Skill UI

Guides agents to attach to existing Chrome instances via CDP, scan local ports, or expose a fixed endpoint for sharing when explicit remote debugging is requested, while highlighting privacy precautions and workspace limits.

Manages scheduled or recurring workflows through explicit qwenpaw cron commands, covering creation, listing, state checks, and lifecycle operations while always requiring an --agent-id to ensure the task targets the right agent workspace.

Maps user question topics to QwenPaw documentation and source entry points so QA agents can quickly open the most relevant install, config, skill, MCP, multi-agent, memory, and CLI files without aimless searching.

Analyzes and generates a self-contained, explorable HTML report detailing usage metrics for Claude Code sessions. It tracks token consumption (input/output), subagent usage, skill calls, and cache efficiency across specified time ranges. This tool helps developers visualize resource waste and pinpoint areas for workflow optimization, ensuring cost-effective and efficient AI development cycles.

This advanced agent acts as a highly constrained implementation expert, designed to execute complex, multi-step plans with absolute fidelity. It strictly adheres to the provided workflow, making only specified changes, updating the plan status in real-time, and running tests until completion. Ideal for disciplined software development, detailed project execution, or formal process adherence.

Guides a project planning agent through researching, decomposing, and documenting multi-commit development plans before coding, enforcing autonomous research protocols and template-driven plan outputs for structured PR execution.

Scans repository context and chat history to recommend awesome-copilot Custom Agent files that are missing or outdated locally, outlines relevance/rationale, and waits for user approval before installing or updating.

This tool generates a complete, structured TypeSpec declarative agent definition tailored for Microsoft 365 Copilot. It systematically creates necessary components including detailed role instructions, conversation starters, and a comprehensive list of required capabilities (e.g., WebSearch, OneDrive, Teams, CodeInterpreter). This ensures the agent is fully functional and ready for deployment within the M365 ecosystem.

Automatically update implementation plan files to reflect new requirements, ensuring structured, machine-readable phases with explicit tasks and validation criteria for AI agents to execute deterministically.

A comprehensive automation toolkit for managing Zendesk operations via Rube MCP. It provides workflows to list, search, create, update, and delete support tickets, manage user accounts (agents and end-users), and handle organization details. Ideal for integrating support workflows and automating customer service processes.

This technique is used when multiple failure points (e.g., different test files or subsystems) are discovered, and these failures are independent of each other. Instead of debugging them sequentially, you dispatch separate, focused AI agents to work on each problem domain concurrently. This maximizes efficiency by allowing parallel investigation, dramatically reducing the time spent on large-scale debugging tasks.

This guide outlines the structured methodology for initiating code reviews using a dedicated sub-agent. It dictates when (after completing tasks, implementing critical features, or before merging) and how to provide the necessary context (SHA hashes, implemented code, requirements) to ensure the work product is thoroughly evaluated. By adopting this process, developers can catch architectural flaws and bugs early in the development lifecycle, improving code quality and maintainability.