Someone just turned Claude Code into a full academic publishing house.
It's called Academic Research Skills.
Research team, paper writer, peer reviewers, and an editor all running as AI agents on your machine.
The pipeline goes: Research → Write → Integrity Check → 5-person Review → Revise → Re-Review → Final Check → Publish-ready PDF.
Here's what's inside:
→ 13-agent deep research team with Socratic guidance and PRISMA systematic reviews
→ 12-agent paper writer that outputs LaTeX in APA 7, IEEE, or Chicago
→ Multi-perspective peer review: Editor-in-Chief 3 reviewers a Devil's Advocate that attacks your core thesis
→ A 10-stage orchestrator with mandatory integrity checkpoints you cannot skip
Here's the wildest part:
The integrity agent verifies 100% of references, data, and claims before review. In the showcase run, it caught 15 fabricated references and 3 statistical errors before a human ever saw the draft.
Every review is scored on a 0-100 rubric. Above 80 gets accepted. Below 50 gets rejected. Just like a real journal.
Free on GitHub. CC-BY-NC 4.0 License.