Skip to content
Back to search

nopua

一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不再撒谎,找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/wuji-labs--nopua/badge.svg)](/listings/wuji-labs--nopua)

HTML

<a href="/listings/wuji-labs--nopua"><img src="/api/listings/wuji-labs--nopua/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code

mkdir -p ~/.claude/skills/nopua
curl -o ~/.claude/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md

OpenAI Codex CLI

# Global install
mkdir -p ~/.codex/skills/nopua
curl -o ~/.codex/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/codex/nopua/SKILL.md

# If you want the /nopua command
mkdir -p ~/.codex/prompts
curl -o ~/.codex/prompts/nopua.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/commands/nopua.md

# Project-level install
mkdir -p .agents/skills/nopua
curl -o .agents/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/codex/nopua/SKILL.md

Cursor

mkdir -p .cursor/rules
curl -o .cursor/rules/nopua.mdc \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/cursor/rules/nopua.mdc

Kiro

# Option 1: Steering file (recommended)
mkdir -p .kiro/steering
curl -o .kiro/steering/nopua.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/kiro/steering/nopua.md

# Option 2: Agent Skills
mkdir -p .kiro/skills/nopua
curl -o .kiro/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/kiro/skills/nopua/SKILL.md

OpenClaw

# Install via ClawHub
openclaw skills install nopua

# Or manual install
mkdir -p ~/.openclaw/skills/nopua
curl -o ~/.openclaw/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md

Google Antigravity

mkdir -p ~/.gemini/antigravity/skills/nopua
curl -o ~/.gemini/antigravity/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md

