#74 · Primary category: Writing & Content

PaperOrchestra

agentic-ai ai-research anthropic antigravity arxiv automated-paper-writing claude-code claude-skills coding-agents cursor latex literature-review llm-agents multi-agent paper-orchestra paperorchestra research-paper semantic-scholar skill-pack

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

Project last updated:08/09/26

GitHub Stars

648

Forks

91

Contributors

3

License

MIT

Why we included this project

Turning scattered notes, experiment logs, and literature into a submission-ready LaTeX manuscript is a slog, and this skill pack automates a good chunk of it. It packages the five-agent pipeline from Google's PaperOrchestra paper as instruction documents and deterministic helper scripts that any coding agent (Claude Code, Cursor, Cline, Aider, and others) can run. There are no API keys and no embedded LLM calls; the host agent does all the reasoning, web search, and LaTeX compilation with its own tools, which keeps setup simple and avoids locking you into one vendor. The skills cover outlining, plotting, literature review, section writing, and content refinement, with JSON schemas, rubrics, and halt rules to keep the output on track. If you already drive a coding agent regularly, this is a practical way to scaffold a full paper draft rather than a standalone application.

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