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 Results Framing

ASecurity

Use when a Physical Review Letters result is correct but its central claim and broad significance are not yet sharp. Structures the one-claim narrative; does not run analysis or design figures.

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

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Prl Results Framing?

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

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

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

Download with Pro
Files
SKILL.md
---
name: prl-results-framing
description: Use when a Physical Review Letters result is correct but its central claim and broad significance are not yet sharp. Structures the one-claim narrative; does not run analysis or design figures.
---

# PRL Results Framing (prl-results-framing)

## When to trigger

- You have the data/derivation but the "so what" is fuzzy
- The draft reads like a chronological lab report, not a single argument
- You have several findings and have not chosen the headline one
- The opening paragraph buries the result under background
- `prl-scope-fit` returned PRL but flagged the breadth framing as weak

## The one-claim discipline

A Letter makes **one** central claim. Everything else is support. Decide the headline result first; demote the rest to corroboration or to Supplemental Material.

- **Primary claim** — the single sentence the title and abstract both encode.
- **Supporting claims** — at most two, and only if they reinforce the primary one.
- **Everything else** — context, controls, extended sweeps → Supplemental Material (see `prl-supplementary`).

If you have two equally important claims, you likely have two papers, or one belongs in a specialized PR journal.

## The opening (first paragraph carries the gate)

PRL openings are short and front-load significance. A reliable four-move pattern:

1. **The general physics context** — one or two sentences a non-specialist physicist understands.
2. **The open question / gap** — what was unknown, unresolved, or impossible before.
3. **What this Letter shows** — the central claim, stated plainly, ideally with the key number or qualitative surprise.
4. **Why it matters broadly** — the consequence for a wider community.

Do not spend the first half-column on a literature tour. The result should appear within the first paragraph or two.

## Framing decision branches

| Symptom                                              | Move                                                        |
|------------------------------------------------------|-------------------------------------------------------------|
| Two co-equal headline results                         | Split, or demote one to support / SM                        |
| Result stated only operationally ("we measured ...")  | Reframe as the physical conclusion it implies               |
| Significance asserted, not shown                      | Tie significance to a concrete prior belief it changes      |
| Background dominates the opening                      | Cut to 2–3 sentences; move detail to body or SM             |
| Abstract lists methods before findings                | Reorder: finding first, method as the enabling clause       |

## Abstract craft

The abstract is a self-contained mini-Letter: context → what you did → what you found (with the key result) → why it matters. Lead with the finding, keep it short, avoid undefined acronyms, and make it readable by a physicist outside the subfield. APS imposes an abstract length limit — verify the current value.

## Checklist

- [ ] Exactly one primary claim, expressible in one sentence
- [ ] Title encodes the central result, not just the topic
- [ ] Opening reaches the result within ~1–2 paragraphs
- [ ] Significance is tied to a belief the result changes, not asserted
- [ ] Abstract leads with the finding and is intelligible out-of-subfield
- [ ] Supporting claims (≤2) genuinely reinforce the primary one
- [ ] Demoted material has a home in the body or SM

## Anti-patterns

- A "kitchen-sink" Letter that reports everything the project produced
- Operational framing ("we observe X") with no physical interpretation
- Significance claims that overreach beyond what the data support
- An abstract that is a methods summary rather than a result statement
- Saving the punchline for the conclusion (there is barely a conclusion in a Letter)

## Output format

```
【Primary claim】one sentence
【Title】encodes the result?  yes / fix
【Opening moves】context / gap / claim / significance — all present?
【Supporting claims】≤2, each justified
【Demoted to SM】list
【Abstract leads with finding】yes / fix
【Next】prl-methods (trust) or prl-figures (lead figure)
```

> Abstract and title norms are durable; verify the current abstract length limit 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 →