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 Ethics

ASecurity

Use to confirm clinical ethics and research-integrity requirements for an NEJM submission — IRB/ethics-committee approval and informed consent per the Declaration of Helsinki, ICMJE conflict-of-interest disclosures and authorship criteria, the role-of-the-funding-source statement, and the ICMJE data-sharing statement.

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

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-ethics --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Nejm Ethics?

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

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

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

Download with Pro
Files
SKILL.md
---
name: nejm-ethics
description: Use to confirm clinical ethics and research-integrity requirements for an NEJM submission — IRB/ethics-committee approval and informed consent per the Declaration of Helsinki, ICMJE conflict-of-interest disclosures and authorship criteria, the role-of-the-funding-source statement, and the ICMJE data-sharing statement.
---

# Clinical Ethics & Integrity (nejm-ethics)

## When to trigger

- The Methods do not state IRB/ethics approval or how informed consent was obtained.
- ICMJE disclosure forms are not collected for every author.
- There is no data-sharing statement (required by ICMJE for clinical trials).
- Authorship, contributions, or the role of the funder are unstated or unclear.

## Human-subjects ethics

- [ ] **IRB / ethics committee approval** — named committee(s) and that approval was obtained before enrollment.
- [ ] **Informed consent** — obtained from participants (or legal surrogates); describe any waiver and its basis.
- [ ] **Declaration of Helsinki** — state the trial was conducted in accordance with it (and GCP for trials).
- [ ] **Special populations** — additional protections for children, incapacitated adults, emergency-consent settings.

## ICMJE conflict-of-interest disclosures

- Every author completes the **ICMJE disclosure form**; financial and non-financial conflicts are reported.
- The manuscript carries a **disclosure / competing-interests statement**; "ICMJE disclosure forms are available with the full text" is the typical NEJM phrasing.
- Disclose relationships even if the author judges them irrelevant — the editor decides relevance.

## Authorship and contributions (ICMJE criteria)

ICMJE authorship requires **all four**: (1) substantial contribution to design or data; (2) drafting or critical revision; (3) final approval; (4) **accountability** for the work. Everyone meeting them is listed; everyone listed meets them.

- Contributors who do not meet all four go in **Acknowledgments** (with permission).
- Disclose **medical writers** and their funding source.
- State the **corresponding author's** attestation of data integrity and analysis.

## Role of the funding source

- A **role-of-the-funding-source statement** is required: did the funder design the study, collect/analyze/interpret data, write the manuscript, or decide to submit?
- For industry-sponsored trials, state who had access to the data and who vouches for completeness and fidelity to the protocol.

## Data-sharing statement (ICMJE)

ICMJE requires a **data-sharing statement for clinical trials**. Specify:

- **What** individual-participant data (and supporting documents: protocol, SAP, analytic code) will be shared.
- **When** (e.g., after publication, with an end date or "indefinitely").
- **To whom and for what** (e.g., researchers with a methodologically sound proposal).
- **By what mechanism** (repository, request to a committee) and under what conditions (data-use agreement).
- "No data will be shared" is a permissible statement but must be explicit and justified.

## Patient privacy and other integrity items

- **De-identify** all data and images; remove PHI; obtain consent for any potentially identifying material (e.g., clinical photographs).
- **Trial protocol publication** — NEJM publishes the protocol and SAP with trials; ensure they are submission-ready (see `nejm-study-design`).
- Report **plagiarism/originality** status: the work is original and not under consideration elsewhere.
- Note any **preprint** posting and prior presentation.

## Output format

```
【IRB/ethics approval + consent】 stated? Helsinki/GCP cited? yes/no
【ICMJE disclosures】 all authors' forms collected + statement drafted? yes/no
【Authorship】 all 4 ICMJE criteria met by each author? contributors acknowledged? yes/no
【Role of funding source】 statement present + data-access/vouching for trials? yes/no
【Data-sharing statement】 what/when/to-whom/how specified (ICMJE)? yes/no
【Privacy】 de-identified, PHI removed, consent for identifying material? yes/no
【Next】 nejm-abstract
```

## Anti-patterns

- **Do not** submit a trial without IRB approval and a consent description in the Methods.
- **Do not** omit the data-sharing statement — ICMJE requires it for clinical trials.
- **Do not** list honorary authors or omit qualifying contributors.
- **Do not** hide the funder's role, or who had full data access in a sponsored trial.
- **Do not** include identifiable patient information without explicit consent.

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 →