Skill UI

The Phoenix CLI is a powerful tool for debugging complex LLM and agent workflows. It allows users to fetch detailed traces, spans, and sessions, analyze errors, and structure findings using open and axial coding techniques. It is essential for investigating complex LLM failures, building robust failure taxonomies, and guiding the next steps in application evaluation after initial instrumentation.

Continuous file-based planning system for multi-step AI agents. Maintains task_plan.md, findings.md, and progress.md files on disk to preserve planning context across sessions. Includes session recovery and replay capabilities for project planning workflows. Never executes declared Markdown commands. Used for research or work requiring 5+ tool calls.

Persistent file-based planning for multi-step AI agent work. Maintains task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected context. Automatic recovery reads only project planning files. Use for research or work with more than 5 tool calls.

This tool acts as an expert prompt engineer, guiding users through a systematic discovery process to create highly structured, production-ready prompts for AI assistants like GitHub Copilot. It covers defining persona, specifying complex tasks, managing context variables, integrating tools, and enforcing strict output standards, ensuring the resulting prompt is comprehensive and actionable for advanced AI agents.

This micro-prompt guides AI agents to adopt the mindset of an interactive programmer. It emphasizes using the REPL (Read-Eval-Print Loop) for systematic system exploration and modification, treating the system state as the ultimate source of truth. It also reminds the agent to utilize structural editing tools and maintain todo lists, significantly improving the accuracy and efficiency of the development workflow in live coding environments.

Provides advanced control over browser debugging protocols (CDP). Use this skill when the user needs to connect to an external, running Chrome instance, scan local CDP ports, or explicitly launch the browser with a fixed debug port. It is specifically designed for complex automation scenarios where multiple tools or agents need to attach to the browser instance.

Manage scheduled or recurring tasks using qwenpaw cron commands. Supports listing, creating, updating, pausing, and deleting jobs. Specify execution times, schedules, and agent IDs explicitly. Ideal for daily reminders, periodic checks, or automated agent queries at specific intervals.

This skill is designed to manage complex, multi-step tasks by coordinating the efforts of multiple specialized AI agents. It provides structured methods for listing available agents, initiating real-time conversations, submitting complex background tasks (such as data analysis or report generation), tracking task status, and maintaining conversational context using session IDs. It is essential when a core task requires diverse expert knowledge or sequential collaboration.

This guide maps user questions and topics (e.g., configuration, memory, skills, CLI) to specific, relevant documentation paths and source code entry points within the QwenPaw ecosystem. It is designed for built-in QA Agents to eliminate aimless searching, ensuring the agent reads the most accurate files to provide comprehensive and precise answers about the system's features.

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.

A command-line interface for managing skills, agents, extras, plugins, and MCP connection settings. Supports configuration, installation, synchronization, auditing, and troubleshooting across AI tools. Features global and project modes with noninteractive automation capabilities for terminal-based workflow management.

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.