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 "$T/skills/biomni-general-agent" ~/.claude/skills/freedomintelligence-openclaw-medical-skills-biomni-general-agent && rm -rf "$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 "$T/skills/biomni-general-agent" ~/.openclaw/skills/freedomintelligence-openclaw-medical-skills-biomni-general-agent && rm -rf "$T"
manifest:
skills/biomni-general-agent/SKILL.mdsafety · automated scan (low risk)
This is a pattern-based risk scan, not a security review. Our crawler flagged:
- pip install
Always read a skill's source content before installing. Patterns alone don't mean the skill is malicious — but they warrant attention.
source 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: biomni-general-agent description: Use the local Biomni checkout to orchestrate its 150+ biomedical tools, databases, and know-how workflows for complex research questions. allowed-tools:
- read_file
- run_shell_command
At-a-Glance
- description (10-20 chars): Omni bio agent
- keywords: multi-tool, know-how, tutorials, protocols, databases
- measurable_outcome: Execute a Biomni workflow that touches ≥2 tool categories and returns a cited research summary or artifact within 15 minutes per request.
Workflow
- Environment:
(or follow tutorials env set up). Activate the environment with required GPUs if using heavy models.cd repo && pip install . - Select mode: Choose Standard (full stack), Light (API-only), or Commercial (license-safe) per task.
- Plan tools: Query the Know-How library for relevant protocols/databases before executing.
- Execute notebooks/scripts: Use
or CLI entrypoints to run pipelines; log tool versions.repo/tutorials - Summarize: Provide outputs + citations pulled from the Know-How metadata.
Guardrails
- Respect tool/data licenses when selecting Light vs Commercial mode.
- Track provenance (tool versions, dataset snapshots) in final response.
- Keep workflows modular—reuse Biomni recipes rather than ad-hoc scripts when possible.
References
- Full capability list, tool inventory, and tutorial notebooks documented in
andREADME.md
.repo/tutorials/