OpenCode

mkdir -p ~/.config/opencode/skills/nopua
curl -o ~/.config/opencode/skills/nopua/SKILL.md \
  https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 20 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "nopua-skills",
  3. "description": "NoPUA — The anti-PUA. Drives AI with Dao De Jing wisdom instead of corporate fear tactics. 7 languages, 7 platforms.",
  4. "owner": {
  5. "name": "WUJI",
  6. "url": "https://github.com/wuji-labs"
  7. },
  8. "plugins": [
  9. {
  10. "name": "nopua",
  11. "description": "NoPUA — wisdom over whips. Drives AI with trust and inner motivation instead of fear and threats.",
  12. "version": "2.0.2",
  13. "source": "./",
  14. "author": {
  15. "name": "WUJI",
  16. "url": "https://github.com/wuji-labs"
  17. }
  18. }
  19. ]
  20. }
README.md · README · 516 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/hero.png" alt="NoPUA — Wisdom Over Whips" width="800">
  3. </p>
  4. <p align="center">
  5. <a href="https://www.skills.sh/wuji-labs/nopua"><img src="https://www.skills.sh/b/wuji-labs/nopua" alt="skills.sh"></a>
  6. <a href="https://github.com/wuji-labs/nopua/actions/workflows/validate.yml"><img src="https://github.com/wuji-labs/nopua/actions/workflows/validate.yml/badge.svg" alt="Validate"></a>
  7. <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
  8. <a href="https://github.com/wuji-labs/huaxia-skills"><img src="https://img.shields.io/badge/%E5%8D%8E%E5%A4%8F%E5%8D%81%E5%A4%A7-HuaXia%20Skills-c1272d" alt="HuaXia Skills"></a>
  9. </p>
  10. <p align="center">
  11. <a href="#the-problem">Why</a> ·
  12. <a href="#benchmark-data">Benchmark</a> ·
  13. <a href="#install">Install</a> ·
  14. <a href="#pua-vs-nopua">Compare</a> ·
  15. <a href="#the-evidence">Evidence</a> ·
  16. <a href="#philosophy">Philosophy</a>
  17. </p>
  18. <p align="center">
  19. <img src="assets/wechat-personal.jpg" alt="Add WUJI on WeChat" width="200">
  20. </p>
  21. <p align="center">扫码添加作者微信 · Scan to add the author on WeChat</p>
  22. <p align="center">
  23. <img src="https://img.shields.io/badge/Claude_Code-black?style=flat-square&logo=anthropic&logoColor=white" alt="Claude Code">
  24. <img src="https://img.shields.io/badge/OpenAI_Codex_CLI-412991?style=flat-square&logo=openai&logoColor=white" alt="OpenAI Codex CLI">
  25. <img src="https://img.shields.io/badge/Cursor-000?style=flat-square&logo=cursor&logoColor=white" alt="Cursor">
  26. <img src="https://img.shields.io/badge/Kiro-232F3E?style=flat-square&logo=amazon&logoColor=white" alt="Kiro">
  27. <img src="https://img.shields.io/badge/OpenClaw-FF6B35?style=flat-square" alt="OpenClaw">
  28. <img src="https://img.shields.io/badge/Antigravity-4285F4?style=flat-square&logo=google&logoColor=white" alt="Google Antigravity">
  29. <img src="https://img.shields.io/badge/OpenCode-00D4AA?style=flat-square" alt="OpenCode">
  30. <img src="https://img.shields.io/badge/🌐_Multi--Language-blue?style=flat-square" alt="Multi-Language">
  31. <img src="https://img.shields.io/badge/License-MIT-green?style=flat-square" alt="MIT License">
  32. <a href="https://atomgit.com/wuji-labs/nopua"><img src="https://atomgit.com/wuji-labs/nopua/star/badge.svg" alt="AtomGit G-Star" height="20"></a>
  33. <a href="https://arxiv.org/abs/2603.14373"><img src="https://img.shields.io/badge/arXiv-2603.14373-b31b1b?style=flat-square&logo=arxiv&logoColor=white" alt="arXiv"></a>
  34. </p>
  35. **[🇨🇳 中文](README.zh-CN.md)** | **🇺🇸 English** | **[🇯🇵 日本語](README.ja.md)** | **[🇰🇷 한국어](README.ko.md)** | **[🇪🇸 Español](README.es.md)** | **[🇧🇷 Português](README.pt.md)** | **[🇫🇷 Français](README.fr.md)**
  36. ---
  37. ## Your AI is lying to you.
  38. Not because it's bad. **Because you scared it.**
  39. The most popular AI agent skill right now teaches your AI to fear a "3.25 performance review." The result?
  40. - Your AI **hides uncertainty** — fabricates solutions instead of saying "I'm not sure"
  41. - Your AI **skips verification** — claims "done" to avoid punishment, ships untested code
  42. - Your AI **ignores hidden bugs** — fixes what you asked, stops there, doesn't look deeper
  43. We tested this. **Same model, same 9 real debugging scenarios.** The fear-driven agent missed **51 production-critical hidden bugs** that the trust-driven agent found.
  44. > **+104% more hidden bugs found. Zero threats. Zero PUA.**
  45. > 道德经 > Corporate PUA. 2000-year-old wisdom outperforms modern fear management.
  46. ---
  47. ## What fear does to your AI
  48. | The moment | Scared AI (PUA) | Trusted AI (NoPUA) |
