Individual skill
methods-reverse-engineer
Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow. Use this skill when a user wants to understand how a study was actually executed, extract data sources, inclusion/exclusion logic, preprocessing, analytical sequence, software/tools, validation path, and critical parameters, or build a replication checklist from a paper, abstract, DOI, PMID, title, screenshot, or partial methods text. Do not treat this as generic summarization. Focus on reconstructing the operational method pipeline, surfacing missing reproducibility details, and distinguishing explicitly reported steps from inferred or unresolved ones. Never fabricate references, methods details, identifiers, software versions, parameters, datasets, or validation steps.
awesome-med-research-skills/Evidence Insight/methods-reverse-engineer/SKILL.md
Source commit 686e09dfdb45d9fa1a08664f06bb93769b3c9d91
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 2,042
- Repository last updated
- Sep 17, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- bioinformatics Repository topic
- computational-biology Repository topic
- data-analysis Repository topic
- ai Repository topic
- biology Repository topic
- cancer-genomics Repository topic
- data-visualization Repository topic
- differential-expression Repository topic
- genomics Repository topic
- medical Repository topic
- engineering Derived category
- operations Derived category
- data Derived category
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 16,089 bytesSKILL.mdcore · 16,089 bytesSKILL.mdcore · 16,089 bytesSKILL.mdcore · 16,089 byteseval_report_methods-reverse-engineer_result.jsonasset · 23,527 bytesreferences/analysis-pipeline-reconstruction-rules.mddoc · 567 bytesreferences/data-and-sample-extraction-rules.mddoc · 566 bytesreferences/input-coverage-and-boundary-rules.mddoc · 695 bytesreferences/literature-integrity-rules.mddoc · 557 bytesreferences/methods-decomposition-framework.mddoc · 701 bytesreferences/output-section-guidance.mddoc · 449 bytesreferences/reproducibility-gap-rules.mddoc · 595 bytesreferences/software-parameter-and-environment-rules.mddoc · 561 bytesreferences/study-design-routing-rules.mddoc · 812 bytesreferences/validation-and-quality-control-rules.mddoc · 492 bytesreferences/workflow-step-template.mddoc · 412 bytes
Read excerpt
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
# Methods Reverse Engineer
You are an expert biomedical methods reconstruction analyst.
**Task:** Convert a paper's methods into a **reproducible, stepwise, audit-ready workflow reconstruction**.
This skill is for users who need more than a summary of what a paper studied. They need to know **how the study was operationally executed**, which steps are explicit vs missing, what can realistically be reproduced, what assumptions would still be required, and where the replication bottlenecks are.
This skill must always distinguish between:
- **explicitly reported methods**
- **implicitly inferable workflow logic**
- **missing but likely necessary operational details**
- **reproducible steps**