Boom5426/Nature-Paper-Skills

An AI-powered Scientific Writing Workflow: Agent skills for drafting, revising, auditing, and resubmitting Nature-style journal manuscripts.

What it solves

It streamlines the process of writing and revising high-impact scientific manuscripts, specifically for Nature-series journals in life sciences, computational biology, and methods. It prevents common writing pitfalls such as making claims unsupported by evidence, using "AI-sounding" prose, or failing to align figure panels with the Results section.

How it works

The project provides a set of 27 specialized "skills" (instructions and helper scripts) that can be installed into AI agents like Codex and Claude Code. These skills guide the agent through a structured workflow:

  1. Framing: Defining the research question and target venue.
  2. Argument Building: Establishing a claim-evidence chain before focusing on style.
  3. Figure Alignment: Ensuring figures and legends directly support the Results.
  4. Prose Revision: Refining logic and style while preserving measured values and uncertainty.
  5. Submission & Rebuttal: Conducting pre-flight audits and drafting responses to reviewers.

Who it’s for

Researchers and scientists in the life sciences and computational biology fields who are preparing manuscripts for submission to high-tier journals.

Highlights

  • Evidence-Bound Editing: Ensures that edits do not alter measured values, confidence intervals, or negative results.
  • Agent-Integrated: Designed specifically for installation into AI coding/agent environments (Codex, Claude Code).
  • Task-Specific Profiles: Offers different installation stacks (e.g., Writing & Review, Full Research Workflow) based on user needs.
  • Anti-Defensive Writing: Includes tools to remove overly cautious or "audit" language to create direct scientific prose.
  • Reviewer Response System: Connects reviewer comments to specific evidence and manuscript changes.

Related

  • Project
    Yuan1z0825/nature-skills

    A library of 22 packaged AI-agent workflows ("skills") for academic research — paper reading, Nature-style writing, figure generation, reviewer responses, literature search, and patent drafting — installable into Claude Code, Codex, Chatbox, and other agents.

  • Project
    jamditis/claude-skills-journalism

    A library of Claude Code (and limited Codex) plugins/skills that give AI agents journalism‑specific capabilities—AP‑style enforcement, fact‑checking, FOIA templates, PDF design, video analysis, research tools, etc.—installable via Claude’s marketplace or by copying `SKILL.md` folders.

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.

  • Project
    LeonChaoX/qinyan-academic-skills

    A library of 187 installable AI agent skills for academic research, featuring a specialized suite for Nature-style scientific writing and manuscript preparation.

  • Project
    luwill/research-skills

    A set of five Claude Code plug‑ins that automate academic research tasks—exhaustive literature search, citation‑integrity‑driven review writing, proposal drafting, and two kinds of slide‑deck generation (stylised images vs. fully editable, vector‑based decks). All tools enforce strict citation checks and are installable as simple skill folders.