RadarTopicsBuildersWeeklyReads
Open Source Radar
tw93/

Waza

GitHub

Waza provides installed AI agent skills for Claude-based workflows to enforce engineering habits. It ships eight skills and a one-command install, with releases updating skill boundaries and safety checks.

6.8kstars
400forks
0issues
MITlicense
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

Waza is a collection of engineered habits converted into skills for Claude-based agents. It includes eight discrete skills, each with a defined playbook and trigger, designed to guide tasks like planning, UI reasoning, checking diffs, debugging, writing, learning, reading, and health checks.

How it works

Skills are installed and then invoked via Claude Code or Codex. Each skill is a folder with reference docs, helper scripts, and gotchas from real failures. Skills are chained, with transitions initiated by the user. The project context feature allows /check to read public repository context to tailor reviews.

Getting started

Install all eight skills with:

npx skills add tw93/Waza -a claude-code codex cursor antigravity-cli -g -y

Update later with:

npx skills update -g -y

Native plugin instructions are provided for Claude Code and Codex, plus a Claude Desktop ZIP download and Pi installation commands:

# Claude Code: install, then `claude plugin update waza`
/plugin marketplace add tw93/Waza
/plugin install waza@waza

# Codex: install, then `codex plugin marketplace upgrade waza`
codex plugin marketplace add tw93/Waza
codex plugin add waza@waza

Pi: pi install npm:@tw93/waza (update with pi update npm:@tw93/waza).


## Recent releases
Latest releases in order:
- v3.33.0 V3.33.0 Frontier 🔭 (2026-08-01): Updated for stronger models, with less ceremony and sharper evidence.
- v3.32.0 V3.32.0 Discipline 🥋 (2026-07-19): Sharper skills and release checks that fail honestly.
- v3.31.2 V3.31.2 Safeguard 🛡️ (2026-07-10): Safer instruction boundaries without literal attack prompts.
- v3.31.1 V3.31.1 Calibrate 🧭 (2026-07-05): Sharper skill boundaries and release-proof handoffs.
- v3.31.0 V3.31.0 Anchor ⚓ (2026-07-04): Fewer setup surprises, clearer release checks.

## Traction
Stars: 6760. Forks: 400. Open issues: 0. Language: Python. License: MIT. Created: 2026-03-12. Last push: 2026-08-02.

## Behind the repo
Not provided in the facts.

## Caveats
License: MIT. No open issues reported in the provided data. Provides installation commands, plugin details, and uninstall steps for Claude Desktop, Codex, and Pi integration.
Agent skills inside · 8
All skills →
healthRuns a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.SecurityscriptscheckReviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.Code Review & QualityscriptswriteRewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like wording, or prepare launch and social copy. Not for code comments, commit messages, or inline docs.Content & MarketingscriptsreadReads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.Content & MarketingscriptsuiProduces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask in any language for UI, page, component, frontend, typography, screenshot-grounded visual polish, or complaints that a screen looks unclear, ugly, inconsistent, or visually wrong. Not for backend logic or data pipelines.Data & AnalyticshuntFinds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.Code Review & Quality
SharePost on XLinkedIn
All trending reposRevenue-verified startups →