquet of texts — word-level DSI (BERT layers 6+7, Beaty/Patterson 2022 recipe), sentence-level mean pairwise cosine distance (SBERT all-MiniLM-L6-v2), and document-level chamfer Distinctness (OpenAI text-embedding-3-large, min cosine distance to any other doc in the…
lirabenjamin/claude-code-for-researchers
Skill Claude CodeCodex
Fetch a Zotero collection's items and PDFs to a local folder so Claude can read them. Use when the user wants to read, analyze, summarize, or reference papers from a specific Zotero collection by name (e.g., "read my Zotero collection linksudip", "fetch papers from my twins collection and summarize"). Creates an…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: