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 "$T/skills/chemical-property-lookup" ~/.claude/skills/freedomintelligence-openclaw-medical-skills-chemical-property-lookup && rm -rf "$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 "$T/skills/chemical-property-lookup" ~/.openclaw/skills/freedomintelligence-openclaw-medical-skills-chemical-property-lookup && rm -rf "$T"
manifest:
skills/chemical-property-lookup/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: chemical-property-lookup description: Compute RDKit-driven molecular properties (MW, logP, TPSA, QED, Lipinski) for a SMILES string to support downstream drug discovery tools. allowed-tools:
- read_file
- run_shell_command
At-a-Glance
- description (10-20 chars): RDKit stats
- keywords: SMILES, RDKit, Lipinski, QED, ADMET
- measurable_outcome: Return a validated property summary (JSON + Lipinski verdict) for each SMILES within 60 seconds of request.
Workflow
- Validate SMILES input; raise explicit errors for invalid syntax.
- Call helpers from
(molecular_tools.py
,summarize_properties
, etc.).check_lipinski - Report MW, logP, TPSA, HBD/HBA, QED, and Lipinski pass/fail with violations.
- Surface any calculation warnings (e.g., aromaticity perception issues).
Guardrails
- Never infer stereochemistry; report as "not provided".
- Log invalid SMILES for manual follow-up.
- Communicate that results are screening heuristics, not definitive ADMET outcomes.
References
plusREADME.md
for function signatures and dependencies.molecular_tools.py