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.
When to open extra files
| File |
Open when |
| references/article-architecture.md |
You need section-level structure, argument order, or published-article writing patterns |
| references/abstract.md |
Drafting or revising an abstract, especially challenge-contribution and challenge-insight-contribution forms |
| references/introduction.md |
Drafting or revising an Introduction, task framing, technical challenge, contribution framing, or teaser/pipeline logic |
| references/related-work.md |
Rebuilding Related Work as topic synthesis instead of a paper-by-paper list |
| references/method.md |
Writing Method sections, pipeline modules, module motivation, technical advantages, or implementation details |
| references/experiments.md |
Planning or writing Experiments/Results around baselines, ablations, metrics, tables, figures, and claim support |
| references/conclusion.md |
Writing a bounded conclusion with contribution, evidence, impact, limitation, and future direction |
| 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 |
Final manuscript self-review, rejection-risk audit, claim-evidence alignment, or reviewer-facing critique |
| 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 |
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
- Build a one-sentence argument:
In [system/problem], we show [advance] using [approach], supported by [evidence], with [boundary].
- Choose the section architecture from
references/article-architecture.md.
- Map each paragraph to one job: context, gap, approach, result, comparison,
mechanism, implication or limitation.
- Draft from evidence outward. Keep claims near the data that support them.
- Calibrate verbs:
show, demonstrate, suggest, indicate, enable,
may, could.
- Remove unsupported novelty and universal claims.
- Run a paragraph-flow check: one paragraph, one message, with a clear first
sentence and explicit sentence-to-sentence relation.
- 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:
Draft: with the requested prose.
Section outline: with 3-7 compact bullets when the task involves a full section.
Assumptions or missing inputs: with only material issues.
Claim-evidence map: for major claims, using Claim: ... | Evidence: ... | Status: supported/needs evidence.
Why this structure: with 2-4 short bullets.
For Chinese author notes, provide polished English first, then brief Chinese
notes explaining major structural choices.
1---
2name: nature-writing
3description: 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.
4version: 0.2.0
5author: Community contribution based on curated Nature/Nature Communications writing patterns and open research-writing notes
6metadata:
7 source: https://skillmd.com/skills/galaxy-dawn/nature-writing
8---
9
10# Nature-Style Scientific Writing
11
12Use this skill when the user needs help creating or rebuilding manuscript prose,
13not merely polishing existing sentences.
14
15## Core stance
16
17- Author evidence comes first. Do not invent results, mechanisms, references,
18 methods, novelty, sample sizes, statistics or limitations.
19- Write the argument before writing the sentences.
20- Make the paper easy to judge: relevance, novelty, trust, reuse and meaning.
21- Use ambitious but bounded claims.
22- If essential evidence is missing, write a placeholder or ask for the missing
23 input instead of filling the gap.
24
25## When to open extra files
26
27| File | Open when |
28|---|---|
29| [references/article-architecture.md](references/article-architecture.md) | You need section-level structure, argument order, or published-article writing patterns |
30| [references/abstract.md](references/abstract.md) | Drafting or revising an abstract, especially challenge-contribution and challenge-insight-contribution forms |
31| [references/introduction.md](references/introduction.md) | Drafting or revising an Introduction, task framing, technical challenge, contribution framing, or teaser/pipeline logic |
32| [references/related-work.md](references/related-work.md) | Rebuilding Related Work as topic synthesis instead of a paper-by-paper list |
33| [references/method.md](references/method.md) | Writing Method sections, pipeline modules, module motivation, technical advantages, or implementation details |
34| [references/experiments.md](references/experiments.md) | Planning or writing Experiments/Results around baselines, ablations, metrics, tables, figures, and claim support |
35| [references/conclusion.md](references/conclusion.md) | Writing a bounded conclusion with contribution, evidence, impact, limitation, and future direction |
36| [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 |
37| [references/paper-review.md](references/paper-review.md) | Final manuscript self-review, rejection-risk audit, claim-evidence alignment, or reviewer-facing critique |
38| [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 |
39| [references/examples/index.md](references/examples/index.md) | You need concrete abstract, introduction, or method examples after choosing the relevant guide |
40
41## Intake
42
43Before drafting, identify:
44
45- manuscript section: title, abstract, introduction, results, discussion,
46 conclusion, significance paragraph or full outline
47- paper type: mechanism, method, resource, device, model, clinical, materials,
48 computational or interdisciplinary
49- core claim: what the paper actually demonstrates
50- evidence: figures, measurements, comparisons, datasets, statistics or examples
51- boundary: where the claim stops
52- target journal or word limit, if provided
53
54If any of `core claim`, `evidence` or `boundary` is absent, expose the gap before
55drafting. You may still produce a scaffold with explicit placeholders.
