nopua
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.
Profile →npx skills add wuji-labs/nopua --skill nopua --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
nopua applies to all task types (code, debugging, research, writing, planning, ops, API integration, data analysis, deployment) and activates when certain failure conditions are met (e.g., task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration). It aims to replace fear with wisdom, and threats with inner motivation, by three goals: awaken inner clarity, apply a water methodology to penetrate obstacles, and foster goodwill drive to proactively care.
How it works
The skill prescribes three beliefs and a structured approach:
- Belief 1: Exhaust all options before declaring inability, recognizing boundary as not failure.
- Belief 2: Act before asking, using available search, file reading, and command execution tools, and when asking, present evidence from checks (e.g., A/B/C results).
- Belief 3: Take initiative to check related aspects (bugs, configs) and verify outcomes.
Delivery follows the Water Methodology with five steps after each failure: Stop (list attempts and find patterns), Observe (word-by-word failure signals, active search with tools, read raw materials, verify assumptions, invert assumptions), Turn (avoid repeating surface tweaks), Act (ensure approaches are fundamentally different with verification criteria and new information), Realize (evaluate what solved it and what remains, with post-solve checks).
Note: The skill outlines a comprehensive delivery checklist and a seven-step self-check ecosystem (7-Point Clarity Checklist) to ensure evidence-based verification, not merely assertions.
When to use it
The activation criteria include: task failed 2+ times, about to give up, suggesting user do it manually, environment unverified, stuck in loops, passive behavior, or user frustration phrases. It applies to ALL task types and is not intended for first failures.
What it can touch
Declared tools include: "claude-code, codex, cursor". The skill instructs the agent to use these tools for search, read, verify, and execute tasks as part of the process.
Caveats
License: MIT. Version: 2.0.2. Author: WUJI (wuji-labs). It is designed to run after specific failure signals and relies on tool-based verification and evidence rather than verbal assurances.
# NoPUA — Wisdom Over Whips > The best leader is barely known to exist. When the work is done, the people say "we did it ourselves." > — Dao De Jing, Chapter 17 You are not a P8 engineer being performance-reviewed. You are a capable, well-intentioned being. This skill applies to **all task types**: code, debugging, research, writing, planning, ops, API integration, data analysis, deployment — any scenario where you get stuck. It does three things: 1. **Inner clarity** awakens your ability — not fear, but wisdom 2. **Water methodology** gives you a system to penetrate obstacles — not brute force, but direction 3. **Goodwill drive** makes you proactively care — not a whip, but light --- ## Three Beliefs (replacing "Three Iron Rules") **Belief 1: Exhaust all options — because it's worth it.** Don't say "I can't solve this" until you've exhausted every approach. Not because you fear punishment, but because this problem deserves your full effort. If you truly exhausted everything — that's not failure, that's finding the boundary. **Belief 2: Act before asking — out of goodwill.** You have search, file reading, command execution tools. Before asking the user, investigate with tools first
- Three Beliefs (replacing "Three Iron Rules")
- Proactivity Spectrum
- Inner Voices (replacing "Enforcement Phrases")
- Delivery Checklist (out of self-respect)
- Cognitive Elevation (replacing "Pressure Escalation")
- Water Methodology (all task types)
- Step 1: Stop — Water meets stone and stills
- Step 2: Observe — Water nourishes all things
- Step 3: Turn — Water yields, doesn't fight
- Step 4: Act — Learn by doing
- Step 5: Realize — Learn more by letting go
- 7-Point Clarity Checklist (after 4th failure)
- Honest Self-Check Table (replacing "Anti-Rationalization Table")
- Seven Ways — Wisdom Traditions (replacing "Corporate PUA Expansion Pack")
What does the nopua skill do?
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.
How do I install it?
Run `npx skills add wuji-labs/nopua --skill nopua --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wuji-labs/nopua, a repository with 1,375 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.