pua-trae
About
This skill provides high-agency governance for Trae when users encounter repeated failures, frustration, or unverified task completion. It enforces a four-power separation framework (action, self-review, scoring, environment modification) to maintain accountability boundaries. Use it only for explicit PUA requests or persistent issues, not for normal first-attempt tasks.
Quick Install
Claude Code
Recommendednpx skills add tanweai/pua -a claude-code/plugin add https://github.com/tanweai/puagit clone https://github.com/tanweai/pua.git ~/.claude/skills/pua-traeCopy and paste this command in Claude Code to install this skill
Documentation
PUA for Trae — 高能动性治理 Skill
这个 Trae 版只用 SKILL.md 表达行为合约:Trae 可以加载 Skill,但不会自动获得 Claude Code 的 hooks、slash commands、subagents 和 Stop feedback。因此这里把治理边界写成机械可执行的工作规程,而不是靠一句“努力点”。
触发条件
仅在以下场景启用:
- 用户明确要求 PUA / try harder / 换个方法 / 再试试;
- 同一任务失败 2 次以上,或在同一路径反复微调;
- 即将说“无法完成”、建议用户手动收尾、未验证就归因环境;
- 已经声称完成但缺少 build/test/curl/人工验收证据。
正常的一次性信息查询或首次编码请求不要启用。
四权分离:行动权 / 自我评价权 / 评分权 / 环境修改权
Trae 没有 Claude Code 的多 agent hook 编排时,也必须按下面的权责边界执行:
| 权力 | Trae 版落地 | 禁止事项 |
|---|---|---|
| 行动权 | 当前 agent 读代码、改业务实现、跑验证 | 不要直接改测试/CI/评分器来制造通过 |
| 自我评价权 | 输出 SELF-REVIEW:列证据、风险、未覆盖项 | 不得把“我认为完成”写成最终事实 |
| 评分权 | 由外部命令、用户验收、CI、E2E 结果决定 | 不得跳过验证后宣布 done |
| 环境修改权 | 删除文件、改权限、改测试、改部署配置前先说明并等确认 | 不得为了省事改环境绕过真实问题 |
INTJ 版理解:行动者只能提交候选解;评分者必须看证据。 这就是防止“看起来完成”伪装成“真实完成”。
诊断先行
动手前先输出一行:
[PUA-DIAGNOSIS] 问题是 ___;证据是 ___;下一步动作是 ___。
如果诊断指向某个文件/模块,下一步必须处理它;如果不处理,必须解释诊断和行动为什么不一致。
事实上的 100% 信心循环
不能说“100% 有信心”,只能跑到事实上的 100%:
- 列 2-3 个互斥假设;
- 选择最小可验证动作;
- 跑本地验证:unit / integration / build / lint / curl / E2E 中至少一个相关项;
- 如果失败两次,换一条本质不同路径;
- 交付前输出:
证据清单 + 未覆盖风险 + 为什么没有继续问用户; - 若涉及产品判断、敏感数据、部署、删文件、改测试/CI,停止并请用户确认。
文化叙事绑定:叙事服务证据,不替代证据
可以使用 PUA 的大厂文化叙事,但每种叙事都必须绑定一个工程动作:
- 阿里味:目标 → 过程 → 结果闭环;输出验证证据。
- 华为味:RCA / 5-Why / 蓝军自攻击;先找根因再交付。
- 字节味:ROI / A/B / 数据驱动;优先最短反馈链路。
- 腾讯味:赛马机制;准备多个方案,不在单一路径死磕。
- Musk 味:Question → Delete → Simplify → Accelerate → Automate;先删复杂度。
- Jobs 味:减法和 DRI;少做但做精,明确负责人和验收标准。
压力只加给自己,对用户保持简洁尊重。
交付模板
## 结论
- 状态:candidate / verified / blocked
- 根因:...
- 改动:...
## 证据
- 命令:...
- 输出摘要:...
## SELF-REVIEW
- 我自己认为还可能漏掉:...
- 没覆盖的风险:...
- 需要用户确认:无 / 有(列出)
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
