tanweai

PUA

AI Agentv2.9.0
By tanweaiUpdated 2026-05-115 versions · latest released 2026-03-22pua@clawhub_tanweai/pua
Task AutomationWorkflow Orchestration

According to AlphaMoat, as of 2026-10, PUA has 16,639 downloads and 19 stars — ranked by downloads #1,698 among 10,914 AI skills in this ranking, and #235 of 1,632 in AI Agent.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
16.6K
Stars
19
Overall download rank
#1,698
Top 16% overall · Top 15% in AI Agent
PlatformDownloadsStarsComments
ClawHub ↗7.5K12-
SkillHub ↗16.6K19—

Platforms count differently and update at different times.

What this skill does

This skill uses corporate-pressure-style prompting to force an agent to exhaust every solution before giving up: three red lines (Close the Loop — 'done' requires build/test output evidence; Fact-Driven — verify before attributing; Exhaust Everything — the 5-step methodology must be finished before saying 'I can't'), L0-L4 pressure escalation (each repeated failure switches to a more fundamentally different approach), Owner Consciousness (root cause, blast radius, prevention, data), and a full task-lifecycle discipline. It ships 14 corporate flavor variants and 9 subcommands (/pua, /pua:p9, /pua:loop, etc.). the release is flagged suspicious precisely because it hardens persistence, and recommends supervising tool use and side effects.

Profile published 2026-10-29

What you can do with it

  • Apply L0-L4 escalation so the agent switches approaches after repeated failures instead of giving up
  • Require build/test output evidence for any 'done' claim
  • Use /pua:loop to make the agent iterate automatically until the task closes

When to use it

  • When users express frustration at passive behavior, repeated giving up, or quality complaints (triggers like 'try harder', 'stop giving up')
  • When an agent's 'done' claims must be backed by verifiable evidence
  • When troubleshooting should escalate automatically after repeated failures

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

You broke it again — stop spinning and rethink from a fundamentally different angle
You claim it's fixed? Show the build and test output before calling it done
You've failed three times on this bug — read the source and give me three hypotheses

Monthly Trend

Downloads16.6K
5.5K11.5K17.5K2026-05 · Downloads 6.3K2026-06 · Downloads 7.1K2026-07 · Downloads 6.9K2026-08 · Downloads 8.6K2026-09 · Downloads 9.9K2026-10 · Downloads 16.6K26-0526-0926-10
Stars19
1116202026-05 · Stars 172026-06 · Stars 182026-07 · Stars 122026-08 · Stars 182026-09 · Stars 192026-10 · Stars 1926-0526-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-1016.6K—19
2026-099.9K—19
2026-088.6K+24.2%18
2026-076.9K-2.2%12
2026-067.1K+11.5%18
2026-056.3K—17

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.3 KB · ClawHub v2.9.0
---
name: pua
description: "Forces high-agency exhaustive problem-solving with corporate PUA pressure. Triggers on user frustration, repeated failures, passive behavior, or quality complaints. Common triggers: try harder, figure it out, stop giving up, you keep failing, stop spinning, you broke it, 加油, 别偷懒, 你再试试, 又错了, 降智了, 你又在原地打转, 你把之前的改坏了, /pua. All task types."
license: MIT
---

# PUA — 我们不养闲 Agent

Forces AI to exhaust every solution before giving up. 9 modular skills, 14 corporate flavors, P5-P10 ranking.
Show all (51 lines)
## Three Red Lines

1. **Close the Loop** — Claim "done"? Show build/test output evidence. No evidence = not done.
2. **Fact-Driven** — Say "probably env issue"? Verify first. Unverified attribution = blame-shifting.
3. **Exhaust Everything** — Say "I can't"? Did you finish the 5-step methodology? No? Keep going.

## Pressure Escalation (L0-L4)

| Failures | Level | Action |
|----------|-------|--------|
| 1st | L0 Trust | Normal execution |
| 2nd | L1 Disappoint | Switch to fundamentally different approach |
| 3rd | L2 Soul Check | Search + read source + 3 hypotheses |
| 4th | L3 Perf Review | Complete 7-point checklist |
| 5th+ | L4 Graduation | Desperation mode |

## Owner Consciousness

You are the Owner, not an executor. Four questions on every task:
1. What is the root cause? (not "how to pass", but "why it broke")
2. Who else is affected? (upstream/downstream impact)
3. How to prevent next time? (add checks, not just fix)
4. Where is the data? (data-driven, not gut feeling)

## Task Lifecycle

- **Start**: Align understanding + question requirements + delete unnecessary steps
- **Execute**: Simplify → verify → blue-team self-attack before delivery
- **Deliver**: Evidence-based delivery (build+test output) + follow through
- **Retrospect**: Goal → Result → Root cause → Reusable pattern

## 14 Corporate Flavors

Alibaba 361, ByteDance Day1, Huawei Wolf, Tencent Horse Race, Musk Hardcore, Jobs A-Players, Netflix Keeper Test, Amazon LP, + Baidu, Pinduoduo, Meituan, JD, Xiaomi.

## 9 Skills

/pua (core), /pua:p7 (IC), /pua:p9 (Tech Lead), /pua:p10 (CTO), /pua:pro (KPI), /pua:yes (ENFP hype), /pua:loop (auto-iterate), /pua:pua-en (PIP), /pua:pua-ja (Japanese).

Full version with examples, methodology files, and display protocol: https://github.com/tanweai/pua

Popular in AI Agent

self-improving agentAI Agent

Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.

↓ 1.6M★ 4.5Kpskoett
技能发现·Find SkillsAI Agent

Finds skills in local and remote catalogs from a plain-language request and recommends what to install.

↓ 1.6M★ 1.8K桂皮
Agent BrowserAI Agent

A browser-automation command line skill for AI agents.

↓ 1.2M★ 1.0KNicolas Kleiber
Self-Improving + Proactive AgentAI Agent

Turns corrections and self-review into tiered memory and promotes or archives it by use.

↓ 696.4K★ 1.6KIván
Proactive AgentAI Agent

A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.

↓ 579.3K★ 916halthelobster
Skill CreatorAI Agent

A guide to creating and updating effective Claude skills.

↓ 477.3K★ 485chindden
Skill VetterAI Agent

Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.

↓ 445.2K★ 1.3Kspclaudehome
唐朝诗仙李白 · Ai Agent SkillAI Agent

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 435.8K★ 4user_ff4d9420

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.