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 Supplementary

ASecurity

Use when partitioning content between the Physical Review Letters body and its Supplemental Material, ensuring the Letter stands alone while derivations and extended data live in the SM. Organizes the SM; does not write the Letter body.

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 prl-supplementary --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prl Supplementary?

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

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

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

Download with Pro
Files
SKILL.md
---
name: prl-supplementary
description: Use when partitioning content between the Physical Review Letters body and its Supplemental Material, ensuring the Letter stands alone while derivations and extended data live in the SM. Organizes the SM; does not write the Letter body.
---

# PRL Supplemental Material (prl-supplementary)

## When to trigger

- The Letter is over length and detail must move out of the body
- A reader cannot follow the Letter without consulting the SM
- You have derivations, extended datasets, or methods detail with no home
- You are unsure what is allowed in SM versus what must stay in the Letter
- Referees of a prior version asked for material that would bloat the body

## The stand-alone rule (non-negotiable)

The Letter must be **fully understandable on its own**. The Supplemental Material *supports* the Letter; it must never be *load-bearing* for the central claim. A reader who never opens the SM should still grasp the result, the evidence for it, and why it matters.

- The central claim, its key evidence, and the decisive control live in the **Letter**.
- The SM holds the exhaustive backup that a skeptical referee or replicator wants.
- Every SM section is **cited from the body** at the point it is relevant.

If removing the SM breaks the argument, the partition is wrong — pull the essential piece back into the Letter (and trim elsewhere via `prl-length-management`).

## What belongs in Supplemental Material

| Content                                            | Home  |
|----------------------------------------------------|-------|
| Full derivations / lengthy algebra                  | SM    |
| Extended datasets, additional samples, full sweeps  | SM    |
| Detailed apparatus, growth, calibration             | SM    |
| Secondary controls and robustness checks            | SM    |
| Full error budget / systematics breakdown           | SM    |
| Numerical convergence studies                        | SM    |
| Additional figures / movies / large tables          | SM    |
| The central claim and its decisive evidence          | Letter|
| The one control ruling out the obvious artifact      | Letter|
| The headline uncertainty                             | Letter|

## SM organization

- Mirror the Letter's logic: order SM sections to match the order they are cited.
- Give SM sections their own clear headings (S1, S2, ...) and self-contained captions.
- SM references: include the works the SM itself needs; follow current APS practice on how SM citations are counted and listed (verify).
- Label SM figures/tables distinctly (Fig. S1, Table S1) to avoid confusion with the Letter.
- Keep the SM honest: it is peer-reviewed alongside the Letter, not a place to hide weak results.

## Checklist

- [ ] The Letter is understandable without ever opening the SM
- [ ] No central-claim evidence is *only* in the SM
- [ ] Every SM section is cited from the body at the relevant point
- [ ] SM sections ordered to match their citation order in the Letter
- [ ] SM figures/tables labeled S1, S2, ... distinctly
- [ ] Derivations, extended data, secondary controls live in SM
- [ ] SM is internally consistent in notation with the Letter
- [ ] SM citation handling follows current APS practice

## Anti-patterns

- A Letter that silently depends on the SM to be understood
- Burying the decisive control or key uncertainty in the SM
- An SM that is a disorganized dump rather than a structured appendix
- SM figures referenced out of order or never cited from the body
- Notation drift between Letter and SM
- Using the SM to smuggle in claims the referees did not vet

## Output format

```
【Letter stands alone】yes / fix (pull back: ...)
【SM sections】S1: ... / S2: ... (cited from body?)
【Central evidence only in SM?】none / move back: ...
【SM figure/table labels】S-prefixed?  yes / fix
【Notation consistent Letter↔SM】yes / fix
【Next】prl-writing-style or prl-length-management
```

> SM scope, citation counting, and file-format rules evolve — verify 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 →