install
source · Clone the upstream repo
git clone https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/precision-oncology-agent" ~/.claude/skills/freedomintelligence-openclaw-medical-skills-precision-oncology-agent && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/precision-oncology-agent" ~/.openclaw/skills/freedomintelligence-openclaw-medical-skills-precision-oncology-agent && rm -rf "$T"
manifest:
skills/precision-oncology-agent/SKILL.mdsource content
<!--
# COPYRIGHT NOTICE
# This file is part of the "Universal Biomedical Skills" project.
# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
# All Rights Reserved.
#
# This code is proprietary and confidential.
# Unauthorized copying of this file, via any medium is strictly prohibited.
#
# Provenance: Authenticated by MD BABU MIA
-->
name: precision-oncology-agent description: Fuse genomic variants, pathology findings, and clinical context to draft evidence-linked therapy options for tumor board review. allowed-tools:
- read_file
- run_shell_command
At-a-Glance
- description (10-20 chars): Tumor board copilot
- keywords: oncology, genomics, OncoKB, therapy-ranking, evidence
- measurable_outcome: Deliver a ranked therapy list with OncoKB/NCCN citations plus data-gap checklist for every case within 10 minutes of receiving inputs.
Inputs
(hg38 preferred) plus optional CNV/fusion summaries.vcf_path
text for histology/grade/biomarkers.pathology_report
dict capturing tumor type, stage, prior lines, ECOG.clinical_context
Outputs
- Ranked treatment options (approved, off-label, clinical trials) with evidence strength + contraindications.
- Variant interpretation table (pathogenicity, tier, therapy linkage).
- Biomarker summary (TMB, MSI, PD-L1 if provided) and missing-test checklist.
Workflow
- Ingest & normalize: Harmonize gene symbols, genome build, and variant effects.
- Annotate: Query OncoKB/NCCN + internal knowledge for actionability tiers.
- Contextualize: Blend pathology + prior therapy info to filter contraindicated options.
- Recommend: Present therapies ordered by evidence + patient fit; cite sources.
- Gaps: Highlight assays or confirmations still required before treatment.
Guardrails
- No autonomous treatment decisions—flag outputs as advisory.
- Cite evidence rigorously (guideline version, publication).
- Highlight resistance mechanisms and prior exposure conflicts.
References
- See
for detailed workflow plus cited Nature Cancer study.README.md