skills.rest
mronkko
mronkkoCOMMUNITY
Explore all skills by this author →
GitHub

empirical-integrity

Enforce pipeline-generated data provenance for quantitative claims in manuscripts.

20|11|Updated Apr 19, 2026
Search Tags:#validation#analysis#pipeline#statistics#manuscript#empirical-integrity#inline-expressions
One-click install
npx skills add https://github.com/mronkko/claude-academic-research --skill empirical-integrity
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: empirical-integrity
Source: https://github.com/mronkko/claude-academic-research/tree/main/skills/empirical-integrity
Command: npx skills add https://github.com/mronkko/claude-academic-research --skill empirical-integrity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Numbers in manuscript prose must come from pipeline-generated sources via code chunks or inline expressions, never hand-typed, to preserve accuracy and reproducibility.

Core Features & Use Cases

  • Enforces end-to-end provenance where every quantitative or methodological claim traces through analysis/raw/ → analysis/scripts/ → analysis/results/ → manuscript (code chunks or inline expressions).
  • Supports inline expressions from a project-owned stats dictionary (analysis/manuscript_stats.py with build_stats()) to render numbers in prose, ensuring consistency with the pipeline outputs.
  • Provides project-specific deny rules and lifecycle guidance to prevent edits to analysis/results/manuscript_stats.json and related artefacts, preserving data integrity.
  • Includes a validation test suite (test_empirical_integrity.py) to catch literals, mismatches, and rendering issues before publication and during manuscript drafting.

Quick Start

Run the project’s empirical-integrity test suite to confirm that every numeric claim in your manuscript traces to analysis/results and the stats dictionary.

Frequently Asked Questions about empirical-integrity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent hand-typed numbers in my Quarto or R Markdown manuscript?▼

To prevent hand-typed numbers in your manuscript, inline expressions and code chunks must render quantitative claims directly from pipeline-generated data stored in the results directory. A validation test suite catches manual literals before publication.

How do I ensure statistics in my manuscript prose match my analysis pipeline outputs?▼

Statistics in manuscript prose match analysis pipeline outputs by enforcing end-to-end provenance, rendering numbers via inline expressions from a project-owned stats dictionary. This dictionary is populated exclusively by pipeline-generated data.

Can I use inline expressions to populate numbers in a LaTeX manuscript from a stats dictionary?▼

Yes, you can use inline expressions in LaTeX manuscripts to populate numbers from a project-owned stats dictionary. This dictionary is generated through the analysis pipeline, ensuring every quantitative claim traces directly to raw data outputs.

What is the best way to validate that every quantitative claim in a manuscript traces back to original data?▼

The best way to validate quantitative claims is running a dedicated validation test suite that enforces end-to-end provenance. This suite catches literals, mismatches, and rendering issues by confirming numbers come solely from pipeline outputs.

Why should I not manually edit the manuscript_stats.json file generated by my analysis pipeline?▼

You should not manually edit manuscript_stats.json because project-specific deny rules and non-editing permissions prevent alterations to pipeline artifacts. This preserves data integrity by ensuring numbers originate only from stored pipeline outputs.

Does this manuscript validation approach work with Jupyter notebooks?▼

Yes, this manuscript validation approach works with Jupyter notebooks. It enforces that quantitative claims in notebook prose originate from pipeline-generated data via code chunks or inline expressions, preventing hand-written literals.

Related Skills

Explore More Education & Research Skills→
Felpix-StudiosFelpix-Studios
8

write-paper

Draft academic manuscript sections from analysis outputs and project specs.

Community
Advanced
drpedapatidrpedapati
88

experiment-provenance

Record experiment provenance and reproducible run metadata for research workflows.

Community
Intermediate
drkamaruldrkamarul

quarto-skill

Create and edit Quarto documents with Markdown, R, and Python code chunks.

Community
Advanced
hyperbolic-chyperbolic-c
5

paper-writer

Generate IMRAD manuscript sections with inline citations from content points and references.

Community
Intermediate