Agent skill · Workflow & Productivity

m4-research

Start a structured clinical research session. Triggers on "/research", "start research", "new study", "analyze cohort", "investigate hypothesis", "research question", or when users describe clinical research goals. Interviews the user, then produces a rigorous research plan.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill m4-research-hannesill-m4 --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 10 KB
Bundled scripts: none
Version: 1.0
Declared author: m4-clinical-extraction
Path: skills/analysis/m4-research-hannesill-m4/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

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

From the SKILL.md

# M4 Clinical Research Workflow This skill guides you through a structured clinical research session. It ensures scientific rigor from hypothesis formation through analysis execution. ## When This Skill Activates - User invokes `/research` command - User describes research intent: "I want to study...", "Can we analyze...", "What's the mortality rate for..." - User mentions cohort analysis, hypothesis testing, or comparative studies ## Phase 1: Research Interview **Before writing any queries, interview the user to establish:** ### 1. Research Question Ask: "What specific clinical question are you trying to answer?" Good questions are: - Specific and answerable with available data - Clinically meaningful - Novel or confirmatory of existing findings Help refine vague questions: - "Are sicker patients dying more?" → "Is day-1 SOFA score independently associated with 30-day mortality in sepsis patients?" ### 2. Study Design Ask: "What type of study is this?" - **Descriptive**: Characterize a population (demographics, distributions) - **Comparative**: Compare groups (exposed vs unexposed, treatment A vs B) - **Predictive**: Build or validate a prediction model - **Exploratory**: Hypothes

What's inside
Steps it walks through
  1. When This Skill Activates
  2. Phase 1: Research Interview
  3. 1. Research Question
  4. 2. Study Design
  5. 3. Outcome Variable
  6. 4. Exposure/Intervention
  7. 5. Population (Inclusion/Exclusion)
  8. 6. Confounders
  9. 7. Dataset Selection
  10. Phase 2: Draft Research Protocol
  11. Phase 3: Scientific Integrity Guardrails
  12. Bias Prevention
  13. Statistical Rigor
  14. Reproducibility
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the m4-research skill do?

Start a structured clinical research session. Triggers on "/research", "start research", "new study", "analyze cohort", "investigate hypothesis", "research question", or when users describe clinical research goals. Interviews the user, then produces a rigorous research plan.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill m4-research-hannesill-m4 --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 majiayu000/claude-skill-registry, a repository with 534 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