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 Figures

ASecurity

Use to finalize PNAS display items — column-width sizing (~9 / 11.4 / 18 cm), minimum font sizes, show-the-data with n and defined error bars, scale bars, colorblind-safe palettes, legend structure, image integrity, and color-mode notes. Enforces figure rigor before submission.

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

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Pnas Figures?

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

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

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

Download with Pro
Files
SKILL.md
---
name: pnas-figures
description: Use to finalize PNAS display items — column-width sizing (~9 / 11.4 / 18 cm), minimum font sizes, show-the-data with n and defined error bars, scale bars, colorblind-safe palettes, legend structure, image integrity, and color-mode notes. Enforces figure rigor before submission.
---

# Display Items (pnas-figures)

## When to trigger

- Figures and tables push the page/item allowance (`pnas-writing`).
- Fonts are unreadable at print size, or colors are not colorblind-safe.
- Bar charts hide the underlying data (no points, no n).
- Panels are screenshots of software output pasted into the figure.
- You are unsure which column width to design to.

## Sizing for PNAS columns

PNAS is a multi-column journal; design each figure to render at a standard print width **without rescaling text**:

- **1 column** ≈ **9 cm** wide
- **1.5 column** ≈ **11.4 cm** wide
- **2 columns (full width)** ≈ **18 cm** wide

> Confirm exact widths in current PNAS author/digital-art guidelines.

- Minimum font in the final figure: **~6–8 pt** (sans-serif, e.g., Helvetica/Arial), legible after reduction to print size.
- Line weights ≥ ~0.5 pt; avoid hairlines that vanish in print.
- Submit at the required resolution (line art high-dpi; halftones/photos at the specified dpi) — confirm specs.

## Show the data, not just the summary

- Replace bar-of-means with **dot plots / box+points / violins+points** wherever n is small.
- Always state **n** in the legend, and **what n is** (cells? animals? subjects? independent experiments?).
- Error bars must be **defined** in the legend (SD vs SEM vs 95% CI) — never undefined.
- For images (blots, micrographs): include **scale bars**, and keep full, uncropped key blots for SI Appendix.

## Color and accessibility

- Use a **colorblind-safe palette** (avoid red/green as the only contrast).
- Don't encode meaning by color alone — add shape/pattern/labels.
- **Color mode:** prepare figures in **RGB** for online; PNAS prints in color and may request or convert to **CMYK** for print — confirm the current color-figure policy and any charges. Check that figures remain interpretable in grayscale.
- No rainbow/jet colormaps for continuous data — use perceptually uniform maps (viridis, etc.).

## Figure legend structure

Each legend: a short **title sentence** (the claim of the figure), then per-panel descriptions (A, B, C…), then statistics (test, n, error-bar definition, exact P or values). The legend should let the figure stand alone.

## Integrity rules (non-negotiable)

- No selective deletion, splicing, or beautification of gels/blots/images without a labeled boundary; disclose any grouping.
- Quantitative comparisons must come from the **same** experiment/exposure.
- Keep unprocessed source images and source data — PNAS may request them (`pnas-data`).

## Multi-panel discipline

- Keep panels purposeful; if a figure sprawls, split it or move panels to SI Appendix.
- Consistent axis scales across comparable panels.
- One message per figure; the legend title states it.

## Output format

```
【Item count】 figures + tables vs page/item allowance (confirm guidelines) → ok / over
【Sizing】 designed at 9 / 11.4 / 18 cm? fonts ≥ ~6–8 pt? yes/no
【Data shown】 points + n + defined error bars? yes/no
【Color】 colorblind-safe? RGB online / CMYK-print aware? grayscale-readable? yes/no
【Integrity】 scale bars / uncropped blots in SI / source data kept? yes/no
【Fixes】 [...]
【Next】 pnas-statistics
```

## Anti-patterns

- **Do not** paste raw Stata/Prism/ImageJ screenshots as figures.
- **Do not** use bars to hide n=3 with huge spread — show the points.
- **Do not** leave error bars undefined or mix SD and SEM across panels.
- **Do not** rely on red-vs-green as the sole encoding.
- **Do not** assume color print is free — confirm the color policy.

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 →