simulation-reproduction

Convert recovered evidence into runnable scripts, numerical outputs, and reproducible figures.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Void0312Aurora/RAAS --skill simulation-reproduction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: simulation-reproduction
Source: https://github.com/Void0312Aurora/RAAS/tree/main/skills/simulation-reproduction
Command: npx skills add https://github.com/Void0312Aurora/RAAS --skill simulation-reproduction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps researchers turn recovered evidence into runnable code, numerical outputs, and reproducible figures, enabling faithful replication of experiments.

Core Features & Use Cases

  • Convert equations, parameters, and plot semantics from evidence into executable scripts.
  • Execute within a task workspace, capturing stdout, stderr, and runtime, then persist figures, raw data, and metadata.
  • Record provenance to allow reviewers to trace outputs back to the evidence bundle across planning, implementation, and verification.

Quick Start

Provide the evidence bundle and run the reproduction workflow to produce runnable code, outputs, and figures.

Frequently Asked Questions about simulation-reproduction

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

FAQPage Schema
How do I convert equations and parameters from a paper into runnable scripts for reproducible research?

To convert evidence into runnable scripts, you provide the recovered evidence bundle to execute a reproduction workflow that generates executable code, numerical outputs, and reproducible figures. This process applies equations and parameters within a task workspace.

How does provenance recording work when reproducing scientific computation results?

Provenance recording works by tracing outputs back to the evidence bundle across planning, implementation, and verification stages. This allows reviewers to verify that numerical outputs and reproducible figures faithfully match the original scientific computation parameters.

What is the best way to generate reproducible figures from recovered scientific evidence?

The best way to generate reproducible figures is by executing deterministic scripts within an isolated task workspace. This workspace captures stdout, stderr, and runtime, then persists the resulting figures, raw data, and metadata alongside provenance records.

Can I execute numerical reproduction workflows in an isolated workspace without external dependencies?

Yes, you can execute numerical reproduction workflows within an isolated task workspace. This environment satisfies deterministic scripting and workspace isolation requirements, independently capturing stdout, stderr, and runtime while persisting outputs.

Does this reproduction workflow support tracking plot semantics and metadata across verification stages?

Yes, the reproduction workflow supports tracking plot semantics and metadata across planning, implementation, and verification stages. It records provenance to ensure reviewers can trace numerical outputs and figures back to the original evidence bundle.

What limitations exist when turning evidence into code for replicating experiments from theses or reports?

A key limitation is the requirement for deterministic scripting and a recovered evidence bundle containing sufficient equations, parameters, and plot semantics. Without complete evidence, the workspace cannot properly generate runnable scripts or persist accurate provenance.