Skill UI

This skill parses complex, free-text clinical trial eligibility criteria from sources like ClinicalTrials.gov into structured, machine-readable rules. It then evaluates these criteria against a comprehensive patient profile (derived from OpenMed data) to determine potential eligibility. The output provides an explainable verdict (eligible, ineligible, or unknown) for every criterion, serving as a critical decision support tool for clinicians and researchers.

Guides users to select a local, on-device Personally Identifiable Information (PII) detection model from a committed registry. It filters models based on language, required runtime environment (e.g., PyTorch, MLX), and size constraints. The process emphasizes building an offline shortlist and mandates rigorous pre-deployment recall validation and performance benchmarking to ensure secure, privacy-preserving deployment.

This gate review forces a transition from vague product direction to a concrete, buildable technical specification. It mandates the creation of architectural diagrams, data flow maps, state machines, and failure mode inventories before a single line of implementation code is written. Essential for complex features with async components or external dependencies.

This utility analyzes code changes within a branch compared to the base branch. It calculates a complexity score, detects scope coherence issues (warning if changes are too large or unrelated), and generates a fully structured Pull Request (PR) draft. It automates the creation of titles, comprehensive descriptions (including checklists and technical details), and even suggests splitting the PR into smaller, manageable units, significantly improving code review quality and efficiency.

This skill manages complex, stateful proof projects as a local-first pipeline. It guides the user through drafting, rigorous verification, and source bookkeeping. It systematically handles proof continuation across runs, maintaining a full audit trail. When local attempts stall, it orchestrates handoffs to external AI models (like GPT Pro) or performs optional deep audits (DeepSeek), ensuring a structured, traceable, and verifiable output suitable for academic or technical submission.

Implements GDPR-compliant pseudonymization for sensitive personal or clinical data from EU residents. Unlike full anonymization, this method creates a reversible mapping key, which must be stored separately and securely. This process allows for controlled re-linkage (e.g., for Subject Access Requests or longitudinal care) while maintaining GDPR Article 4(5) compliance by ensuring the linkage key is kept separate from the working data.

This skill facilitates the crucial grounding step for clinical coding by interacting with external FHIR terminology servers. It supports core operations such as `$validate-code`, `$expand` (for ValueSets), `$lookup`, and `$translate` (ConceptMaps). It ensures that raw text spans are converted into validated, coded `CodeableConcept` resources using industry standards like SNOMED CT, LOINC, and ICD-10, maintaining interoperability.

This skill processes raw mentions of conditions and diagnoses extracted from clinical notes. It performs synonym deduplication, filters out negated or hypothetical mentions, and assigns a structured clinical status (active, resolved, or historical). The output is a clean, reconciled problem list, structured for USCDI Problem or FHIR Condition elements.

A comprehensive assistant designed to analyze existing codebases for adherence to SOLID principles, common code smells, and complexity metrics. It identifies anti-patterns like tight coupling, excessive responsibility, and duplication, providing prioritized, actionable refactoring suggestions to improve code maintainability and quality.

This skill facilitates reversible de-identification (pseudonymization) of clinical text, allowing sensitive Protected Health Information (PHI) to be masked for processing while retaining the ability to restore the original data later under strict authorization. It captures a mapping key and provides a function to re-identify the text, crucial for workflows like GDPR compliance, patient recontact, or auditing. Crucially, the re-identification mapping must be stored separately and securely.

This tool automatically generates comprehensive release notes from git commits. It analyzes version history, categorizes changes (features, fixes, etc.), and outputs three distinct formats: a technical CHANGELOG.md section, a semi-technical PR body, and a user-friendly Slack announcement. It excels at transforming complex technical jargon into accessible messaging for different audiences.

This skill enhances raw clinical entity recognition by assigning three critical axes: Negation, Temporality, and Uncertainty (ConText). It determines the clinical status of a mention (e.g., affirmed, negated, historical, or uncertain), ensuring that basic NER results are transformed into clinically faithful assertions before grounding to standards like FHIR. Essential for accurate problem list generation and differential diagnosis support.