pua

by tanweai

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Content Signals

Repo Health

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

Risk Assessment

• Repository contains multi-agent orchestration patterns (agents/pua-action-executor.md, pua-policy-guardian.md, pua-verifier.md, pua-self-reviewer.md) designed to spawn and coordinate multiple AI agents
• Skill definitions across multiple AI platforms (.claude-plugin, .codebuddy-plugin, .codex, .trae, cursor/rules) suggest autonomous capability injection across multiple AI tool ecosystems
• Files named 'pua-action-executor.md' and 'teardown-all.md', 'reap-orphans.md' indicate execution and resource management without explicit human approval gates
• Repository structure includes agent definitions at multiple capability levels (P7, P9, P10 engineers) suggesting privilege escalation patterns
• Plugin manifests and skill definitions across heterogeneous platforms indicate cross-platform agent deployment mechanism
• Command definitions (commands/*.md) for operational control across multiple systems without visible authorization controls