Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pnas Writing

ASecurity

Use to structure a PNAS main text and hold its length — Title, Significance Statement, Abstract, Introduction, Results, Discussion, in-text Materials and Methods, references — and to choose the required Classification (Biological/Physical/Social Sciences + minor subject) and keywords at submission.

1,052 stars
0 votes
0 copies
1 views
Added 6/6/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill pnas-writing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pnas Writing?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pnas Writing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-pnas-writing/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-pnas-writing)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: pnas-writing
description: Use to structure a PNAS main text and hold its length — Title, Significance Statement, Abstract, Introduction, Results, Discussion, in-text Materials and Methods, references — and to choose the required Classification (Biological/Physical/Social Sciences + minor subject) and keywords at submission.
---

# Main-Text Writing & Structure (pnas-writing)

## When to trigger

- The manuscript structure is unclear or out of PNAS order.
- Materials and Methods are missing, or someone wants to push them out of the main text.
- The paper is over the length budget.
- You have not chosen a **Classification** (major + minor) or keywords.
- The Results read like a lab notebook instead of an argument.

## PNAS main-text order

A PNAS research article runs, in order:

1. **Title** — declarative, specific, parseable by a non-specialist.
2. **Author list & affiliations.**
3. **Significance Statement** — ≤120 words (`pnas-significance`); submitted separately but part of the article.
4. **Abstract** — ~250-word single paragraph (`pnas-abstract`).
5. **Introduction** — the gap and why it matters broadly; end on what you found.
6. **Results** — argument-ordered (below).
7. **Discussion** — interpretation and broader significance; PNAS also permits a **combined "Results and Discussion."**
8. **Materials and Methods** — **kept in the main text** (see below).
9. **Acknowledgments, data availability, references.**

## Materials and Methods stays in-text (a key PNAS difference)

PNAS keeps a **Materials and Methods** section in the main text — unlike *Cell* or *Science* Reports, which push methods to supplements/endmatter. Provide enough method in the body to evaluate and reproduce the work; longer protocols and extended data go to **SI Appendix**. Do not strip the main-text Methods to chase a word count — move detail to SI instead.

## Length budget

- Research articles have **length limits** (commonly framed as up to ~6 journal pages, roughly on the order of ~8 figures/tables and a corresponding word/character budget). PNAS counts the **whole package** — abstract, main text, figures/tables, and references — against the page/character allowance.
- **Confirm the current word/character/page caps and the figure-table allowance in PNAS author guidelines** before finalizing; treat any number here as a working target, not a rule.
- Over-length material (extended methods, supporting figures/tables, supplementary text) → **SI Appendix**.

## Classification + keywords (required at submission)

PNAS requires a **Classification** for every research article:

- **Major category — exactly one division:** **Biological Sciences**, **Physical Sciences**, or **Social Sciences**.
- **Minor subject area:** one (sometimes a permitted second) subject within that division (e.g., Biological Sciences → Genetics; Physical Sciences → Applied Physical Sciences; Social Sciences → Economic Sciences). Pick from the PNAS list.
- **Keywords:** a short set (commonly up to ~5) for indexing.

Choose the classification that matches the **handling and review community** you want, consistent with the venue call in `pnas-fit` and the editor choice in `pnas-track`/`pnas-submission`.

## Structure as argument, not chronology

Order the Results by the **logic of the claim**, not the order experiments were run:

1. Establish the phenomenon (the headline result).
2. Rule out the obvious alternative explanations.
3. Show the mechanism / generality.
4. Demonstrate the broad implication.

Each Results paragraph: **claim sentence first**, then evidence (figure callout + numbers), then inference.

## Cross-references

- Main figures/tables: "Fig. 1", "Table 1".
- Supporting Information: "*SI Appendix*, Fig. S1 / Table S1"; datasets as "Dataset S1".

## Output format

```
【Order check】 Title / authors / Significance / Abstract / Intro / Results / Discussion / Materials and Methods / refs — gaps?
【Methods location】 in main text? yes (FIX if missing) — extended detail in SI Appendix?
【Length】 package within budget? N vs cap (confirm guidelines)
【Classification】 major (Bio/Phys/Social) + minor subject chosen? + keywords (≤~5)?
【Results order】 argument-ordered, claim-first? yes/no
【Items in main vs SI】 main: [...] / SI Appendix: [...]
【Next】 pnas-figures
```

## Anti-patterns

- **Do not** delete the main-text Materials and Methods to fit a word count — move detail to SI Appendix.
- **Do not** omit the Classification or keywords; they are required at submission.
- **Do not** structure Results chronologically when a logical order is clearer.
- **Do not** import a Science Report's "Methods-in-supplement" structure — PNAS keeps Methods in-text.
- **Do not** treat the Significance Statement or abstract as optional sections.

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →