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 Fit

ASecurity

Use first, before any writing, to stress-test whether a result clears PNAS's bar — high quality and broad significance to a general scientific readership — and to make the realistic call between PNAS, Science/Nature, and a specialist field journal.

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

Works with

cli

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Pnas Fit?

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

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

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

Download with Pro
Files
SKILL.md
---
name: pnas-fit
description: Use first, before any writing, to stress-test whether a result clears PNAS's bar — high quality and broad significance to a general scientific readership — and to make the realistic call between PNAS, Science/Nature, and a specialist field journal.
---

# Scope & Significance Fit (pnas-fit)

## Why this is skill #1

PNAS is selective, but its gate is different from Science/Nature. The bar is **high-quality, broadly significant science** — not *only* the single flashiest discovery of the year. A rigorous, important, well-supported paper that a general scientific audience would value has a real home at PNAS even if it is not top-1% headline news. Run this before investing in prose, and use it to make the **realistic step-down** call from Science/Nature.

## When to trigger

- Before drafting, to decide if PNAS is the right venue.
- After a Science/Nature desk reject or transfer, to judge whether PNAS is the right next stop.
- When choosing among Science/Nature, PNAS, and a top field journal.
- When a co-author who is an NAS member offers to communicate the paper (then also run `pnas-track`).

## PNAS's bar vs Science/Nature

| Bar level | Venue |
|-----------|-------|
| Top-1% general-interest discovery, decisive and timely | **Science / Nature** (use those packs) |
| High-quality, important, broadly significant — solid science a general audience values | **PNAS** |
| Deep but mostly of interest to one subfield | top **field journal** |
| Clinical/medical with patient outcomes | **NEJM / Lancet** (use those packs) |

PNAS values **solid important science over only-the-flashiest**. Do not under-sell a strong paper as "not good enough for PNAS" just because it would not lead Science; equally, do not inflate an incremental result.

## The general-significance test

Imagine a reader from a **different** PNAS division (a cell biologist reading a physics paper, an economist reading a genetics paper). The paper passes if that reader would say "I understand why this matters and I'd want to know about it." PNAS spans **Biological, Physical, and Social Sciences**, so the cross-division reader is real — write for them.

## Significance ladder (weak → strong)

1. **Confirms** an expected result in one system. (Weak — field journal.)
2. **Extends** a known effect to a new system/scale with clear added value. (Borderline — PNAS if the lesson is general.)
3. **Resolves** a question the broad community cares about. (Strong — solid PNAS.)
4. **Reveals** a previously unknown phenomenon, mechanism, or capability. (Strong — PNAS or up.)
5. **Overturns** a widely held assumption with decisive evidence. (Strongest — consider Science/Nature too.)

Rungs 2–4 are the PNAS sweet spot. Rung 5 may justify trying Science/Nature first; rung 1 points to a field journal.

## Venue routing

| Situation                                                        | Recommend              |
|-----------------------------------------------------------------|------------------------|
| Rung 4–5, decisive, broad, timely                               | try **Science / Nature** first; **PNAS** is a strong fallback |
| Rung 2–4, solid, broadly significant, rigorous                  | **PNAS** (Direct or Contributed → `pnas-track`) |
| Deep but specialist                                             | top **field journal**  |
| Clinical/medical with patient outcomes                          | **NEJM / Lancet**       |
| Strong idea but evidence not yet decisive                       | add experiments before submitting |

## Fatal weak-fit triggers

- The advance is **incremental** over the authors' own prior paper with no general lesson.
- The claim is **narrow** ("in our system, under our conditions…") and stays there.
- The "broad implication" is **asserted, not demonstrated**.
- **Over-claiming**: the conclusion outruns the evidence.

## Output format

```
【Significance rung】 1–5 + one-line justification
【Cross-division reader test】 pass / borderline / fail (which other-division reader cares, and why)
【PNAS division (likely)】 Biological / Physical / Social Sciences
【Fatal triggers present】 [...]
【Recommended venue】 Science-Nature / PNAS / field journal / NEJM-Lancet
【If PNAS, the single sentence of broad significance】 "..."
【Next】 pnas-track (if PNAS) | reconsider venue (if fail)
```

## Anti-patterns

- **Do not** rationalize a specialist result into "broad significance" with adjectives.
- **Do not** confuse technical difficulty with significance — hard ≠ important.
- **Do not** treat PNAS as merely "the journal you settle for" — it has a real, defensible bar.
- **Do not** let sunk cost drive the venue decision.

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 →