Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Clinical Reports Drafting

Builds safety-bounded draft structures for clinical, trial, and safety reports and runs offline deterministic checks on structure and provenance.

Docs & OfficeAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Routes each artifact to the correct reporting guidance: CARE 2013 for case reports, ACR/CAP/CLIA boundaries for diagnostic scaffolds, CONSORT 2025 for trial results, SPIRIT 2025 for protocols, ICH E3 for CSRs, and ICH E2A/E2B(R3)/E2D(R1) for safety reporting.
  • Generates blank, fail-closed JSON templates from assets/ and requires every populated field to trace back to a verified source-fact ID in a provenance manifest.
  • Runs dependency-free, offline Python scripts to check CARE structure, trial-report structure, aggregate adverse-event tables, terminology schemas, de-identification process documentation, traceability, and internal consistency.
  • Hard-blocks diagnosis, treatment or dosing advice, image/lab interpretation, causality or reportability decisions, signing, filing, and any use of real PHI; every output keeps a "DRAFT — not for clinical use or submission" banner.

Who it's for

  • Medical writers and researchers preparing case reports or journal manuscripts
  • Clinical research and regulatory staff scaffolding trial results reports, protocol reporting checks, or CSR drafts
  • Pharmacovigilance and data teams assembling aggregate safety tables and de-identification documentation

Examples

  1. Run python3 scripts/generate_report_template.py --type case-report --output ./case-report-draft.json, populate only verified facts, then run validate_case_report.py to surface missing CARE items.
  2. Feed an aggregate AE CSV plus metadata to format_adverse_events.py to produce a Markdown table that states denominators and missingness explicitly.
  3. Check a randomized-trial manuscript skeleton against CONSORT 2025, then run provenance_validator.py and consistency_checker.py before handing off to statistical and safety reviewers.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/clinical-reports/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/clinical-reports folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/clinical-reports/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/clinical-reports ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r scientific-agent-skills/skills/clinical-reports ~/.claude/skills/
  5. Confirm Python 3.11+ is available for the optional scripts: python3 --version (no extra packages needed).
  6. Restart Claude Code and try a prompt like "Create a CARE-compliant case report draft structure."
  7. Use only synthetic, de-identified, or aggregate data with a verified source-fact manifest — never real patient records — and route every draft to qualified reviewers.
View source on GitHub ↗License: MIT