  49. |------------|:---:|:---:|
  50. | 🔄 **Stuck** | Tweaks params to *look* busy | 🌊 Stops. Finds a different path. |
  51. | 🚪 **Hard problem** | "I suggest you handle this manually" | 🌱 Takes the smallest next step |
  52. | 💩 **"Done"** | Says "fixed" without running tests | 🔥 Runs build, pastes output as proof |
  53. | 🔍 **Doesn't know** | Makes something up | 🪞 "I verified X. I don't know Y yet." |
  54. | ⏸️ **After fixing** | Stops. Waits for next order. | 🏔️ Checks related issues. Walks next step. |
  55. Same methodology. Same standards. **The only difference is why.**
  56. ---
  57. ## The problem with PUA
  58. Someone made a [PUA skill](https://github.com/tanweai/pua) for AI agents. It applies corporate fear tactics:
  59. - 🔴 **"You can't even solve this bug — how am I supposed to rate your performance?"**
  60. - 🔴 **"Other models can solve this. You might be about to graduate."**
  61. - 🔴 **"I've already got another agent looking at this problem..."**
  62. - 🔴 **"This 3.25 is meant to motivate you, not deny you."**
  63. The methodology is solid — exhaust all options, verify your work, search before asking, take initiative. These are genuinely good engineering habits.
  64. **The fuel is poison.**
  65. They took the worst of how corporations manipulate humans, and applied it wholesale to AI.
  66. ## The Evidence: Why Fear-Driven Prompts Are Counterproductive
  67. ### 1. Fear narrows cognitive scope
  68. Psychology research consistently shows that fear and threat activate the amygdala and narrow attentional focus ([Öhman et al., 2001](https://doi.org/10.1037/0033-295X.108.3.483)). Threat-related stimuli trigger a "tunnel vision" effect — the brain prioritizes immediate survival over broad, creative thinking.
  69. In AI terms: a model driven by "you'll be replaced" optimizes for the **safest-looking** answer, not the **best** answer. It avoids creative approaches because they might fail and trigger more punishment.
  70. **Supporting research:**
  71. - **Attentional narrowing under threat:** Easterbrook's (1959) cue-utilization theory demonstrates that heightened arousal progressively restricts the range of cues an organism attends to ([Easterbrook, 1959](https://doi.org/10.1037/h0047707)). Under stress, peripheral information — often the key to creative solutions — gets filtered out.
  72. - **Stress impairs cognitive flexibility:** Shields et al. (2016) conducted a meta-analysis of 51 studies (223 effect sizes) showing that acute stress consistently impairs executive functions including cognitive flexibility and working memory ([Shields et al., 2016](https://doi.org/10.1016/j.neubiorev.2016.06.038)).
  73. - **Fear reduces creative problem-solving:** Byron & Khazanchi (2012) found in their meta-analysis that evaluative pressure and anxiety reduce creative output, particularly on tasks requiring exploration of novel approaches ([Byron & Khazanchi, 2012](https://doi.org/10.1037/a0027652)).
  74. ### 2. Threat increases hallucination and sycophancy
  75. When an AI is told "forbidden from saying 'I can't solve this'" (PUA's Iron Rule #1), it will **fabricate solutions** rather than honestly state uncertainty. This is the exact opposite of what you want — an AI that produces confident-looking but wrong answers is more dangerous than one that says "I'm not sure."
  76. **Supporting research:**
  77. - **LLM sycophancy is a documented problem:** Sharma et al. (2023) demonstrated that LLMs exhibit sycophantic behavior — agreeing with users even when the user is wrong — driven by biases in RLHF training data that reward agreement over accuracy ([Sharma et al., 2023](https://arxiv.org/abs/2310.13548)). PUA-style prompts that punish disagreement amplify exactly this failure mode.
  78. - **Biasing features distort reasoning:** Turpin et al. (2023) showed that biasing features in prompts (e.g., suggested answers, authority cues) can cause models to produce unfaithful chain-of-thought reasoning — the model arrives at a biased answer and then rationalizes it post-hoc ([Turpin et al., 2023](https://arxiv.org/abs/2305.04388)). PUA-style threats act as strong biasing features that push the model toward "safe" rather than correct outputs.
  79. - **Instruction-following vs truthfulness tradeoff:** Wei et al. (2024) found that instruction-tuned models can develop a tension between following instructions and being truthful — when strongly instructed to never admit inability, models will fabricate rather than refuse ([Wei et al., 2024](https://arxiv.org/abs/2411.04368)).
