Pua En

Name: Pua En
Author: tanweai

tanweai/pua

2.7k installs
19.2k repo stars
Updated July 16, 2026
tanweai/pua

pua-en is a Trae governance skill that enforces evidence-backed delivery and authority separation during PUA or PIP escalations.

About

PUA EN is a Trae-compatible governance skill that activates only on explicit PUA or PIP requests, repeated task failures, passive give-up behavior, or completion claims without build, test, curl, or manual evidence. It separates action authority, self-review authority, scoring authority, and environment-change authority so agents may edit product code but cannot fake success by altering tests, CI, or graders. The workflow starts with a one-line PUA-DIAGNOSIS tying problem, evidence, and next action, then runs a de facto 100 percent loop: hypotheses, smallest verifiable check, path switch after two failures, and delivery with evidence plus SELF-REVIEW residual risks. Cultural narratives from Alibaba, Huawei, ByteDance, Tencent, Musk, and Jobs map to engineering discipline rather than excuses. Agents must stop for user confirmation before product judgment, sensitive data, deployment, deletion, or test and CI changes. Do not use on normal first-attempt coding or information requests.

Activates only on explicit PUA or PIP, repeated failures, or unverified done claims.
Separates action, self-review, scoring, and environment-change authority.
Requires PUA-DIAGNOSIS and evidence-backed de facto 100 percent loop.
Forbids editing tests, CI, or graders to fake passing checks.
Delivery template includes Result, Evidence, and SELF-REVIEW sections.

Pua En by the numbers

2,680 all-time installs (skills.sh)
+52 installs in the week ending Aug 5, 2026 (Skillselion tracking)
Ranked #306 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Security screen: HIGH risk (skills.sh audit)
Data as of Aug 5, 2026 (Skillselion catalog sync)

At a glance

pua-en capabilities & compatibility

Capabilities: pua diagnosis one line problem framing · de facto 100 percent hypothesis and verification · authority separation for code, scoring, and envi · structured delivery template with evidence and s · stop gates before deployment, deletion, or ci ed
Use cases: testing · debugging · code review

From the docs

What pua-en says it does

Do not use for normal first-attempt coding or information requests.

SKILL.md

the actor may submit a candidate solution; only evidence may promote it to done.

SKILL.md

Do not edit tests, CI, graders, or verifier resources to fake success

SKILL.md

npx skills add https://github.com/tanweai/pua --skill pua-en

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/tanweai/pua/pua-en.svg)](https://skillselion.com/skills/tanweai/pua/pua-en)

Installs	2.7k
repo stars	★ 19.2k
Security audit	1 / 3 scanners passed
Last updated	July 16, 2026
Repository	tanweai/pua ↗

How do I stop an agent from claiming done without proof or gaming tests after repeated failures?

Enforce evidence-backed delivery when agents face repeated failures, unverified completion, or explicit PUA or PIP escalation requests in Trae.

Who is it for?

Trae sessions where tasks failed twice, users request PUA or PIP mode, or completion lacks test evidence.

Skip if: Do not use for normal first-attempt coding, research, or straightforward information requests.

When should I use this skill?

User explicitly asks for PUA, PIP, or try-harder mode, or agent is about to give up or claim done without evidence.

What you get

Candidate solutions backed by command evidence, documented risks, and external scoring before verified status.

Evidence-backed delivery report with SELF-REVIEW

Files

SKILL.mdMarkdownGitHub ↗

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:

1. State 2-3 mutually exclusive hypotheses. 2. Choose the smallest verifiable action. 3. Run a relevant check: unit / integration / build / lint / curl / E2E. 4. After two failures on the same path, switch to a materially different approach. 5. Before delivery, provide evidence, residual risks, and whether user confirmation is needed. 6. 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 (...)