Skip to content

Yuan1z0825/nature-skills / skills/nature-writing

nature-writing

Verified

Draft or restructure scientific manuscript arguments, sections, and initial-submission materials from author-provided evidence. Use for 论文写作、章节起草、论证重构、正文压缩、首次投稿材料. Use nature-polishing for language-only edits to existing prose and nature-response for post-decision correspondence.

FileKindSize
README.mdmarkdown4.3 KB
README_EN.mdmarkdown4.9 KB
SKILL.mdskill md8.1 KB
agents/openai.yamlconfig253 B
manifest.yamlconfig8.5 KB
references/abstract.mdmarkdown4.0 KB
references/article-architecture.mdmarkdown3.4 KB
references/chinese-author-workflow.mdmarkdown1.8 KB
references/conclusion.mdmarkdown1.2 KB
references/examples/abstract-examples.mdmarkdown875 B
references/examples/abstract/template-a.mdmarkdown950 B
references/examples/abstract/template-b.mdmarkdown3.2 KB
references/examples/abstract/template-c.mdmarkdown1.7 KB
references/examples/index.mdmarkdown2.3 KB
references/examples/introduction-examples.mdmarkdown1.5 KB
references/examples/introduction/novel-task-challenge-decomposition.mdmarkdown1.5 KB
references/examples/introduction/pipeline-not-recommended-abstract-only.mdmarkdown2.9 KB
references/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.mdmarkdown2.0 KB
references/examples/introduction/pipeline-version-2-two-contributions.mdmarkdown2.0 KB
references/examples/introduction/pipeline-version-3-new-module-on-existing-pipeline.mdmarkdown1.5 KB
references/examples/introduction/pipeline-version-4-observation-driven.mdmarkdown1.4 KB
references/examples/introduction/technical-challenge-version-1-existing-task.mdmarkdown2.6 KB
references/examples/introduction/technical-challenge-version-2-existing-task-insight-backed-by-traditional.mdmarkdown3.8 KB
references/examples/introduction/technical-challenge-version-3-novel-task.mdmarkdown1.6 KB
references/examples/introduction/version-1-task-then-application.mdmarkdown727 B
references/examples/introduction/version-2-application-first.mdmarkdown405 B
references/examples/introduction/version-3-general-to-specific-setting.mdmarkdown847 B
references/examples/introduction/version-4-open-with-challenge.mdmarkdown1.7 KB
references/examples/method-examples.mdmarkdown1.0 KB
references/examples/method/example-of-the-three-elements.mdmarkdown7.3 KB
references/examples/method/method-writing-common-issues-note.mdmarkdown355 B
references/examples/method/module-design-instant-ngp.mdmarkdown4.5 KB
references/examples/method/module-motivation-patterns.mdmarkdown410 B
references/examples/method/module-triad-neural-body.mdmarkdown763 B
references/examples/method/neural-body-annotated-figure-text.mdmarkdown2.8 KB
references/examples/method/overview-template.mdmarkdown2.0 KB
references/examples/method/pre-writing-questions.mdmarkdown479 B
references/examples/method/section-skeleton.mdmarkdown110 B
references/experiments.mdmarkdown4.7 KB
references/introduction.mdmarkdown15.3 KB
references/method.mdmarkdown6.9 KB
references/nat-comms-2025-corpus.mdmarkdown7.3 KB
references/nature-summary-paragraph.mdmarkdown10.3 KB
references/paper-review.mdmarkdown5.3 KB
references/paragraph-flow.mdmarkdown1.7 KB
references/related-work.mdmarkdown1.3 KB
references/submission-package.mdmarkdown7.9 KB
static/core/output-format.mdmarkdown1.8 KB
static/core/stance.mdmarkdown2.2 KB
static/core/workflow.mdmarkdown5.1 KB
static/fragments/journal/generic.mdmarkdown1.1 KB
static/fragments/journal/nat-comms.mdmarkdown3.1 KB
static/fragments/journal/nat-mach-intell.mdmarkdown5.9 KB
static/fragments/journal/nature-family.mdmarkdown1.2 KB
static/fragments/journal/nature.mdmarkdown2.7 KB
static/fragments/language/en.mdmarkdown1.0 KB
static/fragments/language/zh-to-en.mdmarkdown1.6 KB
static/fragments/paper_type/algorithmic.mdmarkdown1.2 KB
static/fragments/paper_type/hypothesis.mdmarkdown1.0 KB
static/fragments/paper_type/methods.mdmarkdown1.2 KB
static/fragments/paper_type/research.mdmarkdown1.3 KB
static/fragments/paper_type/review.mdmarkdown1.2 KB
static/fragments/section/abstract.mdmarkdown1.7 KB
static/fragments/section/conclusion.mdmarkdown929 B
static/fragments/section/discussion.mdmarkdown1.8 KB
static/fragments/section/experiments.mdmarkdown3.0 KB
static/fragments/section/intro.mdmarkdown2.6 KB
static/fragments/section/method.mdmarkdown1.5 KB
static/fragments/section/related-work.mdmarkdown1.2 KB
static/fragments/section/title.mdmarkdown999 B
static/fragments/task/manuscript.mdmarkdown288 B
static/fragments/task/submission-package.mdmarkdown2.5 KB
templates/submission/declarations-and-reviewers.texother2.6 KB
templates/submission/highlights-and-summary.texother1.1 KB
templates/submission/initial-cover-letter.texother1.6 KB
templates/submission/title-page.texother1.9 KB
tests/scoped-drafting.mdmarkdown1.9 KB

