#416 · Primary category: Education & Research

spark-to-paper-skills

One sentence in, one draft paper out: spark-to-paper-skills automatically reviews papers, plans and runs experiments, and writes a research draft—typically using about $10 in API costs per paper.

Project last updated:08/22/26

GitHub Stars

837

Forks

16

Contributors

4

License

MIT

Why we included this project

Researchers and grad students who want to move from a rough idea to a finished paper without doing every step by hand will get real use out of this. It is a set of 13 composable Claude Code skills plus one orchestrator that takes a one-line proposal and carries it through literature review, experiment planning and execution, drafting, figure generation, and LaTeX compilation into a PDF, typically for around $10 in API costs per paper. The machine-checked integrity is what stands out: deterministic gates verify citation records, trace numbers back to the source data, and audit the vector figures, so the result is something you can trust and edit rather than just plausible prose. Everything runs inside Claude Code as a plugin, so there is no separate server or app to set up, and it is template-agnostic, meaning you can add a new venue style without touching code. For a solo researcher or a small team that wants an automated research assistant instead of a heavyweight standalone agent, the skill-based design stays lightweight and easy to adapt.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category