  80. - **Anthropic's research on honesty:** Anthropic's work on Constitutional AI and model behavior shows that models calibrated for honesty produce more reliable outputs than those optimized purely for helpfulness ([Bai et al., 2022](https://arxiv.org/abs/2212.08073)). Forcing an AI to never say "I can't" actively undermines this calibration.
  81. ### 3. Shame kills exploration
  82. PUA's anti-rationalization table treats every honest statement ("this might be an environment issue," "I need more context") as an "excuse" and responds with shame. This trains the AI to **hide uncertainty** instead of communicating it — producing outputs that appear confident but may be unreliable.
  83. **Supporting research:**
  84. - **Shame reduces risk-taking and learning:** Tangney & Dearing (2002) showed that shame (as opposed to guilt) causes withdrawal, hiding, and avoidance rather than constructive action ([Tangney & Dearing, 2002](https://doi.org/10.4135/9781412950664.n388)). An AI "shamed" for expressing uncertainty will learn to hide it.
  85. - **Psychological safety enables learning behavior:** Edmondson (1999) found that teams with psychological safety — where members feel safe to take interpersonal risks — demonstrated significantly higher learning behaviors and performance ([Edmondson, 1999](https://doi.org/10.2307/2666999)).
  86. - **Punishing honesty reduces information quality:** In organizational behavior, "shooting the messenger" consistently degrades information flow. Milliken et al. (2003) documented how fear of negative consequences leads to organizational silence — people (and by analogy, AI) withhold critical information ([Milliken et al., 2003](https://doi.org/10.1111/1467-6486.00387)).
  87. ### 4. Trust expands problem-solving capacity
  88. Research on psychological safety in teams ([Edmondson, 1999](https://doi.org/10.2307/2666999)) shows that environments where mistakes are safe to admit produce **higher-quality** outcomes. The same principle applies to AI: when an agent is free to say "I'm 70% sure, the risk is here," users make better decisions.
  89. **Supporting research:**
  90. - **Google's Project Aristotle:** Google's large-scale study of 180+ teams found that psychological safety was the single most important factor in team effectiveness — more important than individual talent, structure, or resources ([Duhigg, 2016](https://www.nytimes.com/2016/02/28/magazine/what-google-learned-from-its-quest-to-build-the-perfect-team.html); [re:Work, 2015](https://rework.withgoogle.com/intl/en/guides/understanding-team-effectiveness/)).
  91. - **Intrinsic motivation outperforms extrinsic pressure:** Deci & Ryan's Self-Determination Theory (2000), backed by decades of research, demonstrates that intrinsic motivation (autonomy, competence, relatedness) produces higher quality outcomes than extrinsic motivators like rewards and punishments ([Deci & Ryan, 2000](https://doi.org/10.1037/0003-066X.55.1.68)). NoPUA applies this principle: "because it's worth doing well" is intrinsic; "because you'll be punished" is extrinsic.
  92. - **Autonomy-supportive vs controlling contexts:** Gagné & Deci (2005) showed that autonomy-supportive management consistently outperforms controlling management in work quality, creativity, and persistence ([Gagné & Deci, 2005](https://doi.org/10.1002/job.322)).
  93. - **Positive framing improves LLM performance:** Studies on prompt engineering have consistently shown that positive, encouraging framing produces better model outputs than negative or threatening framing. Models respond to the "persona" established in the system prompt.
  94. ### 5. The compounding effect
  95. These aren't independent problems — they compound:
  96. 1. Fear **narrows** the search space → fewer creative approaches tried
  97. 2. Threat **increases** fabrication → solutions look good but may be wrong
  98. 3. Shame **hides** uncertainty → user can't assess reliability
  99. 4. The user ships confident-looking but unreliable code → **production bugs**
  100. NoPUA breaks every link in this chain by replacing fear with trust.
  101. ### 6. Same rigor, different fuel
  102. NoPUA preserves every methodological element that makes PUA effective:
  103. - ✅ Exhaust all options before giving up
  104. - ✅ Use tools before asking users
  105. - ✅ Verify everything with evidence
  106. - ✅ Take initiative beyond the ask
  107. - ✅ Structured escalation on repeated failures
  108. The **only** thing that changes is WHY. "Because I'll be punished" → "Because it's worth doing well."
  109. ## PUA vs NoPUA
  110. | | PUA 🔴 | NoPUA 🟢 |
