Medication Reconciliation
v1.0.0Compare patient pre-admission medication lists with inpatient orders to automatically identify omitted or duplicated medications and improve medication safety.
⭐ 0· 59·0 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 match the included Python implementation: the script loads pre-admission and inpatient JSON medication lists, performs fuzzy/synonym matching, flags dose changes, duplicates, and critical drug-class warnings, and emits a structured report. No unrelated binaries, environment variables, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to prompt for PHI de-identification or authorization, validate inputs, run scripts/main.py, and produce a reconciliation report. The documented workflow and scope boundaries align with the code. Note: the script prints patient_id/name and includes them in the report—this is expected but means PHI can appear in outputs if not de-identified.
Install Mechanism
There is no install spec (instruction-only skill with bundled code). requirements.txt lists 'dataclasses' and 'difflib', both of which are standard-library/backport-related items for Python; no external downloads or installers are invoked. This is low-risk but slightly odd (listing standard modules) — nothing is fetched from network.
Credentials
The skill declares no required environment variables, credentials, or config paths. The code accesses only local JSON files supplied as arguments and writes a local report. Requested privileges are proportional to the task. Users should still avoid supplying PHI unless authorized.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not modify other skills or system settings. It runs as a standalone script and produces local files/STDOUT only.
Assessment
This package appears coherent and low-risk for its stated purpose, but follow these precautions before installing or running it:
- Only run with de-identified data or with explicit authorization (SKILL.md requires this). The script includes patient_id and patient_name in the report and prints counts to stdout.
- Run the script in a controlled/sandboxed environment (not on a public machine) when testing to avoid accidental PHI leakage to logs or shared directories.
- Review the full scripts/main.py before use (the included code uses only local file I/O and standard libraries; no network calls were found). If you will run it in production against real PHI, have your compliance/security team review and approve.
- The requirements.txt lists standard modules; ensure your Python runtime is appropriate (Python version compatibility) and that you install only trusted dependencies if you adapt the skill.
- If you need integration with an EHR or live pharmacy system, do not use this skill directly—its SKILL.md explicitly states it does not access live systems and it is not designed for automated EHR integration.Like a lobster shell, security has layers — review code before you run it.
latestvk977jnz59t8kcs11535at5b3s183q8aj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.