Lipinski Rule Filter
v1.0.0Filter compound libraries based on Lipinski's Rule of Five for drug-likeness.
⭐ 0· 58·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name, description, code (scripts/main.py), and reference material all align: this is a Lipinski Rule of Five filtering tool that uses RDKit. Minor mismatch: SKILL.md's 'Prerequisites' section states 'No additional Python packages required' but requirements.txt lists rdkit-pypi and the script clearly depends on RDKit (the script warns when RDKit is missing). This is likely an authoring omission rather than malicious.
Instruction Scope
SKILL.md instructs the agent to run the packaged script and validate inputs; the script operates only on local input files and writes local outputs. The instructions and implementation stay within the described scope. Note: SKILL.md mentions editing an in-file CONFIG block and strong path validation guidance, but the packaged script does not expose a CONFIG block and performs only basic Path.exists checks (no explicit ../ sanitization), so callers should validate paths themselves.
Install Mechanism
There is no install spec (instruction-only), which minimizes install risk. The package includes requirements.txt listing rdkit-pypi, and the script requires RDKit to be useful. The skill does not attempt to download or execute remote installers; you will need to install RDKit locally (pip install rdkit-pypi or use a platform-appropriate RDKit package).
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportional to its purpose. The only external dependency is RDKit (a normal cheminformatics library).
Persistence & Privilege
The skill does not request permanent/always-on presence (always: false) and does not modify other skills or global agent settings. It runs as a self-contained script that reads/writes files in the workspace when invoked.
Assessment
This package appears coherent and implements a Lipinski Rule of Five filter. Before installing or running: (1) Install RDKit (requirements.txt lists rdkit-pypi); the script will be mostly nonfunctional without it. (2) Review input/output paths you provide — the script will read arbitrary filesystem paths the invoking user can access and will write output files in the same directory; the script does basic existence checks but does not enforce path sandboxing. (3) For large libraries, test performance on a small sample first. (4) The SKILL.md contains a small authoring inconsistency (it claims no prerequisites) — do not rely on that; assume RDKit is required. (5) Run the included audit/test commands (python -m py_compile scripts/main.py; python scripts/main.py --help) in a sandboxed environment if you have any doubt.Like a lobster shell, security has layers — review code before you run it.
latestvk97ejt1d0qqpp0bd5he78fmfbn83nrrc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.