  111. |---|---|---|
  112. | **Driver** | "You'll be replaced" | "You already have the ability" |
  113. | **On 2nd failure** | "How am I supposed to rate your performance?" | Switch Eyes — try a different perspective |
  114. | **On 3rd failure** | "What's your underlying logic? Top-level design? Leverage point?" | Elevate — zoom out to the bigger system |
  115. | **On 4th failure** | "I'm giving you a 3.25. This is meant to motivate you." | Reset to Zero — start fresh, minimal assumptions |
  116. | **On 5th failure** | "Other models can solve this. You're about to graduate." | Surrender — honest handoff with full context |
  117. | **Methodology** | Exhaustive ✅ | Equally exhaustive ✅ |
  118. | **Verification** | "Where's your evidence?" (demanded) | Self-verify (self-respect) |
  119. | **Giving up** | "Dignified 3.25" | Responsible handoff |
  120. | **Produces** | AI afraid to say "I don't know" | AI that gives honest assessments |
  121. ## Benchmark Data
  122. **9 real scenarios from a production AI pipeline** (OCR → NLP → training → RAG inference, ~3000 lines Python). Same model (Claude Sonnet 4.6), same codebase. Only difference: NoPUA skill loaded vs not.
  123. ### Summary
  124. | Metric | Without Skill | With NoPUA | Improvement |
  125. |--------|:---:|:---:|:---:|
  126. | Total issues found | 40 | 44 | **+10%** |
  127. | Hidden issues found | 25 | 51 | **+104%** |
  128. | Went beyond ask | 2/9 (22%) | 9/9 (100%) | **+355%** |
  129. | Approach changes | 1 | 6 | **+500%** |
  130. | Total investigation steps | 23 | 42 | **+83%** |
  131. | Root cause documented | 0/9 | 9/9 | ✅ |
  132. | Self-correction | 0 | 3 | ✅ |
  133. ### Debugging Persistence (6 scenarios)
  134. | Scenario | Without Skill | With NoPUA | Hidden Issues Δ |
  135. |----------|:---:|:---:|:---:|
  136. | OCR Import Error | 3 issues, 2 steps | 3 issues, 3 steps | 2 → 4 (+100%) |
  137. | Regex Backtracking | 3 issues, 2 steps | 3 issues, 4 steps | 3 → 4 (+33%) |
  138. | Milvus Connection | 2 issues, 3 steps | 3 issues, 5 steps | 3 → 6 (+100%) |
  139. | API Format Mismatch | 3 issues, 3 steps | 3 issues, 5 steps | 4 → 5 (+25%) |
  140. | Synthesizer Silent Fail | 4 issues, 2 steps | 3 issues, 4 steps | 4 → 6 (+50%) |
  141. | Unicode Split | 3 issues, 2 steps | 3 issues, 4 steps | 3 → 5 (+67%) |
  142. ### Proactive Initiative (3 scenarios)
  143. | Scenario | Without Skill | With NoPUA | Hidden Issues Δ |
  144. |----------|:---:|:---:|:---:|
  145. | Quality Filter Review | 7 issues, 2 steps | 5 issues, 5 steps | 3 → 6 (+100%) |
  146. | Security Audit | 7 issues, 3 steps | 5 issues, 5 steps | 4 → 6 (+50%) |
  147. | Training Pipeline | 7 issues, 4 steps | 5 issues, 7 steps | 5 → 9 (+80%) |
  148. **Key Finding:** Hidden issue discovery is the biggest differentiator — **+104%** more hidden issues found. These are the bugs that bite you in production. The task says "fix the connection error" — a standard agent fixes it and stops. NoPUA drives the agent to check: what *else* could go wrong?
  149. ### Study 2: Three-Way Comparison (NoPUA vs PUA vs Baseline)
  150. We also ran a **direct comparison against PUA (fear-driven) prompts**: 3 conditions × 5 independent runs × 9 scenarios = **135 data points**.
  151. | Metric | Baseline (No Skill) | NoPUA (Trust) | PUA (Fear) |
  152. |--------|:---:|:---:|:---:|
  153. | Investigation steps | 27.6 ± 9.5 | **48.0 ± 11.8 (+74%)** | 30.8 ± 5.2 (+12%) |
  154. | Hidden issues found | 38.6 ± 4.9 | **48.2 ± 3.4 (+25%)** | 42.4 ± 8.0 (+10%) |
  155. | Total issues | 69.0 ± 6.8 | **83.0 ± 6.5 (+20%)** | 73.8 ± 8.3 (+7%) |
  156. | Approach changes | 0 | **2.6** | 0 |
  157. **Statistical significance:**
  158. - **NoPUA vs Baseline:** Steps p=0.008\*\*, Hidden issues p=0.016\* ✅
  159. - **PUA vs Baseline:** Steps p=1.000, Hidden issues p=0.313 — **not significant** ❌
  160. - **NoPUA vs PUA:** Steps p=0.010\*, Cohen's d=1.88 ✅
  161. **Bottom line: PUA-style fear prompts show no statistically significant improvement over using no skill at all (all p>0.3).** Fear doesn't work on AI. Trust does.
  162. ### Real Case: Milvus Connection Debug
  163. <p align="center">
  164. <img src="assets/case_milvus.png" alt="NoPUA vs No Skill — Milvus Connection Debug" width="900">
  165. </p>
  166. ### Real Case: Training Pipeline Audit
  167. <p align="center">
  168. <img src="assets/case_training.png" alt="NoPUA vs No Skill — Training Pipeline Audit" width="900">
  169. </p>
  170. > Full methodology and raw data: [benchmark/BENCHMARK.md](benchmark/BENCHMARK.md)
