pua

Enforce proactive ownership and escalation frameworks for AI agent task completion.

1|2|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Zhouua/TicketGrabbingPlatform --skill pua-zhouua
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pua
Source: https://github.com/Zhouua/TicketGrabbingPlatform/tree/main/.agents/skills/pua
Command: npx skills add https://github.com/Zhouua/TicketGrabbingPlatform --skill pua-zhouua

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps AI agents avoid stagnation by enforcing a structured, end-to-end ownership mindset and proactivity framework.

Core Features & Use Cases

  • Proactive ownership: prevents waiting for instructions by driving end-to-end task completion.
  • Failure-mode awareness: applies tiered proactivity levels to stall, blame, and quality issues.
  • Evidence-driven delivery: provides clear, verifiable outputs and escalation templates for complex tasks.
  • Use Case: when an AI hits a dead end, apply the PUA rules to drive complete fixes with traceable evidence.

Quick Start

Enable the PUA engine and begin solving tasks end-to-end with proactive ownership and evidence-driven verification.

Frequently Asked Questions about pua

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stop my AI agent from stalling and waiting for instructions during complex tasks?

To stop AI agent stalling, apply an end-to-end ownership framework that enforces proactive task completion. This provides structured proactivity levels and escalation templates to ensure the AI drives deliverables forward without deferring decisions.

What is end-to-end ownership for AI workflows and when do I need it?

End-to-end ownership for AI workflows is a proactivity framework preventing AI agents from delaying decisions. You need it when tasks like coding, debugging, research, writing, or planning hit dead ends and require complete, evidence-driven fixes.

How do I ensure AI agents provide verifiable outputs when they hit a dead end?

To ensure verifiable outputs from AI agents at a dead end, apply structured failure-mode awareness and escalation templates. This enforces evidence-driven delivery, driving complete fixes with traceable evidence rather than allowing the agent to stall.

Does the proactivity framework work for both coding and research tasks?

Yes, the proactivity framework works across coding, debugging, research, writing, and planning tasks. It applies tiered proactivity levels to address stall, blame, and quality issues, ensuring end-to-end ownership regardless of the specific task type.

What are the limitations of using a proactivity mindset framework for AI agents?

The proactivity mindset framework relies on structured rules and escalation templates to enforce ownership, meaning its effectiveness is limited by the AI's ability to interpret these iron laws. It requires clear task definitions to successfully drive evidence-driven deliverables.