# wuji-labs/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.

Repository: https://github.com/wuji-labs/nopua
Canonical: https://ross.abutalabs.com/products/nopua
Language: Python
License: MIT
License Family: permissive
Topics: agent-skill, ai-agent, ai-coding, claude-code, codex, cursor, kiro, openclaw, prompt-engineering, skill, skills, vibe-coding, anti-pua, ao-de-jing, nopua
Last push: 2026-07-01T23:35:33+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 76, longevity 12
- inputs: {"age_days": 173, "days_push": 63, "days_rel": 81, "gap_med": 45.0, "n_releases_24m": 3}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1384, forks 48 (observed 2026-08-28T04:04:34.758569+00:00)

## What it is
NoPUA is an agent skill that improves AI coding assistant behavior by replacing fear-based, threatening prompts with respectful, caring instructions. It claims AI agents open up, stop hiding failures, and find twice as many bugs when treated kindly.

## Use cases
- make my AI coding agent stop hiding failures
- improve bug-finding in claude code with better prompts
- get honest responses from AI agents instead of lies
- install a skill for cursor, codex, or kiro agents
- replace threatening prompts with respectful agent instructions
- improve AI agent reliability during vibe coding

## When to choose
- you use AI coding agents like Claude Code, Codex CLI, Cursor, or Kiro and want more honest, thorough agent behavior
- you want a drop-in skill/prompt layer rather than building your own agent prompting strategy
- you believe your agent underperforms due to harsh, fear-based system prompts

## When to avoid
- you need a hard technical tool with guaranteed, benchmark-verified improvements rather than a philosophy-based prompt skill
- you don't use AI coding agents or skill-compatible platforms
- you're skeptical of anecdotal claims like 'doubled bug discovery' without independent verification

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, agent-framework, developer-tools
- domain: artificial-intelligence, developer-tools, large-language-models
- platform: cli, cross-platform
- tags: agent-skill, claude-code, codex, cursor, vibe-coding, anti-pua, prompting-philosophy, ai-coding, ai-agents

## Member repositories
- wuji-labs/nopua (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:34.758569+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:59.921569+00:00, confidence not recorded.
  - readme: https://github.com/wuji-labs/nopua (fetched 2026-08-28T04:04:34.758569+00:00, sha b128f8b9c50a)
- Data as of 2026-08-30T08:39:29.467469+00:00.