
Nature Polishing
Polish manuscript sections, abstracts, or Chinese drafts into Nature-leaning academic English without inventing data or rewriting core scientific claims.
Overview
Nature Polishing is an agent skill for the Build phase that polishes and restructures academic prose into Nature-leaning English using strategy notes and Phrasebank patterns.
Install
npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-polishingWhat is this skill?
- Dual layer: main strategy (architecture, section logic, evidence thresholds) plus Academic Phrasebank wording support
- Covers abstract, introduction, results, discussion, conclusion, title, and methods polishing
- Explicit ethics: no invented data, references, mechanisms, or novelty; no AI-drafted core argument from scratch
- Reader workflow: relevance, novelty, trust, reuse, meaning—in that empathetic order
- Version 5.0.2 rebuilt from course notes (Chapter1-Week1-7) and Nature/Nature Communications patterns
- Skill version 5.0.2
- Two-level model: main strategy plus reference support (Academic Phrasebank)
- Course-note source span Chapter1-Week1-7
Adoption & trust: 2.3k installs on skills.sh; 17.8k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your draft sounds non-native or structurally weak for a top journal, but you cannot risk invented references, fake novelty, or an AI rewrite of your core science.
Who is it for?
Authors with an existing draft (including Chinese source text) who want publication-quality English polish and section logic for Nature-tier venues.
Skip if: Marketing landing copy, casual blog posts, or empty-slate paper generation where the agent would invent the scientific story.
When should I use this skill?
User asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English.
What do I get? / Deliverables
You get section-aware polished English aligned to Nature-style reader flow and phrase moves, with scientific claims left to your verified evidence.
- Polished section-level English
- Restructured argument flow per Nature-leaning strategy
- Phrase-level revisions without fabricated evidence
Recommended Skills
Journey fit
Publication-quality prose is produced while you are drafting and revising research documents—a docs/build writing task rather than distribution or analytics. The skill targets section-level architecture, phrasebank moves, and ethics for manuscripts—not landing pages, SEO, or app store copy.
How it compares
Discipline-specific academic polishing workflow—not generic “make this sound professional” or SEO content rewriting.
Common Questions / FAQ
Who is nature-polishing for?
Grad students, indie researchers, and lab-adjacent builders polishing manuscripts, abstracts, or translated Chinese drafts for English-language journals.
When should I use nature-polishing?
During Build docs whenever you ask to polish a paragraph, abstract, introduction, results, discussion, conclusion, title, methods, or a Chinese academic draft for publication-quality English.
Is nature-polishing safe to install?
Review the Security Audits panel on this Prism page and the skill’s ethics rules; you remain responsible for factual accuracy and references.
SKILL.md
READMESKILL.md - Nature Polishing
# Nature-Style Academic Polishing Use this skill to improve scientific writing at two levels: - `main strategy`: paper architecture, published-article patterns, section logic, reader workflow, evidence thresholds, and ethics - `reference support`: reusable phrase families, move patterns, transitions, and style checks The main strategy should come from the course notes in `Chapter1-Week1-7` and the curated article-pattern reference. The wording layer should come from `Academic Phrasebank`. ## Default stance - Language serves argument. Do not polish sentences while leaving the reasoning broken. - Write with empathy for the reader: relevance first, then novelty, then trust, then reuse, then meaning. - There should be no mystery for the writer, but there may be one for the reader. - Do not invent data, references, mechanisms, or novelty claims. - Do not let AI draft the paper's core scientific argument from scratch. - If the draft is Chinese or structurally rough, reconstruct the logic first and the prose second. - Avoid em dashes in polished output by default. Prefer commas, parentheses, or full stops. Use colons sparingly unless the user explicitly asks to preserve dash-based punctuation or wants a colon-led style. ## When to open extra files These files are reference support. Use them after the section's rhetorical job is clear. | File | Open when | |---|---| | [references/published-article-patterns.md](references/published-article-patterns.md) | You need Nature/Nature Communications article-level writing patterns for abstracts, introductions, Results, Discussion, conclusions, or titles | | [references/writing-strategy.md](references/writing-strategy.md) | You need paragraph- or section-level argument repair before sentence polishing | | [references/section-moves.md](references/section-moves.md) | You need section-specific move orders or phrase patterns derived from Academic Phrasebank | | [references/phrasebank-playbook.md](references/phrasebank-playbook.md) | You need hedging, transition, evidence, limitation, or future-work phrase families | | [references/style-guardrails.md](references/style-guardrails.md) | You need academic-style checks, paragraph/sentence checks, article use, register, or mechanics | ## Core architecture ### 1. Identify the paper type first Before editing, determine what kind of paper or section this is. - `Research paper`: the reader asks why the phenomenon matters, what was done, what was found, and what it means. - `Methods paper`: the reader asks whether the method works, whether it is reproducible, and whether it is better under a fair comparison. - `Hypothesis-based work`: the argument tries to establish or rule out a causal explanation. - `Algorithmic or device work`: the argument proposes a procedure, tool, or system and must show that it performs reliably and advantageously. Do not use one narrative logic for all paper types. For article-level rewrites, especially abstracts, introductions, Results openings, Discussion paragraphs, conclusions, and titles, also apply the writing patterns in `references/published-article-patterns.md`. ### 2. Write for the reader, not for the draft chronology Most readers follow a stable sequence: 1. Is this relevant to me? 2. What is new here? 3. Do I trust it? 4. Can I reuse it? 5. What does it mean, and where are the boundaries? Polishing should help the paper answer these questions in this order. ### 3.