Skip to main content
skill CX Codex

nature-writing · galaxy-dawn — Claude Code skill: what it does, install

The nature-writing skill drafts and restructures Nature-style research writing from claims, results, figures, notes, or Chinese drafts. Use it for a section, outline, or full manuscript argument.

MIT 306 installs ★ 6,082 updated 2026-10-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Galaxy-Dawn/claude-scholar --skill nature-writing -a claude-code
Open on GitHub

What nature-writing does

nature-writing helps build or rebuild a manuscript title, abstract, introduction, results narrative, discussion, conclusion, or full paper argument. It first identifies the central claim, supporting evidence, and claim boundary, then assigns each paragraph a job and keeps statements close to the data that supports them.

Its workflow covers section planning, paragraph-flow checks, and alignment between claims and evidence. Inputs can include notes, measurements, figures, comparisons, or Chinese drafts. The skill does not fill gaps with invented results, methods, references, or limitations. When core claim, evidence, or boundary is missing, it uses a placeholder or asks for the missing material.

The package also points to files under references/ for abstracts, introductions, methods, experiments, conclusions, related work, paragraph flow, Chinese-author workflows, and manuscript review. Those files shape the writing process when they are available in the installed skill environment.

What it helps with

  • turn research notes and results into a paper outline
  • rebuild an introduction around an unresolved gap
  • draft an abstract from claims and supporting evidence
  • map Results claims to figures and comparisons
  • audit a manuscript for unsupported conclusions

Example prompts for the agent

  • Rewrite this introduction around the supplied claims, results, and figures while keeping each claim within its evidence.
  • Draft a Nature-style abstract from this manuscript and mark places where the evidence is insufficient.
  • Check the flow of the Results section and propose paragraph roles without adding new findings.

How to install nature-writing

1Skills CLI (Vercel)

npx skills add Galaxy-Dawn/claude-scholar --skill nature-writing -a claude-code

2Manually: put the files in place

~/.claude/skills/nature-writing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nature-writing/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nature-writing

How do I install nature-writing in Claude Code?

Run npx skills add Galaxy-Dawn/claude-scholar --skill nature-writing -a claude-code, then check ~/.claude/skills/nature-writing/SKILL.md.

What does nature-writing do?

It drafts or restructures scientific manuscript sections, from titles and abstracts to Results, Discussion, and Conclusions. The workflow ties claims to supplied evidence and limits unsupported conclusions.

What does nature-writing need to work?

You can provide claims, results, figures, notes, or a Chinese draft. The workflow needs a core claim, evidence, and boundary; a missing item becomes a placeholder or a clarification request.

Source text

SKILL.md · MIT
---
name: nature-writing
description: Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, results narrative, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose.
version: 0.2.0
author: Community contribution based on curated Nature/Nature Communications writing patterns and open research-writing notes
---

# Nature-Style Scientific Writing

Use this skill when the user needs help creating or rebuilding manuscript prose,
not merely polishing existing sentences.

## Core stance

- Author evidence comes first. Do not invent results, mechanisms, references,
  methods, novelty, sample sizes, statistics or limitations.
- Write the argument before writing the sentences.
- Make the paper easy to judge: relevance, novelty, trust, reuse and meaning.
- Use ambitious but bounded claims.
- If essential evidence is missing, write a placeholder or ask for the missing
  input instead of filling the gap.

## Mined writing memory

Before drafting or restructuring academic prose, check the active installed
`skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md`
under the current client's skill home. Read only entries relevant to this paper's
section, article type, and venue. Use mined patterns for structure and wording
ideas, while grounding every claim in the author's evidence and the target
journal's requirements. Do not copy source phrasing. If the memory is absent or
has no relevant entries, continue with this skill's references.

## When to open extra files

| File | Open when |
|---|---|
| [references/article-architecture.md](references/article-architecture.md) | You need section-level structure, argument order, or published-article writing patterns |
| [references/abstract.md](references/abstract.md) | Drafting or revising an abstract, especially challenge-contribution and challenge-insight-contribution forms |
| [references/introduction.md](references/introduction.md) | Drafting or revising an Introduction, task framing, technical challenge, contribution framing, or teaser/pipeline logic |
| [references/related-work.md](references/related-work.md) | Rebuilding Related Work as topic synthesis instead of a paper-by-paper list |
| [references/method.md](references/method.md) | Writing Method sections, pipeline modules, module motivation, technical advantages, or implementation details |
| [references/experiments.md](references/experiments.md) | Planning or writing Experiments/Results around baselines, ablations, metrics, tables, figures, and claim support |
| [references/conclusion.md](references/conclusion.md) | Writing a bounded conclusion with contribution, evidence, impact, limitation, and future direction |
| [references/paragraph-flow.md](references/paragraph-flow.md) | User asks whether a paragraph flows, makes sense, or is clear; use reverse outlining and paragraph-message checks |
| [references/paper-review.md](references/paper-review.md) | Final manuscript self-review, rejection-risk audit, claim-evidence alignment, or reviewer-facing critique |
| [references/chinese-author-workflow.md](references/chinese-author-workflow.md) | The user's notes are Chinese, mixed Chinese-English, or organized as lab notes rather than manuscript prose |
| [references/examples/index.md](references/examples/index.md) | You need concrete abstract, introduction, or method examples after choosing the relevant guide |

## Intake

Before drafting, identify:

- manuscript section: title, abstract, introduction, results, discussion,
  conclusion, significance paragraph or full outline
- paper type: mechanism, method, resource, device, model, clinical, materials,
  computational or interdisciplinary
- core claim: what the paper actually demonstrates
- evidence: figures, measurements, comparisons, datasets, statistics or examples
- boundary: where the claim stops
- target journal or word limit, if provided

If any of `core claim`, `evidence` or `boundary` is absent, expose the gap before
drafting. You may still produce a scaffold with explicit placeholders.

## Writing workflow

1. Build a one-sentence argument: `In [system/problem], we show [advance] using
   [approach], supported by [evidence], with [boundary].`
2. Choose the section architecture from `references/article-architecture.md`.
3. Map each paragraph to one job: context, gap, approach, result, comparison,
   mechanism, implication or limitation.
4. Draft from evidence outward. Keep claims near the data that support them.
5. Calibrate verbs: `show`, `demonstrate`, `suggest`, `indicate`, `enable`,
   `may`, `could`.
6. Remove unsupported novelty and universal claims.
7. Run a paragraph-flow check: one paragraph, one message, with a clear first
   sentence and explicit sentence-to-sentence relation.
8. Return prose plus concise notes on assumptions and missing inputs.

## Section defaults

### Abstract

Default Nature pattern:

`context/problem -> gap -> approach -> key result -> implication -> boundary`

For technical AI, ML, CV or method-heavy manuscripts, open
`references/abstract.md` and choose one of:

- `challenge -> contribution`
- `challenge -> insight -> contribution`
- `multiple contributions`

Keep it compact. Include quantitative or comparative detail when the user
provided it. End with what the work enables, not generic importance.

### Introduction

Use:

`field scale -> bottleneck -> prior attempts -> unresolved gap -> present study`

For method-heavy papers, open `references/introduction.md` and reason backward
from the technical challenge and contribution before drafting forward.

Do not summarize all results. The final paragraph should state what this paper
does and how it addresses the gap.

### Results narrative

Use an evidence ladder:

`system/workflow -> validation -> main result -> baseline comparison ->
mechanism/diagnostic analysis -> application or generalization`

Each subsection should have a claim-first opening and then data support.

For ML/conference-style experiment sections, open `references/experiments.md`
and make sure each major claim is backed by comparison, ablation, or stress-test
evidence.

### Related Work

Use:

`topic scope -> representative methods -> limitation tied to this paper ->
distinction`

Group prior work by technical topic and mechanism, not by publication year.

### Discussion

Use:

`central advance -> evidence meaning -> relation to prior work -> constraints ->
future use`

This is where interpretation and limitations belong. Do not repeat the Results
section figure by figure.

