#296296th of 324 in Skills, plugins and prompts
nopua
Agent skill that replaces fear-based prompts with trust-based debugging guidance
- Stars
- 1.4k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Jun 2026
- Language
- Python
1,089 on 3 Apr 20261,403 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
NoPUA is a prompt skill for coding agents. It activates after repeated failures or give-up phrases, or on /nopua. It replaces threat-style escalation with a staged method: switch perspective, zoom out, reset assumptions, then hand off with full context. The authors report a 9-scenario benchmark on Claude Sonnet 4.6, a three-way comparison against a fear-driven skill, and an arXiv paper.
Who it is for: Users of Claude Code, Codex or Cursor whose agents stall or claim false success
Strengths
- Auto-triggers on 2+ failures, give-up phrases and frustration, or manually via /nopua
- Publishes benchmark methodology, raw data and an arXiv paper (2603.14373)
- Lists support for Claude Code, Codex CLI, Cursor, Kiro, OpenCode and others
- Fixed escalation ladder: switch eyes, elevate, reset to zero, responsible handoff
Weaknesses
- Benchmark is author-run on one ~3000-line Python pipeline and one model
- Three-way comparison uses only 5 runs per condition
- Much of the README is psychology argument rather than usage detail
- Install steps are not visible in the truncated README
What it needs
- no GPU
- Models: Claude Code, OpenAI Codex CLI, Cursor, Kiro, OpenClaw
Quick answers
Is nopua open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |