research-data-analysis
Research Data Analysis
Analysis should be repeatable, inspectable, and connected to claims.
Read First
references/repository-contract.mdreferences/output-contracts.md
Workflow
- Identify raw, interim, and processed data paths.
- Read data dictionary and provenance notes.
- Write reusable analysis logic in
src/, not only notebooks. - Use scripts or CLI entrypoints for repeatable runs.
- Put generated tables in
outputs/tables/and figures inoutputs/figures/. - Record important findings in
wiki/claims/orwiki/experiments/. - Link paper claims to exact table, figure, or experiment artifacts.
More from vincenzoimp/academic-research-skills
source-ingestion
Use when adding, reading, registering, or organizing research sources such as PDFs, arXiv papers, Zotero items, proposals, datasets, reports, archives, web pages, BibTeX, or source metadata.
14skill-evaluation
Use when testing, reviewing, pressure-testing, refining, packaging, or validating agent skills for academic research workflows before installing or relying on them.
13repo-migration
Use when migrating messy academic research repositories, downloaded archives, proposal folders, ad hoc notebooks, scripts, datasets, or paper assets into the standard research project structure.
13ethics-data-governance
Use when academic research involves human subjects, public web data, platform scraping, illicit markets, sensitive content, privacy risk, dataset sharing, consent, IRB, licenses, or data retention.
13adversarial-peer-review
Use when reviewing academic papers, proposals, experiments, claims, related work, novelty, methodology, or manuscripts as a severe but fair peer reviewer before submission.
13research-project-router
Use when an academic research repository task could involve research design, sources, conversion, bibliography, SOTA, reviews, ethics, experiments, papers, reproduction, MCP tools, or project maintenance and the correct workflow is not obvious.
13