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

Prl Figures

ASecurity

Use when designing or auditing figures for a Physical Review Letters manuscript, where a few high-impact figures must carry the central result and count against the length limit. Designs figure strategy; does not run the analysis or write prose.

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

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Prl Figures?

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

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

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

Download with Pro
Files
SKILL.md
---
name: prl-figures
description: Use when designing or auditing figures for a Physical Review Letters manuscript, where a few high-impact figures must carry the central result and count against the length limit. Designs figure strategy; does not run the analysis or write prose.
---

# PRL Figures (prl-figures)

## When to trigger

- You have many candidate figures and need to choose a few
- Your lead figure does not convey the central result at a glance
- Panels are dense, captions are long, or symbols are unreadable at column width
- You are over length and figures (which count against the limit) are a target
- A coauthor wants to "add one more panel just in case"

## Figure strategy for a Letter

A Letter carries **a few high-impact figures only** — typically on the order of three or four, sometimes fewer. Every figure must earn its place against the deductible length limit (figures consume the word budget; see `prl-length-management`). The hierarchy:

- **Lead figure (Fig. 1)** — conveys the central result at a glance. A physicist skimming should grasp the headline from this figure plus its caption alone.
- **Supporting figures** — each makes exactly one additional point (a control, a dependence, a comparison to theory).
- **Everything else** — parameter sweeps, raw traces, extended datasets → Supplemental Material.

If a figure does not advance the single central claim or one essential support, move it to SM.

## Lead-figure design rules

| Principle                     | Practice                                                        |
|-------------------------------|----------------------------------------------------------------|
| One glance, one message       | The eye should land on the central result immediately          |
| Self-explaining               | Headline readable from figure + caption, without the body      |
| Schematic + data              | A small schematic/inset can orient out-of-subfield readers     |
| Theory vs. experiment overlaid| Show the decisive comparison directly, not in separate panels  |
| Annotate the key feature      | Arrow / label on the peak, transition, or scaling that matters |

## Production standards (column format)

- Design for **single-column width** first; use double-column only when the data demand it.
- Fonts, axis labels, and tick numbers must be legible at final printed size (roughly match the body text size).
- Use vector formats (EPS/PDF) for line art; high-resolution raster only for images/maps.
- Curves distinguishable in grayscale and color-blind-safe palettes; do not rely on color alone.
- Define every symbol/line in the caption; keep captions informative but tight (they count against length).
- Match notation in figures to the body; use SI units and consistent significant figures.

## Panel discipline

- Prefer fewer panels with a clear reading order; label (a), (b), (c).
- A six-panel Fig. 1 usually signals that supporting panels belong in SM.
- Insets are powerful for a zoom or a schematic, but must remain legible.

## Checklist

- [ ] Total figure count is small (a few) and each is essential
- [ ] Fig. 1 conveys the central result at a glance
- [ ] Every figure makes exactly one point
- [ ] All figures legible at single-column print size
- [ ] Color-blind-safe; not color-dependent; grayscale-distinguishable
- [ ] Decisive theory/experiment comparison shown directly
- [ ] Captions define all symbols and are as short as clarity allows
- [ ] Non-essential panels/datasets moved to SM

## Anti-patterns

- A lead figure too dense to parse without the body text
- Six-panel megafigures that hide the headline
- Color-only encoding that fails in grayscale or for color-blind readers
- Tiny fonts / unreadable tick labels at column width
- Decorative figures that do not advance the central claim
- Long captions that quietly consume the length budget

## Output format

```
【Figure count】N — each essential?  yes / cut list
【Fig. 1 conveys central result at a glance】yes / redesign
【Per-figure single point】list
【Legibility at column width】pass / fix
【Color-blind / grayscale safe】yes / fix
【Moved to SM】list
【Next】prl-supplementary (SM) or prl-length-management (fit limit)
```

> Figure formatting and length-counting rules are durable in spirit but specific in detail — verify current figure and length-deduction rules on the official APS / PRL author page.

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 →