Skill UI

This skill automatically collects raw activity data (merged PRs, issues, commits, and optional Slack updates) from repositories. It formats this data using predefined templates, runs quality checks, and prepares a structured changelog draft. It can automatically commit the draft to a new branch and open a Pull Request (PR) for review, making it ideal for generating weekly or monthly release notes.

This skill outlines the complete workflow for capturing and structuring meeting notes using Granola. It captures audio, transcribes the content, and intelligently merges live user notes with the full transcript. The output is structured into key sections like Summaries, Decisions, and Action Items. Users can also interact with Granola Chat for post-meeting Q&A, making it an essential tool for professional meeting documentation and follow-up.

This workflow provides an AI-powered platform for immersive conversation practice. It uses advanced language models (like GPT-4o) and real-time speech APIs to simulate real-life scenarios (e.g., ordering food, navigating). Users receive immediate, detailed feedback on pronunciation (phoneme level), grammar corrections, and vocabulary notes, making it an ideal core module for building language fluency and simulating professional tutoring experiences.

Generates professional conference presentation slides from a compiled research paper. This skill produces dual outputs: a polished Beamer LaTeX PDF for high-quality typesetting, and an editable PPTX for flexible adjustments. It supports multiple talk types (Poster, Spotlight, Oral, Invited) and includes detailed guidelines for speaker notes and talk scripting, making it essential for academic researchers preparing for major ML and systems conferences.

This skill provides a seamless workflow for publishing content stored in Obsidian notes to X (Twitter). It intelligently handles both short-form posts (text, images, videos) and rich, long-form articles (X Articles) derived from Markdown. By utilizing a real Chrome browser, it ensures compatibility and bypasses anti-bot detection mechanisms, making it ideal for content creators and knowledge workers who need to automate their social media sharing process from their local knowledge base.

This skill provides comprehensive strategies to optimize resource usage and mitigate rate limits when integrating with the OneNote Graph API. It focuses on reducing the operational 'cost' of making API calls by implementing metadata caching (TTL), utilizing JSON batch requests, and performing delta synchronization instead of full list fetches. Essential for high-volume, stable OneNote enterprise integrations.

A self-hosted, semantic memory service designed for AI agents. It allows agents to save worklogs, decisions, and notes, and recall this knowledge across sessions based on meaning rather than exact keywords. Using pgvector and structured workspaces, it maintains persistent, context-aware knowledge bases, making it ideal for collaborative AI projects.

Transform raw meeting transcripts, call notes, or chat logs (from Zoom, Teams, etc.) into professional, structured summaries. This tool automatically extracts key decisions, identifies open risks, and generates actionable item lists with clear owners and proposed due dates, making outputs ready for immediate sharing.

This skill facilitates structured, bidirectional reading and knowledge synthesis for academic texts, theories, and articles. It forces users to first capture the source material's original intent, before critically mapping its relationships, conflicts, and absorptions against the CrossFrame framework. It ensures structured output with clear source boundaries, making it ideal for deep learning and scholarly work.

Execute arbitrary PySpark or pure Python code directly on Fabric Spark compute using the Livy API. This method creates ephemeral sessions without generating persistent notebook artifacts. It provides full read/write access to lakehouse Delta tables, making it ideal for agent-driven ETL pipelines, quick data transformations, or analyses where session cleanup is critical. Users must manage the session lifecycle (create, run, and delete).

A comprehensive guide on querying data stored in Fabric's OneLake using DuckDB. This skill supports two operational modes: local command line interface (CLI) for ad-hoc analysis, and in-notebook mode for seamless integration within Fabric notebooks. It can read Delta Lake tables and various raw formats (Parquet, CSV, JSON), making it ideal for data exploration, validation, and schema discovery in a read-only fashion.

This template transforms complex, multi-source materials (meeting notes, research, product data, financial feedback) into a single, highly structured, actionable one-page memo. It forces the user to distill the core problem, define a clear recommendation, map out tradeoffs, and list actionable next steps, making it ideal for C-level decision-making.