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

Clinical Decision-Support Research & Evaluation Artifacts

Builds and validates research-only CDS artifacts—GRADE evidence profiles, aggregate cohort tables, survival plans, model/biomarker evaluations, and de-identification checklists—with a hard no-patient-care boundary.

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

What it does

  • Drafts and validates research, evaluation, and governance documentation for clinical decision-support work.
  • Pairs each need with a JSON template and a dependency-free Python checker: intended-use statements, GRADE evidence profiles, aggregate model/biomarker evaluation, aggregate cohort tables, survival analysis plans, decision-logic traceability matrices, and de-identification checklists.
  • Enforces a required artifact header (purpose, intended users, limitations, human-review roles, citations, monitoring/change control, and a visible "Not for patient care" statement).
  • Applies a strict data gate: aggregate or synthetic input only, no patient rows, no identifiers, no network calls, no API keys.
  • Refuses diagnosis, treatment recommendations, dosing, triage, and any live clinical operation, routing such requests to licensed professionals.

Who it's for

  • Clinical researchers, biostatisticians, and epidemiologists
  • Teams validating medical AI models or biomarkers who need transparent, reviewable documentation
  • Regulatory/quality staff assembling governance, traceability, and change-control records
  • Not for anyone building an actual bedside or point-of-care tool—the skill explicitly refuses that.

Examples

  1. GRADE evidence profile: fill risk of bias, inconsistency, indirectness, and source IDs per outcome, then run evidence_profile_check.py to catch missing judgments or broken citation links (it never computes certainty for you).
  2. Aggregate model evaluation: supply confusion-matrix counts and calibration bins to generate a report with Wilson intervals, subgroup differences, and explicit small-cell suppression.
  3. Cohort table + privacy review: set a minimum cell threshold, generate the aggregate shell with primary and complementary suppression, then use the de-identification checklist to escalate free text, dates, and rare combinations.
  4. Survival plan review: verify time zero, competing events, censoring, estimand, horizon, and proportional-hazards checks are pre-specified via survival_plan_validator.py.

· · · 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-decision-support/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-decision-support folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/clinical-decision-support/.
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-decision-support ~/.claude/skills/

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

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Confirm Python 3.11+ is available: python3 --version.
  3. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  4. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/clinical-decision-support ~/.claude/skills/
  5. Restart Claude Code and confirm clinical-decision-support appears in your skills list.
  6. Smoke-test the helpers from the skill directory: python3 scripts/validate_cds_artifact.py --help
  7. Optionally run the bundled tests: python3 -m unittest discover -s tests/clinical-decision-support -p 'test_*.py'
  8. When using it, feed only synthetic or aggregate data—never patient-level records.
View source on GitHub ↗License: MIT