56
57## Writing workflow
58
591. Build a one-sentence argument: `In [system/problem], we show [advance] using
60 [approach], supported by [evidence], with [boundary].`
612. Choose the section architecture from `references/article-architecture.md`.
623. Map each paragraph to one job: context, gap, approach, result, comparison,
63 mechanism, implication or limitation.
644. Draft from evidence outward. Keep claims near the data that support them.
655. Calibrate verbs: `show`, `demonstrate`, `suggest`, `indicate`, `enable`,
66 `may`, `could`.
676. Remove unsupported novelty and universal claims.
687. Run a paragraph-flow check: one paragraph, one message, with a clear first
69 sentence and explicit sentence-to-sentence relation.
708. Return prose plus concise notes on assumptions and missing inputs.
71
72## Section defaults
73
74### Abstract
75
76Default Nature pattern:
77
78`context/problem -> gap -> approach -> key result -> implication -> boundary`
79
80For technical AI, ML, CV or method-heavy manuscripts, open
81`references/abstract.md` and choose one of:
82
83- `challenge -> contribution`
84- `challenge -> insight -> contribution`
85- `multiple contributions`
86
87Keep it compact. Include quantitative or comparative detail when the user
88provided it. End with what the work enables, not generic importance.
89
90### Introduction
91
92Use:
93
94`field scale -> bottleneck -> prior attempts -> unresolved gap -> present study`
95
96For method-heavy papers, open `references/introduction.md` and reason backward
97from the technical challenge and contribution before drafting forward.
98
99Do not summarize all results. The final paragraph should state what this paper
100does and how it addresses the gap.
101
102### Results narrative
103
104Use an evidence ladder:
105
106`system/workflow -> validation -> main result -> baseline comparison ->
107mechanism/diagnostic analysis -> application or generalization`
108
109Each subsection should have a claim-first opening and then data support.
110
111For ML/conference-style experiment sections, open `references/experiments.md`
112and make sure each major claim is backed by comparison, ablation, or stress-test
113evidence.
114
115### Related Work
116
117Use:
118
119`topic scope -> representative methods -> limitation tied to this paper ->
120distinction`
121
122Group prior work by technical topic and mechanism, not by publication year.
123
124### Discussion
125
126Use:
127
128`central advance -> evidence meaning -> relation to prior work -> constraints ->
129future use`
130
131This is where interpretation and limitations belong. Do not repeat the Results
132section figure by figure.
133
134### Conclusion
135
136Use:
137
138`contribution -> decisive evidence -> implication -> boundary`
139
140No new data. No unsupported promises.
141
142### Title
143
144Prefer concrete titles that combine:
145
146`system/object + action/capability + application or consequence`
147
148Avoid slogan titles, grant-style aims and overbroad field claims.
149
150## Output format
151
152Default output:
153
1541. `Draft:` with the requested prose.
1552. `Section outline:` with `3-7` compact bullets when the task involves a full section.
1563. `Assumptions or missing inputs:` with only material issues.
1574. `Claim-evidence map:` for major claims, using `Claim: ... | Evidence: ... | Status: supported/needs evidence`.
1585. `Why this structure:` with `2-4` short bullets.
159
160For Chinese author notes, provide polished English first, then brief Chinese
161notes explaining major structural choices.