### Conclusion

Use:

`contribution -> decisive evidence -> implication -> boundary`

No new data. No unsupported promises.

### Title

Prefer concrete titles that combine:

`system/object + action/capability + application or consequence`

Avoid slogan titles, grant-style aims and overbroad field claims.

## Output format

Default output:

1. `Draft:` with the requested prose.
2. `Section outline:` with `3-7` compact bullets when the task involves a full section.
3. `Assumptions or missing inputs:` with only material issues.
4. `Claim-evidence map:` for major claims, using `Claim: ... | Evidence: ... | Status: supported/needs evidence`.
5. `Why this structure:` with `2-4` short bullets.

For Chinese author notes, provide polished English first, then brief Chinese
notes explaining major structural choices.

© Community contribution based on curated Nature/Nature Communications writing patterns and open research-writing notes · MIT · Galaxy-Dawn/claude-scholar

Similar skills

All skills for Science and research →

nature-writing by other authors comes first.

nature-writing Yuan1z0825 nature-writing — a skill that drafts and restructures scientific manuscript sections and first-submission materials from evidence you supply. CX Codex +1 17,500installs scientific-writing K-Dense-AI The scientific-writing skill drafts and audits scientific manuscripts and reports while tying claims to verified evidence. Use it for sections, references, declarations, and submission checks. CX Codex +1 2,700installs ccf-paper-reviewer mikubaka88 The ccf-paper-reviewer skill for Claude Code reviews scientific manuscripts, helping assess claims, evidence, and writing quality before submission. CX Codex +1 2,300installs nature-story franklee16 nature-story — a skill that transforms raw research ideas into rigorous scientific narratives with competing hypotheses, literature benchmarks, and figure-driven paper plans. CX Codex +1 ★ 240repo stars nature-reviewer Yuan1z0825 The nature-reviewer skill runs a Nature-style referee assessment of a scientific manuscript: three independent reviewer reports plus a post-review synthesis. Useful before you submit. CX Codex +1 15,400installs nature-statistics Yuan1z0825 nature-statistics is a Claude Code skill that audits statistical reporting in manuscripts and helps revise it. It responds to requests about methods, results, figure legends, and reviewer comments. CX Codex +1 13,400installs scientific-manuscript-review lyndonkl scientific-manuscript-review — a skill that walks a scientific manuscript through eight review passes: structure, sections, claim clarity, language and journal formatting. CX Codex +1 484installs

From the same set31

The whole set →
agent-identifier The agent-identifier skill helps create and configure Claude Code agents, from frontmatter to system prompts. Use it for autonomous multi-step work. CX Codex +1 352installs nature-polishing nature-polishing is a Claude Code skill that adapts academic manuscripts to Nature publishing standards. It restructures draft sections, abstracts, and section arguments. CX Codex +1 337installs obsidian-project-kb-core The obsidian-project-kb-core skill manages a project-scoped Obsidian research vault: it builds the structure, routes notes, and keeps indexes, the registry, and checks up to date. CX Codex +1 332installs obsidian-source-ingestion obsidian-source-ingestion turns outside material into source notes inside a project-scoped Obsidian vault: papers, web pages, data, interviews. Useful when sources need a shelf, not a summary. CX Codex +1 329installs obsidian-kb-artifacts obsidian-kb-artifacts — a skill for Obsidian formatting and derived artifacts: wikilinks, registry tables, canvas files, Bases, and link repair. Works in Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. CX Codex +1 328installs expression-skill The expression-skill skill shapes concise, decision-ready answers with evidence, risks, and next steps. Use it for reports, plans, research notes, and writing feedback. CX Codex +1 284installs nature-response nature-response is a Claude Code skill that drafts and audits point-by-point replies during Nature-family manuscript revisions. CX Codex +1 276installs nature-data nature-data is a skill that builds and audits Nature-style Data Availability statements, repository plans, dataset citations, and FAIR metadata checklists. CX Codex +1 272installs

Project sponsors

Companies that keep this analytics open