Skill UI

A specialized framework for conducting non-Wi-Fi RF/SDR security research in controlled, authorized laboratory environments. Focuses on passive signal identification, protocol analysis (e.g., remote controls, ADS-B), and feasibility studies. Emphasizes strict legal compliance, requiring analysis to be performed only in shielded labs with explicit authorization, and defaults to receiving-only mode.

This skill structures free-text adverse event narratives into the mandatory ICH E2B(R3) format. It populates critical fields required for regulatory submissions (like FAERS/EudraVigilance), including suspect drugs, reactions (mapped via MedDRA), seriousness criteria, and reaction outcomes. Use it when generating Individual Case Safety Reports (ICSRs) from clinical narratives.

This command inspects the native code execution sandbox environment. It reports on platform compatibility (e.g., bubblewrap, Seatbelt), active security configurations (auto-allow status, filesystem policies, network allowlists), and details recent security violations. Use it to audit the execution environment before running autonomous workflows.

This skill interfaces with the modern v2 REST API of ClinicalTrials.gov, allowing users to search for clinical studies matching specific conditions, interventions, and recruitment statuses. It is essential for building patient-to-trial matching features, generating a corpus of trial records for biomedical NER, or finding open studies for a given diagnosis or drug. It uses cursor pagination and requires no API key.

This tool analyzes SonarCloud quality issues for a specific pull request (PR). It fetches detailed metrics, including severity, issue type, and violation count, and generates a comprehensive, structured report. The output provides an executive summary, identifies top violating files and rules, and delivers a clear, actionable plan to guide developers toward merging high-quality code.

Generates highly accurate, structured summaries from complex clinical notes, such as discharge summaries, SBAR reports, or problem lists. The core function is to anchor every generated claim to a specific source span within the original text, guaranteeing verifiability and eliminating hallucination. Essential for clinical documentation drafting and chart abstraction.

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.

This skill takes validated talk angles and titles to produce a comprehensive, professional presentation package. It generates a detailed 5-act narrative script with embedded speaker notes, a precise slide-by-slide design specification for visual implementation, and a ready-to-use AI prompt (Kimi) for automated slide generation. Ideal for transforming raw ideas into polished, actionable presentations.

This protocol simulates a diverse, anonymous jury of 3 to 5 specialized subagents to reach a committed, non-ambiguous verdict. It is designed to combat cognitive biases like anchoring and groupthink by running blind, independent opinions before structured deliberation. Ideal for high-stakes decisions across product development, architecture, strategy, and vendor choice where a single perspective is insufficient.

This tool leverages an LLM-as-a-Judge agent to thoroughly evaluate staged Git changes before they are committed. It checks for correctness, completeness, and safety issues, providing a detailed verdict (APPROVE, NEEDS_REVIEW, REJECT) and actionable feedback. It is essential for maintaining high code quality, especially in complex or security-sensitive code sections.

This skill validates FHIR R4 resources and Bundles against mandatory US Core profiles (USCDI). It goes beyond mere syntactic checks to ensure that data prepared for submission to major Electronic Health Records (EHRs) like Epic or Cerner meets the required US-specific conformance standards. It detects common data gaps, checks 'must-support' elements, and converts the comprehensive validation report into a standard FHIR OperationOutcome for seamless pipeline integration.

This comprehensive skill allows users to search the web using the DuckDuckGo API, retrieving diverse content including text results, news articles, images, and videos. It supports advanced filtering options such as time range, region, content type (e.g., news, images), and specific media characteristics (e.g., image size, video duration). Ideal for research, fact-checking, academic study, and gathering current web resources.