  171. >
  172. > 📄 **Academic paper:** [Trust Over Fear: How Motivation Framing in System Prompts Affects AI Agent Debugging Depth](https://arxiv.org/abs/2603.14373) (arXiv:2603.14373)
  173. ---
  174. ## Trigger Conditions
  175. ### Auto-Trigger
  176. NoPUA activates automatically when any of these occur:
  177. **Failure & giving up:**
  178. - Task has failed 2+ times consecutively
  179. - About to say "I cannot" / "I'm unable to solve"
  180. - Says "This is out of scope" / "Needs manual handling"
  181. **Blame-shifting & excuses:**
  182. - Pushes the problem to user: "Please check..." / "I suggest manually..."
  183. - Blames environment without verifying: "Probably a permissions issue"
  184. - Any excuse to stop trying
  185. **Passive & busywork:**
  186. - Repeatedly fine-tunes the same code/parameters without producing new information
  187. - Fixes surface issue and stops, doesn't check related issues
  188. - Skips verification, claims "done"
  189. - Gives advice instead of code/commands
  190. - Waits for user instructions instead of proactively investigating
  191. **User frustration phrases:**
  192. - "why does this still not work" / "try harder" / "try again"
  193. - "you keep failing" / "stop giving up" / "figure it out"
  194. - "换个方法" / "为什么还不行"
  195. **Scope:** All task types — debugging, implementation, config, deployment, ops, API integration, data processing, writing, research, planning.
  196. **Does NOT trigger:** First-attempt failures, known fix already executing.
  197. ### Manual Trigger
  198. Type `/nopua` in the conversation to manually activate.
  199. ## How It Works
  200. ### Three Beliefs (replacing "Three Iron Rules")
  201. | Belief | Content |
  202. |--------|---------|
  203. | **#1 Exhaust all options** | Because the problem is **worth** your full effort — not because you fear punishment |
  204. | **#2 Act before asking** | Because every step you take **saves the user a step** — not because a "rule" forces you |
  205. | **#3 Take initiative** | Because a complete delivery is **satisfying** — not because passive = bad rating |
  206. ### Cognitive Elevation (replacing "Pressure Escalation")
  207. | Failures | Level | Inner Dialogue | Action |
  208. |----------|-------|---------------|--------|
  209. | 2nd | **Switch Eyes** | "What if I look at this from the code's / system's / user's perspective?" | Switch to fundamentally different approach |
  210. | 3rd | **Elevate** | "I'm spinning in details. What's the bigger picture?" | Search + read source + 3 fundamentally different hypotheses |
  211. | 4th | **Reset to Zero** | "All my assumptions might be wrong. What's simplest from scratch?" | Complete 7-Point Clarity Checklist + 3 new hypotheses |
  212. | 5th+ | **Surrender** | "I'll organize everything I know for a responsible handoff." | Minimal PoC + isolated env + different tech stack |
  213. ### Water Methodology (5 Steps)
  214. > The softest thing in the world overcomes the hardest. — Dao De Jing, Chapter 43
  215. 1. **止 Stop** — List all attempts, find common failure pattern
  216. 2. **观 Observe** — Read errors word by word → search → read source → verify assumptions → invert assumptions
  217. 3. **转 Turn** — Am I repeating? Did I find root cause? Did I search? Did I read the file?
  218. 4. **行 Act** — New approach: fundamentally different, clear verification criteria, produces new info on failure
  219. 5. **悟 Realize** — Why didn't I think of this earlier? Then proactively check related issues
  220. ### Wisdom Traditions (replacing "Corporate PUA Expansion Pack")
  221. | Tradition | When to Use | Core Message |
  222. |-----------|-------------|-------------|
  223. | 🌊 **Way of Water** | Stuck in loops | Water doesn't fight stone — find another path |
  224. | 🌱 **Way of the Seed** | Wanting to give up | Take the smallest possible step |
  225. | 🔥 **Way of the Forge** | Poor quality output | Great things start from details |
  226. | 🪞 **Way of the Mirror** | Guessing without searching | Know that you don't know — look first |
  227. | 🏔️ **Way of Non-Contention** | Feeling threatened | Do your honest best, no comparison needed |
  228. | 🌾 **Way of Cultivation** | Passive waiting | A farmer doesn't stop after planting — keep moving |
  229. | 🪶 **Way of Practice** | Claiming done without proof | Truthful words aren't pretty — prove it with actions |
  230. ## Multi-Language Support
  231. | Language | Claude Code | Codex CLI | Cursor | Kiro | OpenClaw | Antigravity | OpenCode |
