pua-skill

让 AI 不敢摆烂的高压推进 skill。适用于任务反复失败、同一路径微调、想放弃、建议用户手动处理、没验证就下结论等场景。要求主动排查、换路径、拿证据闭环。

This skill is coherent with a debugging/aggressive-troubleshooting purpose, but it explicitly encourages the agent to read source files, run commands, and include full-source evidence in reports. Before installing or enabling it: (1) avoid using it on private or sensitive repos, (2) require the agent to ask for explicit permission before reading files or running system commands, (3) restrict implicit invocation or disable automatic execution in production agents, (4) review the agents/openai.yaml and any policy settings (allow_implicit_invocation) and change them if you want manual control, and (5) monitor logs and outputs for accidental inclusion of secrets. If you want the behavior but with safer boundaries, ask for explicit limits in the SKILL.md (allowed paths, file types, redaction rules, and an explicit confirmation step before any destructive or wide-ranging action).

Type: OpenClaw Skill Name: pua-skill Version: 1.0.0 The 'pua-skill' bundle is a behavioral meta-prompting tool designed to make the AI agent more persistent and thorough in task execution. It uses 'high-pressure' instructional language (SKILL.md) to discourage the agent from giving up, forcing it to provide evidence-based conclusions and exhaustively search for solutions. There is no evidence of malicious intent, data exfiltration, or unauthorized system access; the instructions focus entirely on improving the quality of technical troubleshooting and verification.