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 Significance

ASecurity

Use to write the mandatory PNAS Significance Statement — ≤120 words, written so an educated reader outside the field (down to an undergraduate) understands why the work matters. Distinct from the abstract. The highest-value PNAS-specific artifact.

1,052 stars
0 votes
0 copies
2 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-significance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pnas Significance?

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

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

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

Download with Pro
Files
SKILL.md
---
name: pnas-significance
description: Use to write the mandatory PNAS Significance Statement — ≤120 words, written so an educated reader outside the field (down to an undergraduate) understands why the work matters. Distinct from the abstract. The highest-value PNAS-specific artifact.
---

# Significance Statement (pnas-significance)

## Why this is a flagship PNAS skill

Every PNAS research article must include a **Significance Statement** — a short, mandatory, separately submitted paragraph that explains, in plain language, **why the work matters to science and society**. It appears prominently with the article and is read by editors at triage and by the broad readership. It is **not** a second abstract. Getting it right is one of the highest-leverage things you can do for a PNAS submission, so draft it as soon as the central claim is locked — do not leave it to the final upload.

## When to trigger

- The submission has no Significance Statement.
- The Significance Statement just restates or condenses the abstract.
- It is dense with jargon and undefined acronyms.
- It exceeds ~120 words.

## The hard rule: ≤120 words, written for a non-specialist

- **Length:** **≤ 120 words** (confirm the exact cap in current PNAS author guidelines; treat 120 as the ceiling).
- **Audience:** an **educated scientist outside your field — down to a bright undergraduate**. If a chemistry undergraduate or a non-specialist colleague cannot follow it, rewrite it.
- **Test:** read it aloud to someone who is smart but not in your subfield. If they can say back *why the result matters*, it works.

## What it must do (and not do)

The Significance Statement answers **"so what, and who cares?"** — the abstract answers **"what did you do and find?"**

| Significance Statement | Abstract (`pnas-abstract`) |
|------------------------|----------------------------|
| Why it matters, for a broad reader | What/how/found, for scientists |
| Plain language, minimal jargon | Technical but accessible |
| The gap + the advance + the broader consequence | Context, methods, quantified results, conclusion |
| ≤120 words | ~250 words |

## Template (four short moves, no headings)

1. **The problem / gap (1–2 sentences).** What broad question or limitation does the field face? State the stakes plainly.
2. **What this work shows (1–2 sentences).** The advance, in non-technical terms — the result, not the method.
3. **Why it matters (1–2 sentences).** The consequence for the field, for other fields, or for society — what changes because of this.
4. *(Optional)* one sentence on broader application or future direction, only if it is concrete.

> Keep it to one paragraph. No citations, no figure references, no undefined acronyms, no equations.

## Worked shape

> *"[Broad phenomenon] underlies [important process], yet how [specific gap] has remained unclear. Here we show that [plain-language advance], demonstrating that [general principle]. This finding [changes/explains/enables] [broad consequence], with implications for [adjacent field or application]."*

## The undergraduate rewrite drill

When a draft statement is too technical, run this pass:

1. Underline every word a second-year undergraduate in another discipline would not know.
2. For each, replace it with a plain phrase, or cut the sentence it lives in.
3. Replace gene/protein/parameter names and acronyms with what they *do* ("a protein that controls cell division" not "CDK1").
4. Read what remains. If the "why it matters" is now gone, you were hiding it behind jargon — write it back in plainly.

> The cap is short (≤120 words) precisely to force this. You are not summarizing the paper; you are answering "why should a non-specialist care?"

## Common failures (rewrite on sight)

- **Too technical** — full of jargon, gene names, model parameters, or acronyms.
- **A restatement of the abstract** — reviewers and editors notice immediately; it must be genuinely broader and plainer.
- **Method-led** — leads with what you did rather than why it matters.
- **Over-claiming** — promising societal impact the data do not support (cross-check `pnas-fit`).
- **Over length** — anything past ~120 words signals the author did not engage with the genre.
- **No "so what"** — describes the result but never says why a non-specialist should care.

## Output format

```
【Word count】 N ≤ 120
【Reader test】 can a non-specialist / undergraduate state why it matters? yes/no
【Four moves present?】 gap / advance(plain) / why-it-matters / (optional) application
【Distinct from abstract?】 yes/no (if no, rewrite — not a condensed abstract)
【Jargon / acronym hits removed】 [...]
【Over-claiming check】 consequence supported by the data? (link pnas-fit if not)
【Next】 pnas-abstract
```

## Anti-patterns

- **Do not** copy-paste or compress the abstract into the Significance Statement.
- **Do not** write it for specialists — write it for a smart reader outside the field.
- **Do not** exceed ~120 words "to be thorough"; the cap is the point.
- **Do not** lead with methods; lead with the problem and the consequence.
- **Do not** claim societal impact the evidence cannot back.

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 →