Skip to main content
skill CX Codex

domain-research-health-science — Claude Code skill: how to install

domain-research-health-science structures health science and medical evidence synthesis using PICOT framing, formal bias checklists, and GRADE certainty scoring.

no license 119 installs ★ 203 updated 2026-09-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add lyndonkl/claude --skill domain-research-health-science -a claude-code
Open on GitHub

What domain-research-health-science does

The skill guides assistants through a six-step workflow for health science literature review. It begins with explicit PICOT structuring and matches inquiry types to corresponding study architectures, selecting randomized trials for therapies or cohort studies for prognosis.

Bias appraisal uses recognized domain benchmarks: Cochrane RoB 2 for randomized trials, ROBINS-I for observational cohorts, and QUADAS-2 for diagnostic tests. It prioritizes endpoints that matter directly to patients over laboratory surrogates, establishing minimal clinically important differences before synthesising evidence.

Synthesized outputs follow GRADE criteria down to final certainty ratings. The bundled validation rubric enforces an average score threshold of at least 3.5, which blocks superficial reviews that skip confounder analysis.

What it helps with

  • structure clinical inquiries using the PICOT framework
  • assess trial risk of bias with Cochrane RoB 2 or ROBINS-I
  • separate patient-critical endpoints from laboratory surrogate markers
  • rate evidence certainty using standardized GRADE criteria

Example prompts for the agent

  • Structure a PICOT question comparing SGLT2 inhibitors against standard care for heart failure
  • Evaluate this observational study for risk of bias using ROBINS-I criteria
  • Generate a summary of findings table and assign GRADE certainty ratings to these outcomes

How to install domain-research-health-science

1Skills CLI (Vercel)

npx skills add lyndonkl/claude --skill domain-research-health-science -a claude-code

2Manually: put the files in place

~/.claude/skills/domain-research-health-science/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/domain-research-health-science/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about domain-research-health-science

How do I install domain-research-health-science in Claude Code?

Run npx skills add lyndonkl/claude --skill domain-research-health-science -a claude-code. The file is saved to ~/.claude/skills/domain-research-health-science/SKILL.md.

What does domain-research-health-science do?

It provides structured guidance for clinical evidence reviews, covering question formulation, study quality appraisal, outcome hierarchy definition, and GRADE evidence profiles.

Which bias assessment tools are supported?

It incorporates Cochrane RoB 2 for randomized controlled trials, ROBINS-I for non-randomized studies, QUADAS-2 for diagnostic accuracy, and AMSTAR 2 for reviews.

Similar skills

All skills for Science and research →

From the same set49

The whole set →
d3-visualization d3-visualization is a Claude Code skill for building D3.js charts, maps, network diagrams and hierarchies with animation and interactivity. It gives control over visual details beyond ready-made libraries. CX Codex +1 126installs one-pager-prd one-pager-prd is a Claude Code skill that turns a feature idea into a one-page spec or PRD with its problem, solution, users, metrics, and scope, before detailed design or development. CX Codex +1 125installs environmental-scanning-foresight environmental-scanning-foresight tracks external trends across six PESTLE dimensions, catches weak signals of change, builds scenario futures, and sets adaptive indicators for early warning. CX Codex +1 120installs scout-mindset-bias-check scout-mindset-bias-check is a Claude Code skill that checks forecasts with Scout Mindset procedures, including when an estimate feels emotional or stuck at 50/50. CX Codex +1 119installs adr-architecture adr-architecture turns an architecture choice into a written decision record with context, rejected options and consequences, then scores the draft against a rubric. CX Codex +1 118installs constraint-based-creativity constraint-based-creativity — a skill that makes the model invent inside tight limits, such as a small budget or a fixed format, so brainstorming stops circling the same answers. CX Codex +1 115installs translation-reframing-audience-shift translation-reframing-audience-shift rewrites content for a different audience: technical docs to business cases, strategy to action steps, expert text to plain language. CX Codex +1 115installs meta-prompt-engineering The meta-prompt-engineering skill turns unclear prompts into structured instructions with a defined role, task steps, constraints, and quality checks. Use it when an agent’s responses vary between runs. CX Codex +1 114installs

Project sponsors

Companies that keep this analytics open