Skill UI

This utility provides programmatic access to Granola meeting data, enabling developers to build automated post-meeting workflows. Users can read meeting notes from the local cache, integrate with MCP servers for AI context, automatically extract action items and assignees, and sync outcomes directly into coding tasks, project documentation, or issue trackers like GitHub. Ideal for automating the development lifecycle from meeting insights.

Guides Claude Code plugin authors through creating event-driven hooks that validate tool usage, react to outcomes, and gate completion with prompt-based or command hooks, covering PreToolUse, PostToolUse, Stop, Session events, and session context loading.

This skill provides a rigorous framework for tackling complex software development tasks. It guides users to break down large features, refactoring efforts, or bug fixes into small, actionable, and independently verifiable steps. By focusing on clear outcomes, dependencies, and specific verification criteria, it ensures that the implementation process is structured, manageable, and traceable from start to finish.

A comprehensive workflow designed for advanced voice agent and telephony operations using Retell AI. This tool facilitates complex call management, including running outbound campaigns, handling call transfers, and managing concurrent calls. Users can list call details, retrieve high-fidelity recordings, and access full transcripts to analyze communication outcomes.

Tracks and runs regression suites, automating execution of critical tests and analyzing outcomes so Claude highlights failures, flaky checks, and stability impacts before deployments.

Automatically gather Playwright test outcomes, highlight failures/flakies, and deliver summaries (Markdown, Slack, TestRail, HTML) aligned with existing workflows for quick triage.

This skill manages comprehensive software development life cycle operations—including issue triage, PR reviews, version releases, bug fixing, and marketing content generation. It operates using a parallel "agent army" of dynamic agents (10-20 per task), requiring the user to adopt an Engineering Manager (EM) mindset. Key principles involve rigorous citation checking (anti-hallucination) and applying multiple roles (Product Owner, Open Source Contributor, Architect) simultaneously to ensure robust, safe, and user-centric outcomes across all platforms.

Conducts a multistep preflight validation for Azure Bicep deployments, covering syntax checks, what-if previews, permission verification, and report generation so teams can confidently run azd or az deployments with known outcomes.

Catalogs 42 cloud-agnostic design patterns that architects can apply when designing, reviewing, or operating distributed systems to boost reliability, performance, messaging, security, and deployment outcomes.

This skill guides comprehensive website exploration using Playwright MCP for robust testing. It involves navigating a specified URL, identifying and simulating 3-5 core user flows, meticulously documenting user interactions, relevant UI locators, and expected outcomes. Upon completion, the skill summarizes findings and generates detailed, actionable test cases, ensuring thorough coverage of the application's functionality.

This module provides essential GraphQL response abstractions and helper types. It includes standardized structures for handling various API outcomes, such as general success responses, list data, common errors, and specific security statuses (e.g., Not Found, Not Authorized). Using these abstractions ensures that API interactions are robust, predictable, and adhere to consistent patterns.

A comprehensive guide detailing the multi-stage, double-anonymous review process used at major academic conferences like OOPSLA. It explains the four possible outcomes (Accept, Minor/Major Revision, Reject), the mechanics of 'round-hopping' between submission volumes, and provides strategic advice on how to write author responses and manage revision expectations to maximize publication chances.