Nature PolishingSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

nature-polishing/
├── SKILL.md
├── README.md
└── references/
├── published-article-patterns.md
├── phrasebank-playbook.md
├── section-moves.md
├── style-guardrails.md
└── writing-strategy.md

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: nature-polishing
description: Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English.
version: 5.0.2
author: Yuan1z skill rebuilt from course notes plus Academic Phrasebank
---

# 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.

## Mined writing memory

For academic prose, check the active installed
`skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md`
under the current client's skill home. Use only source-attributed entries that
fit the section and venue, alongside this skill's curated references. Treat them
as optional style and structure examples. Preserve the author's claims and
evidence, follow current journal instructions, and do not copy source phrasing.
If the memory has no relevant entries, continue without it.

## 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. Use the hourglass structure

Strong papers often mirror an hourglass:

- `Introduction`: open broadly, then narrow to the specific gap, question, hypothesis, methods, and study
- `Discussion/Conclusion`: widen again, connecting the findings back to the literature and explaining how the knowledge gap was filled

If a paragraph or section violates this architecture, rebuild it before polishing wording.

### 4. Use the correct writing order

For a research article, a productive writing order is:

1. Results
2. Introduction and Conclusion
3. Title
4. Discussion
5. Materials and Methods
6. Authors
7. Abstract

For a methods paper, a productive writing order often begins with:

1. Methods
2. Results
3. Introduction
4. Conclusion
5. Discussion
6. Abstract

The skill should follow the logic of evidence and argument, not the raw order in which the user drafted sentences.

### 5. Protect the core argument

The paper's core argument includes:

- the scientific question the paper actually answers
- why that question matters
- how the work differs from existing research
- what the results imply
- how the main line of reasoning unfolds

AI may help polish, structure, or compare phrasings. AI should not invent or author the core argument. If the argument is weak or unclear, expose that weakness rather than hiding it under polished language.

### 6. Diagnose the failure mode before editing

Before rewriting, identify the main problem:

- wrong paper type logic
- mis

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.