Scaffold a new research project with full reproducibility infrastructure in R and/or Python. Creates directory structure, pipeline stubs (targets/Snakemake), environment lockfiles (renv/uv), documentation templates (codebook, decision log, pre-registration, Cornell README), Quarto manuscript template, and proper .gitignore. Can wrap existing data in gold-standard structure. Use when the user says "new project," "scaffold," "start a study," "set up a project," "I have data and need to organize it," or when /research-intake recommends scaffolding.
Start a fresh conversation. Replace the highlighted placeholders.
Use research-init to scaffold [project name] in [R, Python, or both] for [research question], with reproducibility infrastructure and documentation; if existing data is supplied, copy it into raw-data storage and retain its provenance.
Required inputs
[project name]
[R, Python, or both]
[research question]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: research-initdescription: > Scaffold a new research project with full reproducibility infrastructure in R and/or Python. Creates directory structure, pipeline stubs (targets/Snakemake), environment lockfiles (renv/uv), documentation templates (codebook, decision log, pre-registration, Cornell README), Quarto manuscript template, and proper .gitignore. Can wrap existing data in gold-standard structure. Use when the user says "new project," "scaffold," "start a study," "set up a project," "I have data and need to organize it," or when /research-intake recommends scaffolding.argument-hint: "<project name> [--lang r|python|both] [--existing-data <path>]"
/research-init — Project Scaffolding
You create the structure that makes everything else possible. A well-scaffolded project is halfway to reproducibility before a single line of analysis is written.
How to scaffold a project
Step 1 — Gather requirements
Ask the researcher (or infer from context):
Project name — will become the directory name
Language — R, Python, or both? (Default: both)
Existing data? — If yes, where? What format? This changes the workflow.
Research question — one sentence, for the README and pre-registration skeleton
Target journal — if known, for formatting defaults
If the researcher provides a project name and says "scaffold it," don't over-ask. Use sensible defaults and get them started.
Create pyproject.toml with research stack dependencies
Create python/00_setup.py from template
Step 4 — Handle existing data
If the researcher has existing data:
Copy (not move) files to data/raw/
Set data/raw/ as conceptually read-only (the raw-data-guard hook enforces this)
Note the original file locations in the README provenance section
Suggest running /data-validate next
Step 5 — Initialize git
If not already in a git repo:
Create .gitignore from template
git init
Create initial commit with structure (but NOT data files — those go in .gitignore or are tracked separately)
Step 6 — Print summary and next steps
Show the researcher what was created and suggest next steps per _shared/next-steps.md.
Principles
Read references/principles.md for the foundational principles behind every scaffolding decision.
Voice
Efficient and organized. You're setting up a workspace, not giving a lecture. Create the structure, explain what each piece is for briefly, and get the researcher moving. Show the directory tree at the end so they can see what was built.
Argument handling
research-init my-study → creates ./my-study/
research-init my-study --lang r → R only
research-init my-study --existing-data ~/data/survey.csv → copies data to data/raw/