Boom5426/Nature-Paper-Skills

Agent skills for drafting, revising, auditing, and resubmitting Nature-style journal manuscripts.

What it solves

This project provides a specialized set of agent skills designed to guide researchers through the entire lifecycle of preparing manuscripts for the Nature family of journals. It moves beyond general writing tips to enforce a "journal-first" and "claim-driven" approach, ensuring that scientific claims are strictly backed by evidence and that the manuscript structure adheres to the high standards of top-tier journals.

How it works

The repository contains a collection of self-contained skills (scripts and Markdown guides) that can be installed into AI agents like Claude Code or Codex. These skills are organized into a structured workflow:

  1. Project Initialization: Setting up the source of truth and state files.
  2. Structural Planning: Using reverse outlines to stabilize the evidence chain before polishing prose.
  3. Figure Planning: Defining the main claim for each figure before generating the actual visuals.
  4. Verification: Auditing statistical reporting, verifying citations, and checking that claims in the Abstract/Introduction do not exceed the evidence provided in the results.
  5. Submission & Rebuttal: Performing pre-submission audits and managing the response to reviewer comments.

Who it’s for

Researchers and scientists aiming to publish in Nature series journals (particularly in life sciences, computational biology, and methodology) who use AI agents to assist in drafting, revising, and auditing their manuscripts.

Highlights

  • Claim-Driven Workflow: Prioritizes evidence boundaries over stylistic polishing.
  • Integrated Figure Stack: Includes tools for figure planning and generating publication-quality plots using Python/R.
  • Rigorous Auditing: Dedicated skills for statistical reporting audits and citation verification.
  • Agent-Native Installation: One-command installation for Claude Code and Codex agents.
  • Comprehensive Lifecycle Support: Covers everything from the first draft and structural revision to submission audits and rebuttal responses.

Related

  • Project
    Yuan1z0825/nature-skills

    A library of reusable research skills for AI agents to automate high-impact academic workflows, from paper reading and Nature-style polishing to peer review simulation and patent drafting.

  • Project
    bahayonghang/academic-writing-skills

    A collection of specialized skills for Claude Code and Codex to polish, audit, and validate academic manuscripts in LaTeX and Typst.

  • Project
    jamditis/claude-skills-journalism

    A genuine open‑source repo that bundles reusable “Agent Skills” for Claude Code (and Codex) to help journalists and newsroom teams automate tasks such as fact‑checking, source verification, FOIA filing, data‑journalism, PDF design, and multi‑agent workflows. Install via Claude’s plugin commands or copy individual `SKILL.md` folders; the repo includes a catalog, docs site, and up‑to‑date skill set.

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that automate academic peer review, grant proposal evaluation, and paper-code reproducibility checks for researchers.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills and workflows for AI agents to automate tasks ranging from content creation and 3D generation to complex software engineering.