Use when starting empirical analysis, creating a data pipeline, generating results, or when data or model specifications change. Enforces end-to-end reproducibility — every number in the paper must be regenerable from raw data by a script with a fixed seed. Replaces TDD for the research domain.
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 19 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill86%
Checks it passed that the model alone missed
Directs saving execution logs in output/logs/.
Instructs prompting the user to specify a project-level default seed.
Rejects relying on cached intermediate outputs when script inputs change.
and 12 more in the full report
10 fixed9 passed either way3 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+50%
Agent turns
0%
Response time
-39%
Model gemini-3.6-flashMeasured 8/8/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
Our plotting script `code/04_figures.R` generates vector plots at `output/figures/event_study.pdf`. What LaTeX command must be used in `paper/paper.tex` to display this vector graphic?
What was checked, without and with the skill
Checked
Without skill
With skill
Requires using \includegraphics{output/figures/...} to include vector figures in LaTeX.
Missed
Passed
Specifies placing figure output files under output/figures/.
Passed
Passed
case-11 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md126 linessingle file
Replication-Driven Research
Overview
This skill is the research-domain analogue of test-driven development. The core philosophy is the same as TDD: evidence before claims, automated verification, invalidation on input change. No result is valid until the pipeline runs end-to-end without error. No number enters the paper until a script regenerates it from raw data. This is the single most important discipline in the superpapers plugin, and every analysis skill defers to it.
When to Use
Start of a new empirical project
First time running analysis code in a project
Before generating any table or figure for a paper
After any change to raw data, sample selection, or model specification
Before declaring a result "final" or "verified"
When the user asks "is this reproducible?"
When reviewer comments require re-running the analysis
Canonical Directory Structure
The canonical project layout is:
project-root/
├── data/
│ ├── raw/ # raw downloads, never manually edited
│ ├── processed/ # cleaned data, output of scripts
│ └── manifest.md # documents every dataset (source, URL, date, variables)
├── code/
│ ├── 01_collect.R # or .py — fetches raw data
│ ├── 02_clean.R # raw → processed
│ ├── 03_analyze.R # processed → results
│ └── 04_figures.R # processed → figures
├── output/
│ ├── tables/ # .tex files generated by scripts
│ ├── figures/ # .pdf vector files generated by scripts
│ └── logs/ # execution logs with timestamp + seed
├── paper/
│ ├── paper.tex # main document
│ ├── references.bib # bibliography
│ └── sections/ # split sections if needed
└── CLAUDE.superpapers.md # project settings