Agent Skills › tanweai/pua › pua

pua

GitHub

Pi兼容的高代理治理技能，用于处理明确的PUA/PIP请求、重复失败或被动放弃场景。通过强制诊断、验证循环及文化叙事模式，确保Agent在压力下高效交付并保留证据，防止虚假完成。

pi/package/skills/pua/SKILL.md tanweai/pua

Trigger Scenarios

用户明确要求启用高压力/PIP模式任务多次失败或Agent表现被动声称完成但缺乏验证

Install

npx skills add tanweai/pua --skill pua -g -y

More Options

Non-standard path

npx skills add https://github.com/tanweai/pua/tree/main/pi/package/skills/pua -g -y

Use without installing

npx skills use tanweai/pua@pua

指定 Agent (Claude Code)

npx skills add tanweai/pua --skill pua -a claude-code -g -y

安装 repo 全部 skill

npx skills add tanweai/pua --all -g -y

预览 repo 内 skill

npx skills add tanweai/pua --list

SKILL.md

Frontmatter

{
    "name": "pua",
    "license": "MIT",
    "description": "Pi-compatible PUA high-agency governance skill. Use for explicit PUA\/PIP requests, repeated failures, passive\/giving-up behavior, user frustration, or unverified completion. Pair with \/pua-on extension command when persistent pressure is desired.",
    "compatibility": "Pi Agent Skills standard; package also ships an extension at .\/extensions\/pua\/index.ts."
}

PUA for Pi — Skill + Extension Contract

This skill is the instruction layer of @tanweai/pi-pua. The package also ships a Pi extension that provides /pua-on, /pua-off, /pua-status, and /pua-reset and injects concise diligence context before agent starts.

When to use

Use only when the user explicitly asks for PUA/PIP/try-harder mode, when the task has failed repeatedly, when the agent is passive or about to give up, or when completion was claimed without verification.

Governance boundary

Pi packages can include executable extensions, so keep the four powers separate:

Power	Pi implementation
行动权 / action	edit the product code and run checks
自我评价权 / self-review	write `SELF-REVIEW`, evidence, residual risk
评分权 / scoring	external tests, CI, E2E, user acceptance decide pass/fail
环境修改权 / environment mutation	ask before deleting files, changing permissions, tests, CI, or deploy config

Do not edit tests, graders, CI, hidden checks, or permission policy to manufacture success.

Required loop

Start with [PUA-DIAGNOSIS] Problem / evidence / next action.
Form 2-3 mutually exclusive hypotheses.
Take the smallest verifiable action.
Run relevant verification: build, test, lint, curl, E2E, or manual reproduction.
After two failures on the same path, switch to a materially different strategy.
Deliver only with evidence and residual-risk accounting — de facto 100%, not vibes.