references/experiments.md

View on GitHub
# Experiments Writing Guide

## Contents

- [Goal](#goal)
- [Three Core Questions](#three-core-questions)
- [Experiment Planning](#experiment-planning)
- [Experiment Section Decomposition](#experiment-section-decomposition)
- [Figure/Table Writing Rules](#figuretable-writing-rules)
- [Recommended Ablation Package](#recommended-ablation-package)
- [Experimental Rigor Checklist](#experimental-rigor-checklist)


## Goal

Convince reviewers with complete evidence on effectiveness, causality, and practical value.

## Three Core Questions

1. Is the method better than strong baselines?
   - Run comparison experiments against strong and recent baselines.
   - Report standard metrics on the main benchmark(s).
   - Include SOTA or strongest public methods, not only weak baselines.
   - Keep protocol fair (same data split, preprocessing, and evaluation settings).
2. Which modules/design choices make the gain?
   - Run ablation studies for each key module/design choice.
   - Use remove/replace/disable variants and report delta to full model.
   - Include component interaction ablations when modules are coupled.
3. How far can the method generalize under harder settings?
   - Run demos/evaluations on harder or out-of-distribution settings.
   - Add stress-test scenarios (more complex scenes, rarer cases, noisier inputs, or stricter constraints).
   - Report both gains and failure modes to show realistic boundaries.

## Experiment Planning

```mermaid
flowchart TB
    A["Key Paper Claims"] --> B["What Contributions Are Claimed?"]
    B --> C1["Contribution 1"]
    B --> C2["Contribution 2"]
    B --> C3["Contribution 3"]
    C1 --> D1["Validation Experiment 1"]
    C2 --> D2["Validation Experiment 2"]
    C3 --> D3["Validation Experiment 3"]

    E["Method Pipeline Figure"] --> F["What Modules and Parameters Matter?"]
    F --> G1["Technical Module 1"]
    F --> G2["Technical Module 2"]
    F --> G3["Key Parameter 1"]
    F --> G4["Key Parameter 2"]
    G1 --> H1["Ablation Study 1"]
    G2 --> H2["Ablation Study 2"]
    G3 --> H3["Ablation Study 3"]
    G4 --> H4["Ablation Study 4"]
```

## Experiment Section Decomposition

```mermaid
flowchart TB
    S1["Experimental Setup"] --> S2["Validation Experiment 1"]
    S2 --> S3["Validation Experiment 2"]
    S3 --> S4["Ablation Studies"]
```

## Figure/Table Writing Rules

`Good tables are part of experiment communication quality, not decoration.`

1. Figure captions and table captions are equally important in the writing quality of Experiments.

### Hard rules

1. Put caption above the table.
2. Avoid vertical lines (`|`) in tabular columns.
3. Do not use double rules or dense `\hline` stacks.
4. Use `booktabs` style (`\toprule`, `\midrule`, `\bottomrule`) for clean structure.
5. Use as few horizontal rules as possible; lines should separate groups, not every row.
6. Highlight key numbers (best/second-best or target rows) with subtle color emphasis.

### Readability rules from review practice

1. Label metric direction in column headers (for example `PSNR ↑`, `LPIPS ↓`).
2. Add units when needed so values are interpretable without guessing.
3. Align text columns left; keep numeric columns consistently aligned.
4. Keep numeric precision consistent (same decimal places within a metric column).
5. Group multi-dataset or multi-setting results using `\multicolumn` + `\cmidrule`, not vertical separators.
6. One table, one message: do not mix unrelated results in a single table.
7. If rows represent different attributes/ablations, encode that explicitly in row names or attribute columns.
8. Keep caption focused on setting/protocol/notation, not long discussion.
9. If there is little detail to explain, use one concise sentence to summarize the main result.
10. For single-column figures/tables in two-column papers, prefer placing them in the right column when layout allows, so readers can enter the page from the left-top text without breaking reading flow.

### Minimal LaTeX checklist

1. Add packages in preamble: `\usepackage{booktabs}`, `\usepackage{colortbl,xcolor}` (and optionally `\usepackage{siunitx}` for decimal alignment).
2. Replace `\hline`-heavy style with `\toprule/\midrule/\bottomrule`.
3. Put `\caption{...}` before `\label{...}` and keep caption above.
4. Use restrained highlighting; never color too many cells.

## Recommended Ablation Package

1. One core ablation table for all major contributions.
2. Several focused mini-ablations for module-level design choices.
3. Matching qualitative visual results for each important ablation.

## Experimental Rigor Checklist

1. Are baselines recent and relevant?
2. Are metrics sufficient and standard for this task?
3. Is ablation tied to every key design claim?
4. Are claims in Abstract/Introduction supported by reported numbers?
5. Are limitations of evaluation scope explicitly stated?
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall