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

Nejm Fit

ASecurity

Use first, before any writing, to stress-test whether a clinical study clears NEJM's bar — practice-changing clinical impact, methodological rigor, and generalizability. Decides NEJM vs Lancet/JAMA vs a specialty journal.

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

Works with

cli

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Nejm Fit?

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

Security grade badge for Nejm Fit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-nejm-fit/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-nejm-fit)

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

Download with Pro
Files
SKILL.md
---
name: nejm-fit
description: Use first, before any writing, to stress-test whether a clinical study clears NEJM's bar — practice-changing clinical impact, methodological rigor, and generalizability. Decides NEJM vs Lancet/JAMA vs a specialty journal.
---

# Clinical Significance Fit (nejm-fit)

## Why this is skill #1

NEJM triages **the large majority of submissions to rejection without external review**. The gate is not "is the study sound" — it is **"would this change clinical practice, and is the evidence definitive enough to justify that change."** A well-conducted but narrow study is desk-rejected. Run this before investing in prose.

## When to trigger

- Before drafting, to decide if NEJM is even the right venue.
- When a co-author says "this is an NEJM paper" and you need a sober second opinion.
- When choosing between NEJM, Lancet, JAMA, a specialty journal (e.g., Circulation, Blood, JCO), and NEJM Evidence.

## The three gates (all must hold)

NEJM weighs three things together. A paper passes only if it clears all three:

1. **Clinical importance** — does it address a question clinicians and patients actually face, with an outcome that matters (mortality, major morbidity, function, quality of life — not just a surrogate)?
2. **Methodological rigor** — is the design strong enough that the result is believable and not likely to be overturned (adequately powered RCT, rigorous observational design with confounding addressed)?
3. **Generalizability** — do the findings extend beyond a single center / narrow population to the broad practice community NEJM serves?

A large RCT with a surrogate endpoint can still fail gate 1. A striking finding from one underpowered single-center study fails gates 2–3.

## Significance ladder (weak → strong)

1. **Case report / small case series.** (Weak — correspondence or specialty journal.)
2. **Mechanistic or early-phase finding** without clinical outcomes. (Specialty / translational journal.)
3. **Single rigorous study extending known effects** to a new population. (Borderline — JAMA/Lancet/specialty.)
4. **Definitive RCT or landmark study answering a practice question** with a hard outcome. (Strong.)
5. **Practice-changing trial that resolves a controversy or sets a new standard of care.** (Strongest.)

If you cannot place the work at rung 4+, NEJM is a long shot — be honest with the user and name the realistic target.

## Fatal desk-reject triggers

- Outcome is a **surrogate** (lab value, imaging marker) with no patient-important endpoint.
- **Underpowered** for the primary outcome, or the primary outcome was changed post hoc.
- **Single-center**, narrow population, with no claim to generalizability.
- **Not prospectively registered** for a trial (an ICMJE deal-breaker — see `nejm-study-design`).
- **Over-claiming**: causal language on observational data, or a subgroup result sold as the main finding.
- Incremental over the authors' own prior trial with no new practice implication.

## Venue routing

| Situation                                                          | Recommend                          |
|--------------------------------------------------------------------|------------------------------------|
| Definitive, practice-changing, generalizable RCT/landmark study    | **NEJM** (Original Article)        |
| Rigorous and important, but global-health or broad public-health framing | **The Lancet**               |
| Strong clinical trial/study, large general-medicine audience       | **JAMA**                           |
| Methodologically strong, fits open-science/registration ethos      | **BMJ**                            |
| Important to one specialty, not broad practice                     | **specialty journal** (Circulation, Blood, JCO, …) |
| Solid but not top-tier general impact; pragmatic/methods focus     | **NEJM Evidence** / specialty      |
| Early-phase / mechanism / surrogate only                           | translational or specialty journal |

## Output format

```
【Three gates】 clinical importance / rigor / generalizability — pass or fail each, one line
【Significance rung】 1–5 + one-line justification
【Outcome type】 patient-important / surrogate-only → flag if surrogate
【Fatal triggers present】 [...]
【Recommended venue】 NEJM / Lancet / JAMA / BMJ / specialty / NEJM Evidence
【If staying with NEJM, the single sentence of practice-changing impact】 "..."
【Next】 nejm-study-design (if pass) | reconsider venue (if fail)
```

## Anti-patterns

- **Do not** rationalize a narrow result into "practice-changing" with adjectives — editors discount adjectives.
- **Do not** confuse a statistically significant surrogate endpoint with clinical importance.
- **Do not** let sample size alone stand in for rigor — a large biased study is still biased.
- **Do not** let sunk cost ("the trial took five years") drive the venue decision.

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 →