ADME Property Predictor
v1.0.0Analyze data with `adme-property-predictor` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.
⭐ 0· 22·0 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 skill claims to predict ADME properties and includes a Python implementation using RDKit and descriptor calculations; the declared dependencies (rdkit) and the presence of scripts/main.py align with that purpose.
Instruction Scope
SKILL.md instructs the agent to validate inputs, run python -m py_compile and execute scripts/main.py — these remain within the stated ADME analysis scope. Minor inconsistency: an example in SKILL.md shows importing from scripts.adme_predictor while the provided code lives in scripts/main.py (documentation out-of-sync).
Install Mechanism
No install spec is provided (instruction-only), so nothing is automatically downloaded or written. However RDKit is required at runtime (requirements.txt lists rdkit); RDKit can be non-trivial to install and should be installed in a controlled environment. No remote download URLs or extract steps are present.
Credentials
The skill requests no environment variables, credentials, or config paths. The code does not reference external secrets or network endpoints and thus is proportionate to its stated function.
Persistence & Privilege
The skill does not request always:true, does not declare modifications to other skills or system config, and contains no self-install behavior. It will only run when invoked.
Assessment
This skill appears coherent for ADME prediction, but take these precautions before running: 1) Install and test RDKit in an isolated virtual environment (RDKit can be tricky to install). 2) Run python -m py_compile scripts/main.py to confirm syntax, then inspect scripts/main.py yourself (it is the main implementation). 3) Note the SKILL.md example import mismatch (scripts.adme_predictor vs scripts/main.py) — ensure you call the correct entrypoint. 4) Since the skill source is listed as unknown, avoid feeding proprietary or sensitive compound libraries until you’ve vetted outputs in a sandbox. 5) Verify the license and any provenance you require before using results for critical decisions.Like a lobster shell, security has layers — review code before you run it.
latestvk97eeattksqczdbkdhdk4apg7s8426e9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.