Skill UI

This skill replaces detected Protected Health Information (PHI) in clinical notes with realistic, type-matched synthetic surrogates. Unlike simple redaction, surrogates maintain the natural readability and structure of the text, ensuring the data remains parseable for downstream NLP tasks, QA, or human review. It supports consistent, reproducible fake identities and allows custom identifier generation for proprietary formats.

This skill implements an advanced reference pattern for integrating with Monitoring Control Platform (MCP) servers. It ensures accurate data retrieval by first reading a domain-specific 'gotchas' reference file, mitigating query failures caused by complex server behaviors, pagination limits, or subtle API quirks. It analyzes issue data, groups errors by root cause, and generates a structured, actionable markdown report for improved system health visibility.

This skill generates browser-playable video assets for web pages by acting as an adapter for the OpenRouter API. It manages the entire asynchronous video generation lifecycle, including submitting the job, polling the status, downloading the final MP4 file, and outputting a structured media manifest for web integration. Use this when a local web video asset is required and configuration details are provided.

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.

This skill performs deep 'git archaeology' by cross-referencing commit history, changelogs, and initial summaries. It extracts verified metrics like commit velocity, contributor rankings, and release timelines, generating multiple detailed reports. Use this when building a REX talk and needing factual, data-backed evidence from a source git repository.

This skill generates a comprehensive, structured catalogue of all key concepts found within a talk's summary and timeline. It categorizes each concept and scores its potential for presentation (HIGH/MEDIUM/LOW) to help users identify the strongest narrative angles. The output is designed to serve as a structured inventory, guiding the subsequent positioning and content development stages.

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 skill provides comprehensive tools for creating and refining visual assets. It supports generating entirely new images, artwork, diagrams, or product mockups using advanced AI models. It also facilitates sophisticated image editing, allowing users to preserve, modify, or combine elements from existing visuals turn by turn. Ideal for designers, marketers, and content creators needing high-quality, context-aware visual content.