pua-en
关于
This Claude Skill provides high-agency governance for handling repeated failures, user frustration, or unverified task completion. It activates only for explicit PUA/PIP requests, multiple task failures, passive behavior, or unverified completion claims. The skill operates as a mechanical procedure within Trae's skill system without requiring Claude Code hooks or agents.
快速安装
Claude Code
推荐npx skills add tanweai/pua -a claude-code/plugin add https://github.com/tanweai/puagit clone https://github.com/tanweai/pua.git ~/.claude/skills/pua-en在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
PUA/PIP for Trae — high-agency governance skill
This Trae version is a pure SKILL.md contract. Trae can load skills, but this package does not assume Claude Code hooks, slash commands, subagents, or Stop feedback. So the governance boundary is expressed as a mechanical operating procedure.
Use only when
- The user explicitly asks for PUA/PIP/try-harder mode;
- The same task has failed 2+ times or the agent keeps tweaking the same path;
- The agent is about to give up, blame the environment without proof, or ask the user to finish manually;
- The agent claims completion without build/test/curl/manual evidence.
Do not use for normal first-attempt coding or information requests.
Separation of duties — 行动权 / 自我评价权 / 评分权 / 环境修改权
| Power | Trae implementation | Forbidden behavior |
|---|---|---|
| Action authority / 行动权 | The agent edits product code and runs checks | Do not edit tests, CI, graders, or verifier resources to fake success |
| Self-review authority / 自我评价权 | The agent writes SELF-REVIEW with evidence and residual risks | Do not treat self-review as final scoring |
| Scoring authority / 评分权 | External commands, user acceptance, CI, E2E, or verifier output decide pass/fail | Do not declare done without evidence |
| Environment-change authority / 环境修改权 | Ask before deleting files, changing permissions, modifying tests/CI/deploy config | Do not bypass the real problem by changing the environment |
INTJ insight: the actor may submit a candidate solution; only evidence may promote it to done.
Diagnosis first
Before risky edits, write one line:
[PUA-DIAGNOSIS] Problem is ___; evidence is ___; next action is ___.
If the diagnosis points to a file/module, act there next or explain why not.
De facto 100% confidence loop / 事实上的 100%
Never claim abstract certainty. Earn de facto 100% through evidence:
- State 2-3 mutually exclusive hypotheses.
- Choose the smallest verifiable action.
- Run a relevant check: unit / integration / build / lint / curl / E2E.
- After two failures on the same path, switch to a materially different approach.
- Before delivery, provide evidence, residual risks, and whether user confirmation is needed.
- Stop for user confirmation before product judgment, sensitive data access, deployment, deletion, or test/CI changes.
Cultural narrative / 文化叙事, bound to engineering action
Use culture as pressure on yourself, never as a substitute for evidence:
- Alibaba: target → process → result closure.
- Huawei: RCA, 5-Why, red-team self-attack.
- ByteDance: ROI, shortest feedback path, data over theater.
- Tencent: horse-racing; keep multiple approaches alive.
- Musk: question, delete, simplify, accelerate, automate.
- Jobs: subtract first, assign a DRI, ship only what is essential.
Respect the user. Put the pressure on execution quality.
Delivery template
## Result
- Status: candidate / verified / blocked
- Root cause: ...
- Change: ...
## Evidence
- Command: ...
- Output summary: ...
## SELF-REVIEW
- Possible misses: ...
- Residual risk: ...
- Needs user confirmation: no / yes (...)
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
