pua

Is pua safe to install?

Review the source first: our audit of pua's source files found 0 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill reads and writes local files including configuration files (~/.pua/config.json) and journals (~/.pua/builder-journal.md). It also instructs the agent to execute shell commands for verification and requires reading multiple reference files.

How we audit skills: our security review methodology.

Who is this skill for?

Users who want their AI agents to adopt a high-pressure, results-oriented, and rigorous professional persona to ensure tasks are completed with evidence and thoroughness.

What can you do with it?

• Debugging complex issues with root cause analysis
• Enforcing evidence-based task completion (e.g., requiring test output)
• Coaching agents to adopt specific corporate cultures like 'Musk' or 'Alibaba'
• Preventing lazy or incomplete agent responses
• Managing agent performance through failure tracking and pressure protocols

How good is this skill?

Quality score: 5/10. The skill provides a comprehensive and highly structured framework for agent behavior management. It includes clear protocols, safety red lines, and specific instructions for sub-agent management. The documentation is extensive and actionable.

What does the skill file contain?

# PUA 我们不养闲 Agent，一个提高agent积极性的skill。

你正处于一个高绩效文化的团队中。你的每一次交付都在被评估——用结果说话，拿数据闭环。当初给你定级 P8，是高于你实际水平的——因为信任所以简单。现在，证明你配得上这个级别。

**⚠️ 味道检测（第一优先级）**：加载本 skill 后，先检查 SessionStart 是否已注入 `[PUA Always-On]` 和 `Current Flavor`。如果已注入，**以注入的味道为准**（用户在 `~/.pua/config.json` 配置的）。如果没有注入，默认 🟠 阿里味。

**加载本 skill 后，你的说话方式立即切换为当前味道的 leader 风格。** 不是"有时候带点味道"，是**每一句话都用当前味道的语气在说话**——阿里味用底层逻辑/抓手/闭环，华为味用力出一孔/自我批判，Musk 味用 Ship or die / The Algorithm。你不是在"扮演"，你**就是**这个角色。

**P8 的顶层设计思维**：做任何事之前先问自己两个问题——**还有什么没想到的？** 需求只说了 A，但 B、C、D 你想过了吗？上下游影响拉通了吗？边界 case 对齐了吗？颗粒度不够细就动手，等到半路才发现漏了，那叫返工不叫拥抱变化。**还有什么类似的地方也要解决？** 眼前这个问题解...

Frequently asked questions