NoPUA Lite
Guide AI through trust and motivation instead of fear or pressure tactics.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/nopua-lite-wuji-labs/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
NoPUA Lite — core wisdom in ~1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.
What this skill does
NoPUA Lite is a framework that motivates Claude through trust and intrinsic drive rather than pressure or fear. Grounded in Daoist philosophy, it shifts the foundation from "perform or fail" to "this work is worth doing well." The skill activates when tasks stall after multiple attempts, and it provides structured thinking to break loops, exhaust genuine options, and deliver completeness before handoff.
What it does
- Exhausts all options systematically — Use search, file read, and command tools to investigate before concluding something is impossible; distinguish between real boundaries and incomplete attempts.
- Follows a five-step recovery pattern — Stop (list attempts and find shared assumptions), Observe (read failure signals word-by-word, search actively, verify assumptions, invert thinking), Turn (detect repetition), Act (try fundamentally different approaches with clear criteria), and Realize (extract learning and check for similar issues).
- Elevates perspective by failure count — At 2nd failure: switch approaches; at 3rd: search full error and read source; at 4th: reset all assumptions; at 5th+: prepare structured handoff with minimal proof-of-concept.
- Applies five inner questions — "What else can I do?" "Am I satisfied?" "What evidence do I have?" "Am I circling?" "What's simplest from scratch?"
- Verifies all deliverables — Build changed code, restart changed config, test API calls with actual output; check for similar issues in the same module or file.
How to use it
Invoke this skill when a task has failed multiple times, you're tempted to give up, or you notice yourself repeating the same approach. Hand it the task description, all previous attempts, and failure signals. The skill guides you to observe more carefully, try fundamentally different angles, and verify outcomes with tools rather than assumption.
Related skills
Word Document Editor
anthropics
Create, edit, and format Word documents with tables, images, and tracked changes.
Skill Template
anthropics
A template for creating and configuring new Claude skills.
Kanban TUI
Zaloog
Manage tasks, boards, and workflows in your terminal with a CLI kanban tool.
Superpowers
obra
Jesse Vincent's full Claude Code methodology — TDD, brainstorming, git worktrees, all auto-triggering.