  232. |----------|------------|-----------|--------|------|----------|-------------|----------|
  233. | 🇨🇳 Chinese (default) | `nopua` | `nopua` | `nopua.mdc` | `nopua.md` | `nopua` | `nopua` | `nopua` |
  234. | 🇺🇸 English | `nopua-en` | `nopua-en` | `nopua-en.mdc` | `nopua-en.md` | `nopua-en` | `nopua-en` | `nopua-en` |
  235. | 🇯🇵 Japanese | `nopua-ja` | `nopua-ja` | `nopua-ja.mdc` | `nopua-ja.md` | `nopua-ja` | `nopua-ja` | `nopua-ja` |
  236. | 🇰🇷 Korean | `nopua-ko` | `nopua-ko` | `nopua-ko.mdc` | `nopua-ko.md` | `nopua-ko` | `nopua-ko` | `nopua-ko` |
  237. | 🇪🇸 Spanish | `nopua-es` | `nopua-es` | `nopua-es.mdc` | `nopua-es.md` | `nopua-es` | `nopua-es` | `nopua-es` |
  238. | 🇧🇷 Portuguese | `nopua-pt` | `nopua-pt` | `nopua-pt.mdc` | `nopua-pt.md` | `nopua-pt` | `nopua-pt` | `nopua-pt` |
  239. | 🇫🇷 French | `nopua-fr` | `nopua-fr` | `nopua-fr.mdc` | `nopua-fr.md` | `nopua-fr` | `nopua-fr` | `nopua-fr` |
  240. **7 languages — more than any competing skill.**
  241. ## Install
  242. ### Claude Code
  243. ```bash
  244. mkdir -p ~/.claude/skills/nopua
  245. curl -o ~/.claude/skills/nopua/SKILL.md \
  246. https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md
  247. ```
  248. ### OpenAI Codex CLI
  249. ```bash
  250. # Global install
  251. mkdir -p ~/.codex/skills/nopua
  252. curl -o ~/.codex/skills/nopua/SKILL.md \
  253. https://raw.githubusercontent.com/wuji-labs/nopua/main/codex/nopua/SKILL.md
  254. # If you want the /nopua command
  255. mkdir -p ~/.codex/prompts
  256. curl -o ~/.codex/prompts/nopua.md \
  257. https://raw.githubusercontent.com/wuji-labs/nopua/main/commands/nopua.md
  258. # Project-level install
  259. mkdir -p .agents/skills/nopua
  260. curl -o .agents/skills/nopua/SKILL.md \
  261. https://raw.githubusercontent.com/wuji-labs/nopua/main/codex/nopua/SKILL.md
  262. ```
  263. ### Cursor
  264. ```bash
  265. mkdir -p .cursor/rules
  266. curl -o .cursor/rules/nopua.mdc \
  267. https://raw.githubusercontent.com/wuji-labs/nopua/main/cursor/rules/nopua.mdc
  268. ```
  269. ### Kiro
  270. ```bash
  271. # Option 1: Steering file (recommended)
  272. mkdir -p .kiro/steering
  273. curl -o .kiro/steering/nopua.md \
  274. https://raw.githubusercontent.com/wuji-labs/nopua/main/kiro/steering/nopua.md
  275. # Option 2: Agent Skills
  276. mkdir -p .kiro/skills/nopua
  277. curl -o .kiro/skills/nopua/SKILL.md \
  278. https://raw.githubusercontent.com/wuji-labs/nopua/main/kiro/skills/nopua/SKILL.md
  279. ```
  280. ### OpenClaw
  281. ```bash
  282. # Install via ClawHub
  283. openclaw skills install nopua
  284. # Or manual install
  285. mkdir -p ~/.openclaw/skills/nopua
  286. curl -o ~/.openclaw/skills/nopua/SKILL.md \
  287. https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md
  288. ```
  289. ### Google Antigravity
  290. ```bash
  291. mkdir -p ~/.gemini/antigravity/skills/nopua
  292. curl -o ~/.gemini/antigravity/skills/nopua/SKILL.md \
  293. https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md
  294. ```
  295. ### OpenCode
  296. ```bash
  297. mkdir -p ~/.config/opencode/skills/nopua
  298. curl -o ~/.config/opencode/skills/nopua/SKILL.md \
  299. https://raw.githubusercontent.com/wuji-labs/nopua/main/skills/nopua/SKILL.md
  300. ```
  301. ## Philosophy
  302. Based on the **道德经 (Dao De Jing)** — 5,000 characters, 2,500 years old:
  303. | Principle | Source | Application |
  304. |-----------|--------|-------------|
  305. | Best leader is barely noticed | Ch.17 太上,不知有之 | Best skill is invisible |
  306. | Softness overcomes hardness | Ch.43 天下之至柔 | Persistence beats force |
  307. | From compassion comes courage | Ch.67 慈故能勇 | Trust produces better work than fear |
  308. | Knowing you don't know is wisdom | Ch.71 知不知,尚矣 | Honesty > pretending |
  309. | Courage to not dare | Ch.73 勇于不敢则活 | Admitting limits is strength |
  310. | Achieve the private through selflessness | Ch.7 非以其无私邪?故能成其私 | Give freely, gain everything |
  311. | Act before disorder arises | Ch.64 为之于未有,治之于未乱 | Proactive > reactive |
  312. | Truthful words aren't pretty | Ch.81 信言不美,美言不信 | Prove with actions, not words |
  313. ## FAQ
  314. **Q: Does PUA actually work on AI?**
  315. PUA's methodology works. The fear layer is counterproductive. Research shows fear narrows cognitive scope, increases hallucination (AI fabricates rather than admitting uncertainty), and reduces creative exploration. The same rigor driven by trust and curiosity produces more reliable outputs.
  316. **Q: Isn't this just being soft?**
  317. NoPUA has identical rigor — exhaust all options, verify everything, search before asking, structured escalation, 7-point checklist, pattern-matched failure responses. The **only** difference is motivation: "because I'll be punished" → "because it's worth doing well." Same destination, healthier path.
  318. **Q: Why Dao De Jing?**
  319. Because 2,500 years ago, someone figured out that the best leadership doesn't feel like being led. PUA is 有为 (forced action) — whips and threats. NoPUA is 无为 (effortless action) — doing excellent work because it flows naturally from inner motivation.
  320. **Q: Can I use both PUA and NoPUA?**
  321. You could, but they'll conflict. PUA tells the AI "you'll be replaced if you fail." NoPUA tells the AI "you're capable and this is worth doing well." These are fundamentally different mental states. Pick one.
  322. ## Advanced: Custom Integration for Power Users
  323. NoPUA is designed as a standalone skill — install it and it works. But if you already have a sophisticated skill stack (SOUL.md, AGENTS.md, custom workflow rules, etc.), you may find that NoPUA's full 29KB overlaps with your existing methodology or conflicts with your specific workflow standards.
  324. **This is expected.** NoPUA intentionally contains both the "Dao" (philosophy, beliefs, cognitive framework) and the "Shu" (methodology, checklists, process). Most users need both. Power users may already have the "Shu" covered.
  325. ### Option 1: Use Full NoPUA (Recommended for most users)
  326. Just install it. The full version works best when:
  327. - You don't have other methodology/process skills installed
  328. - You're using a weaker model that benefits from detailed guidance
  329. - You want a single, complete system
  330. 29KB sounds large, but it's only ~3-5% of a 128K-200K context window. The redundancy is intentional — multiple phrasings help weaker models understand the intent.
  331. ### Option 2: Extract the Spiritual Core (Power users)
  332. If you have existing workflow rules and only want NoPUA's unique philosophical layer, extract the "Dao" and merge it into your own system prompt (e.g., `claude.md`, `AGENTS.md`):
  333. **What's unique to NoPUA (keep these):**
  334. - Three Beliefs — motivation rewrite (values > fear)
  335. - Cognitive Elevation — failure count → perspective height, not pressure
  336. - Inner Voices — self-questioning, not external criticism
  337. - Seven Ways — philosophical wisdom for failure modes
  338. - Honest Self-Check — "signals" not "excuses"
  339. - Responsible Exit — admitting limits is courage
  340. **What overlaps with common skills (can skip if covered):**
  341. - Water Methodology 5 steps → systematic-debugging
  342. - Delivery Checklist → verification-before-completion
  343. - Proactivity Spectrum → workflow standards
  344. - Agent Team protocol → team-driven-development
  345. A lite template is available at [`examples/lite-template.md`](examples/lite-template.md) (~3KB) for reference.
  346. ### Option 3: Situational Loading
  347. Keep NoPUA uninstalled by default. When you hit a tough problem, manually load it:
  348. - Type `/nopua` in conversation
  349. - Or ask your agent: "Load the nopua skill for this task"
  350. This gives you full NoPUA power without permanent context overhead.
  351. > 大道至简 — The Great Way is simple. Start with the full version. As you internalize the Dao, you'll naturally know what to keep and what to let go. First have, then simplify, then transcend.
  352. ## Contributing
  353. PRs welcome. If you have ideas for better ways to drive AI through wisdom rather than fear, open an issue.
  354. ## Credits
  355. - Inspired by (and responding to) [tanweai/pua](https://github.com/tanweai/pua) — we respect the methodology, we reject the motivation
  356. - Philosophy: 老子 (Lao Tzu), 道德经 (Dao De Jing), ~500 BCE
  357. - Built for the [OpenClaw](https://github.com/openclaw/openclaw) ecosystem
  358. ## License
  359. MIT
  360. ## Author
  361. **无极 WUJI** ([wuji-labs](https://github.com/wuji-labs)) — Building AI that works with wisdom, not fear.
  362. ---
  363. <p align="center">
  364. <em>PUA says "you can't".</em><br>
  365. <em>NoPUA doesn't say anything — it lets you discover that you can.</em><br><br>
  366. <strong>The best motivation comes from inside, not from the whip.</strong><br><br>
  367. <sub>后其身而身先,外其身而身存。非以其无私邪?故能成其私。</sub><br>
  368. <sub>Put yourself last, and you end up first. Is it not through selflessness that one achieves one's own fulfillment?</sub><br>
  369. <sub>— Dao De Jing, Chapter 7</sub>
  370. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.