Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Clinical Reports Drafting Skill

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

Docs & OfficeAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Produces draft structures — not finished documents — for clinical case reports, radiology/pathology/laboratory report scaffolds, randomized-trial results and protocol reports, Clinical Study Reports, and aggregate safety tables.

  • Routes each artifact to the right official guidance: CARE 2013, CONSORT 2025, SPIRIT 2025, ICH E3/E2A/E2B(R3)/E2D(R1), ACR, CAP protocols, CLIA 42 CFR 493.1291
  • Builds a source-fact provenance manifest so every populated field maps to a verified fact ID; unsupported fields stay null
  • Ships offline, standard-library-only validators: CARE structure, trial-report structure, aggregate AE tables, terminology schema, de-identification process docs, provenance and consistency checks
  • Keeps a persistent "DRAFT — NOT FOR CLINICAL USE" banner on every artifact

Hard boundaries: no diagnosis, dosing, triage, image/specimen/lab interpretation, causality or seriousness judgments, no real PHI, no external API or model calls.

Who it's for

  • Clinical researchers preparing a case report for journal submission
  • Trial teams pre-checking CONSORT/SPIRIT item coverage
  • CRO and pharma medical writers standardizing CSR skeletons and aggregate safety tables
  • Research operations staff documenting de-identification processes and traceability

Examples

  1. Case report draft: run generate_report_template.py --type case-report, populate only verified fields, then validate_case_report.py to surface missing CARE items.
  2. Trial manuscript audit: feed your manifest to validate_trial_report.py to structurally check the 30 minimum CONSORT 2025 items before internal review.
  3. Aggregate AE table: pass a de-identified aggregate CSV to format_adverse_events.py to emit a Markdown table with explicit denominators and missingness (never a reportability decision).

· · · Install guide · · ·

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 this skill only: cp -r scientific-agent-skills/skills/clinical-reports ~/.claude/skills/
  5. Verify Python: python3 --version (3.11+ needed for the optional scripts; no extra packages required).
  6. Restart Claude Code and try: "Use the clinical-reports skill to scaffold a CARE-based case report template."
  7. Only supply synthetic, de-identified, or aggregate data, and route every draft to the qualified clinical, statistical, safety, and privacy reviewers before any use.
View source on GitHub ↗License: MIT