Agent skill · Code Review & Quality

prl-methods

Use when deciding what methodological detail belongs in a Physical Review Letters body versus Supplemental Material, so a physicist can trust the result without the Letter becoming a long paper. Partitions methods; does not design figures or run analysis.

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill prl-methods --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 6 KB
Bundled scripts: none
Path: Physical-Review-Letters-Skills/skills/prl-methods/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 909 · +31 this week
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# PRL Methods (prl-methods) ## When to trigger - Your Methods text is several paragraphs of apparatus, sample, or derivation detail - You cannot tell what a reader *needs* versus what is reassuring completeness - Reviewers of a prior draft asked for more rigor, and you are tempted to add bulk - The Letter is over length and methods are a prime trimming target - You are unsure which derivation steps to keep inline versus move to SM ## The trust-minimum principle In a Letter, methods exist to let a competent physicist **believe the central claim** — not to enable full replication inline. Full replication detail lives in Supplemental Material. Keep in the body only what is load-bearing for trust: - The essential experimental configuration or theoretical setup (one compact description). - The key control(s) that rule out the obvious alternative explanation. - The decisive statistical/systematic statement (uncertainties, significance) for the headline number. - The one or two equations that define the quantity being claimed. Everything else — calibration procedures, sample growth, full Hamiltonians, lengthy derivations, parameter sweeps, additional checks — goes to SM and is cited inlin

What's inside
Steps it walks through
  1. When to trigger
  2. The trust-minimum principle
  3. Partition table
  4. Rigor without bulk
  5. Worked micro-example: compressing an apparatus paragraph
  6. Sentence patterns that buy trust cheaply
  7. Checklist
  8. Anti-patterns
  9. Output format
More from Awesome-Journal-Skills
All skills →
About this skill
What does the prl-methods skill do?

Use when deciding what methodological detail belongs in a Physical Review Letters body versus Supplemental Material, so a physicist can trust the result without the Letter becoming a long paper. Partitions methods; does not design figures or run analysis.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill prl-methods --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going