This skill answers health, nutrition, exercise, sleep and wellness questions using only trusted sources, ranked in tiers, and gives each answer an evidence rating inspired by the GRADE system. A quick mode searches the web in about half a minute, and a deep mode adds more sources. It can optionally add your Apple Health data for context, but the path in the package points to the author's own files, so change it to your own export before using that part. It is research help, not medical advice. You get a sourced answer with a clear rating of how strong the evidence is.
Check healthcare claims against CMS billing rules and NCCI editsThis AWS Labs reasoning skill helps an agent answer questions about healthcare claims billing and spot likely fraud, waste and abuse. It holds reference material on CMS site-of-care codes, post-surgery global periods, modifiers such as 25 and 59, and NCCI code-pair edits, plus patterns like upcoding, unbundling, phantom billing and impossible days. It also helps tell coding errors apart from fraud, and answers lead with a recommendation followed by the specific criteria and caveats. It is meant for claims audit and billing compliance work. Billing rules change, so check the current CMS and NCCI tables before acting on an answer.HealthcareHealthcare claimsBilling compliance
De-identify clinical data with a local script before AI analysisThis skill from Aperivue's medical research collection guides a researcher through removing protected health information from CSV, TSV or Excel files before any AI-assisted analysis. The removal itself happens in a Python script on the researcher's computer that never goes online or calls a model, using patterns for 12 countries and an interactive review in the researcher's own terminal. The agent explains and checks the process but is told never to ask for raw patient data or to read the mapping file of original values. It covers assessment, scanning, review, de-identification and verification, with references for the HIPAA Safe Harbor list and date shifting. Never paste or upload raw patient data to the agent, and check the output before sharing it, since a pattern-based tool can miss identifiers.HealthcareHealthcare dataPrivacy
Convert, read and de-identify DICOM and NIfTI medical imagesAn AWS Labs skill for working with medical image files. It gives an agent ready commands and Python for turning DICOM series into NIfTI with dcm2niix, reading headers and pixels with pydicom, stripping patient details and private tags, loading NIfTI volumes with nibabel and arranging data in the BIDS folder layout. It also covers batch work grouped by series and a decision guide for choosing a de-identification approach. Its de-identification code is a starting point: check the results against your compliance rules, including any text burned into the images, before sharing them.HealthcareDICOMHealthcare
Prepare for a doctor's appointment and weigh the evidenceThis skill helps you get ready for a medical appointment when you ask for it by name. It organizes your symptoms over time, weighs the evidence behind a diagnosis or treatment you're looking into, checks for red flags that need urgent care, and keeps alternative explanations in view. It ends with a structured summary and a list of questions to bring to your clinician. It is not medical advice.Healthcare
Parse, profile and check healthcare claims data for billing anomaliesAn AWS Labs skill that gives an agent copy-ready Python and SQL for healthcare claims data. It parses X12 837 and 835 files into tables, profiles providers' evaluation and management coding against peers, flags outliers and impossible days, checks NCCI code-pair edits, finds duplicate claims and runs a Benford's law test on charges. It is aimed at analysts building claims pipelines or reviewing billing patterns. An outlier it flags is a lead to review, not proof of fraud.HealthcareHealthcare claimsAnalytics
Check a manuscript against reporting guidelinesThis skill audits a medical or scientific manuscript one item at a time against a published reporting checklist or a risk-of-bias tool. It covers 49 instruments, including CONSORT, STROBE, STARD, PRISMA, TRIPOD+AI and QUADAS, picks the right one from the study type or asks when unsure, and marks every item as present, partial or missing with where it was found. It adds cross-checks such as registration timing and PRISMA flow-diagram arithmetic, and it can tell when an older checklist no longer matches the current draft. It is part of a set of medical-research skills built by a physician-researcher.HealthcareMedical researchManuscript review
Check healthcare claims against CMS billing rules and NCCI edits
De-identify clinical data with a local script before AI analysis
Prepare for a doctor's appointment and weigh the evidence