Pua Trae
tanweai/puaThis set of rules helps an AI assistant handle difficult tasks. It activates when a task fails multiple times or the user shows frustration. The assistant must diagnose the problem, try different approaches, and prove its work with real tests. It never claims success without solid evidence. This ensures the assistant does not give up too early and delivers verified results.
Developers who build AI agents benefit from these rules. The rules prevent the agent from stopping short or skipping verification. They push the agent to keep trying and to show clear proof of completion.
The rules also include cultural narratives for motivation. Each narrative must link to a specific engineering action. This keeps the focus on practical steps rather than empty words.
Add Pua Trae skill to your workflow
Global
mkdir -p ~/.claude/skills/pua-traeProject
mkdir -p .claude/skills/pua-traeSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly