Academic Research Skills

Academic Research Skills is a suite of Claude Code skills for academic research and publication, maintained by Cheng-I Wu. It covers four areas: deep research, academic paper writing, academic paper review, and an academic-pipeline orchestrator.

The suite uses staged, human-in-the-loop workflows. Research modes support literature reviews, systematic reviews, fact-checking, paper comparison, and Socratic guidance; writing modes produce and revise manuscripts, convert citation formats, generate LaTeX and optional DOCX/PDF outputs, and check citations; review modes use multi-perspective peer review, revision tracking, and optional reviewer calibration. The pipeline orchestrator connects these activities through ten stages, user-confirmation checkpoints, Material Passport handoffs, claim and citation verification, integrity gates, and final process summaries. Optional citation auditing retrieves cited sources against locator anchors and evaluates whether claims are supported. ARS checks reported manuscripts, citations, methodology, experiment-to-claim alignment, and package conformance, but does not establish that experiments were actually performed, raw data are authentic, or results reproduce.

It is distributed as a Claude Code plugin for the CLI, VS Code, and JetBrains, with additional project, global, Claude Science, and community-maintained Pi installation paths documented in the repository. The core skills are prompt-driven; some optional guards, verification, caching, and revision features use Python, and Pandoc and tectonic are optional for DOCX and PDF output. The repository is licensed CC BY-NC 4.0.