SkillPedia Skills Encyclopedia
中文 EN

nopuawuji-labs/nopua

Installs a set of self-questioning checklists into AI coding agents so they proactively catch perfunctory work,…

No ratings yet Rate this skill
Stars1.4k
Forks54
Watchers1.4k
Open Issues1

InstallOne-line install

Installable · 22 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add wuji-labs/nopua

22 more are not listed — run npx skills@latest add wuji-labs/nopua --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Installs a set of self-questioning checklists into AI coding agents so they proactively catch perfunctory work, omissions, and going in circles before delivery, instead of waiting for users to find faults. Key capabilities include: 1. Pre-delivery self-check: through questions like "Is this really done?" and "What evidence do I have?", it forces the agent to provide verification evidence before claiming completion, reducing cases where deployment is declared done without validation; 2. User-perspective shift: through questions like "How would the user feel?" and "What else can I do?", it pushes the agent to go one step further and actually solve the problem instead of saying "please handle it manually"; 3. Anti-loop detection: through questions like "Am I going in circles?" and "If I started over, what is the simplest way?", it identifies repeated ineffective attempts and switches to a simpler approach; 4. Similar-issue sweep: through questions like "Have I checked for similar issues?" and "What is the next step?", it expands a single fix into a systematic sweep and clarifies follow-up actions; 5. Curiosity-driven exploration: through questions like "I am curious what is behind this" and "Am I satisfied with this?", it encourages the agent to dig into root causes and take responsibility for output quality.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID867
Data sourceGitHub
Repositorywuji-labs/nopua
CategoryAI & Agent Development / AI Coding & Prompt Engineering
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1181318933
Node IDR_kgDORml_FQ
Rank#567 (position within the source ranking)
Site-wide popularity rank#668 (computed live from Stars, across all 5845 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05001k1.5k2026-09-292026-10-112026-09-29 · 1,3942026-10-11 · 1,401
  • Now1,401
  • Previous point · 09-29 1,394
  • vs previous point +7
  • 2 data points 12 days
02040602026-09-292026-10-112026-09-29 · 542026-10-11 · 54
  • Now54
  • Previous point · 09-29 54
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-03-14 01:47:208 months ago
Data last updated2026-10-26 12:00:1724 days ago
Last commit2026-09-28 13:56:241 months ago

CommitLatest commit

Committed by wuji-labs. Update Category: Documentation Updates. Commit details: docs: 统一作者微信二维码 · unify author WeChat QR. This update refines the documentation for easier onboarding.

44010e0 wuji-labs 2026-09-28

Next stepsNext steps