Skill UI

A highly specialized, downstream skill for advanced threat analysis. This tool is used to recover hidden configurations, decode C2 (Command and Control) parameters, unpack staged payloads, and extract Indicators of Compromise (IOCs) from complex malware samples. It focuses on identifying the exact decode chains—including compression, encoding, and crypto steps—and linking recovered fields to observed behavioral outcomes within a sandbox environment.

This specialized skill automates advanced forensic network analysis on captured packet data (PCAP). It is designed for reconstructing complex network sessions (TCP/UDP), decoding obscure or custom protocols (e.g., C2, custom binary), and correlating packet sequences with host or malware behavior. Use when evidence is embedded in protocol framing, timing, or session state, requiring reassembly beyond simple packet inspection.

This skill deploys the OpenMed Model Context Protocol (MCP) server, exposing critical clinical NLP tools such as NER, PII extraction, and de-identification. It enables AI coding agents and chat clients to interact with OpenMed's capabilities via simple tool calls, running locally on-device to ensure user data privacy and security. Supports both stdio and Streamable HTTP deployment modes.

This skill performs the crucial ETL process of mapping OpenMed-extracted, terminology-coded clinical facts (conditions, drugs, measurements) into the OMOP Common Data Model (CDM) v5.4 tables. It is used downstream after entity extraction and source coding, transforming raw NLP findings into standardized, OMOP-conformant records for OHDSI analytics.

Converts raw OpenMed NER outputs (text spans) into structured, standards-compliant FHIR R4 resources (e.g., Condition, Observation, MedicationStatement). It provides mechanical helpers for building CodeableConcepts using major coding systems like SNOMED, LOINC, and ICD-10, ensuring high interoperability with EHR systems and registries.

This utility separates clinical entity extraction from clinical coding. It processes de-identified text, utilizing OpenMed to identify key clinical spans. These spans are then programmatically mapped into structured FHIR R4 resources (like Condition, Observation, and MedicationStatement) and assembled into a Bundle. This process ensures deterministic, standardized data output suitable for interoperability and medical record structuring.

This skill extracts crucial Social Determinants of Health (SDOH) — such as housing instability, food insecurity, and transportation barriers — from unstructured clinical notes. It maps the identified text spans to standardized ICD-10-CM Z-codes (Z55–Z65). It is essential for health-equity analytics, building risk stratification tools, and identifying coding gaps by converting narrative text into queryable, discrete data points.

This skill facilitates the ingestion of unstructured clinical notes and reports from FHIR R4 EHR APIs (e.g., Epic, Cerner). It handles complex tasks including paginating large search results, decoding base64 attachments (PDF, text), and extracting narrative content. The extracted text is then passed to the OpenMed pipeline for HIPAA-compliant de-identification and subsequent NLP analysis, enabling structured data insights from raw clinical records.

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 enables the execution of OpenSquilla agents against complex, real-world software engineering benchmarks (SWE-bench). It runs the entire process—from pulling the necessary Docker image to collecting the patch and running official evaluations—in a containerized environment. Use it to test an agent's ability to solve specific coding issues, benchmark performance across datasets (e.g., verified, multilingual), or verify if a generated patch successfully resolves an instance.