Agent skill · AI & Agents

nejm-abstract

Use to write the NEJM structured abstract — four headed sections (Background, Methods, Results, Conclusions), ≤250 words, with the trial registration number and funding source, leading the Results with the primary outcome reported as an effect size with a 95% CI. Late-stage polish skill.

brycew6m4,252★ · +31/wk · 3 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill nejm-abstract --agent claude-code

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

Facts
Files in the skill folder: 1
SKILL.md size: 5 KB
Bundled scripts: none
Path: NEJM-Skills/skills/nejm-abstract/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

# Structured Abstract (nejm-abstract) ## When to trigger - Significance, design, reporting, and statistics are settled (do this late). - The abstract is unstructured prose, or exceeds the word cap. - The Results section reports P values but not the primary outcome with its effect size and CI. - The trial registration number and funding source are missing. ## The four required sections (Background, Methods, Results, Conclusions) NEJM uses a **structured abstract, ≤250 words**, with four headed sections. Confirm the exact cap against the current author guidelines; design for 250 as the ceiling. ### Background One or two sentences: the clinical problem and the specific question. State why the question matters in practice — no extended literature review. ### Methods Design (e.g., "randomized, double-blind, placebo-controlled trial"), population and setting, intervention/comparator, randomization, the **pre-specified primary outcome** and key secondary outcomes, and the analysis population (intention-to-treat). ### Results Lead with the **primary outcome**. Report the **effect size with a 95% confidence interval** — absolute difference and/or relative measure (hazard ratio, risk ratio,

What's inside
Steps it walks through
  1. When to trigger
  2. The four required sections (Background, Methods, Results, Conclusions)
  3. Background
  4. Methods
  5. Results
  6. Conclusions
  7. Hard constraints
  8. Concrete template (RCT)
  9. Operating pass for New England Journal of Medicine
  10. Output format
  11. Anti-patterns
More from Awesome-Journal-Skills
All skills →
About this skill
What does the nejm-abstract skill do?

Use to write the NEJM structured abstract — four headed sections (Background, Methods, Results, Conclusions), ≤250 words, with the trial registration number and funding source, leading the Results with the primary outcome reported as an effect size with a 95% CI. Late-stage polish skill.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill nejm-abstract --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