tw93-claude-health

Skills

Each engineering habit gets an installed skill. In Claude Code, type the slash command. In Codex, invoke the installed skill by name and follow the same playbook.

Skill	When	What it does
/think	Before building anything new	Challenges the problem, pressure-tests the design, and produces a decision-complete plan another agent can implement.
/ui	Building frontend interfaces	Produces distinctive UI, including screenshot-driven aesthetic iteration, with a committed direction rather than generic defaults.
/check	After a task, before merging or release	Reviews the diff, extracts project-specific constraints, handles approved release/publish/push/reaction follow-through, and verifies with evidence.
/hunt	Any bug, regression, or unexpected behavior	Systematic debugging. Root cause confirmed before any fix is applied, especially when something used to work.
/write	Writing or editing prose	Rewrites prose to sound natural in Chinese and English. Cuts stiff, formulaic phrasing.
/learn	Diving into an unfamiliar domain	Six-phase research workflow: collect, digest, outline, fill in, refine, then self-review and publish.
/read	Any URL or PDF	Reads URLs and PDFs with platform-specific routing. Plain reads return a concise summary; Markdown output is used when asked to convert, quote, cite, save, or feed downstream work.
/health	Auditing Agent Health	Checks Codex, Claude Code, project instructions, verifier output, and AI maintainability with a budget-aware summary pass before deep inspection.

Each skill is a folder with reference docs, helper scripts, and gotchas from real failures.

Install

One command installs all eight skills, with no prompts and no errors. Copy and run:

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

One canonical copy lands in the shared ~/.agents/skills store (the agents.md standard directory) with Claude Code symlinked in, so Codex, Cursor, Kimi Code CLI, Amp, Cline, and every other agent reading that directory picks Waza up automatically. Models routed through these harnesses (GLM or Kimi K2 behind Claude Code-compatible endpoints) need nothing extra; tools with a private skills directory append their agent id (e.g. -a qwen-code iflow-cli). Update later with npx skills update -g -y.

Native plugin (for host-native update 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

Claude Desktop: download waza.zip, then Customize > Skills > "+" > Create skill, and upload the ZIP. Re-upload the latest ZIP to update.

Pi: pi install npm:@tw93/waza (update with pi update npm:@tw93/waza). /health audits Pi settings alongside Claude Code and Codex.

Chaining Skills

Skills chain together, but every transition is a manual step you trigger. Each skill finishes its task and stops, waiting for you to decide what comes next.

Common workflows:

• Plan a feature: /think → approve → say "implement X" → /check → merge
• Ship a fix: /hunt → fix → /check → release/publish/push/issue follow-through
• Research and write: /read (fetch sources) → /learn (synthesize) → /write (polish)
• Debug and verify: /hunt (find root cause) → fix → /check (review changes)

Project Context