Back to directory

Academic Research Skills for Claude Code

A suite of Claude Code skills that walk a researcher through an academic paper's full pipeline, research, writing, review and revision, with the researcher confirming and staying responsible for every stage.

Academic Research Skills for Claude Code

The pipeline pauses for the researcher's confirmation at each step rather than running end to end on its own, and a Socratic-dialogue planning command helps structure a paper before drafting begins; the README frames its stance as AI acting as a copilot handling grunt work such as reference hunting, citation formatting and consistency checks, while the researcher keeps the decisions that require judgment.

Integrity gates run a multi-mode checklist against known failure modes of autonomous research systems, citing published findings on both a fully autonomous research system and large-scale citation-hallucination rates in preprints. Recent versions add trust-chain metadata and locator anchors for each citation, plus an opt-in audit pass that fetches a cited source and checks whether it actually supports the claim made against it.

Python.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.