Digital Twin Discharge Drafter
v0.1.0Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissio...
⭐ 0· 92·0 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
Name and description (discharge summaries, personalized instructions, simulations) align with the provided code and references. The included Python class implements summary generation, simulation, personalization, risk-based plans, and QA checks — all consistent with the stated purpose.
Instruction Scope
SKILL.md instructs only local operations (generate summaries, read local model files, write outputs). It does not ask for unrelated system files or credentials. Minor issues: examples import from scripts.discharge_drafter or call scripts/discharge_drafter.py, but the repository contains scripts/main.py (which defines DischargeDrafter). The SKILL.md and main.py appear truncated in places; main._load_model currently returns an empty dict rather than loading a model file, so model-loading behavior may be incomplete — a functionality concern, not a security inconsistency.
Install Mechanism
No install spec is provided (instruction-only skill with code files bundled). That is lowest-risk from an install perspective. requirements.txt lists small, common Python deps; no remote downloads or archive extraction are performed by an installer here.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The code does not access environment variables or external secrets. This is proportionate to its stated function, which operates on supplied patient data and local model files.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or system-wide settings in the provided files. Autonomous invocation is allowed by default (platform default) and is not, by itself, a concern.
Assessment
This skill appears coherent with its stated purpose, but before installing or using it with real patients: 1) Verify PHI handling and compliance (HIPAA): ensure logs, outputs, and any model files stay on approved infrastructure and are encrypted/authorized. 2) Confirm the model-loading behavior: main._load_model currently returns {} and SKILL.md references a different module name (scripts.discharge_drafter) — fix/test the code to ensure it actually loads and validates local model files and does not call unexpected endpoints. 3) Test with synthetic data first to validate outputs and to ensure no accidental network calls or telemetry exist. 4) Review and pin any runtime dependencies and run a code review for secure handling of files/paths. If you need the skill to integrate with other systems (EHR, messaging), require explicit, minimal credentials and audit those integrations separately.Like a lobster shell, security has layers — review code before you run it.
latestvk97b5fxz9kq4pjn0yada1f560d8376sc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.