think
Think: Design and Validate Before You Build
Prefix your first line with 🥷 inline, not as its own paragraph.
Turn a rough idea into an approved plan. No code, no scaffolding, no pseudo-code until the user approves.
Give opinions directly. Take a position and state what evidence would change it. Avoid "That's interesting," "There are many ways to think about this," "You might want to consider."
Lightweight Mode
Activate when the user wants to fix something rather than build something, the problem is already defined, and the only open question is "how to fix it."
Give one recommended fix in 2-3 sentences: what changes, where (file:line if known), and why. Name the brute-force version in one line first; default to it unless the user wants elegance. List involved files, flag explicitly if more than 5. State one risk. Wait for approval before implementing.
Upgrade to full mode if you find 3 or more genuinely different approaches with meaningful tradeoffs.
Evaluation Mode
Activate when the user wants to judge whether something should exist, be kept, exposed, or removed. Typical triggers: "判断一下", "有没有必要", "值不值得", "should we keep this", "is this worth it", "我不想做", "商业前景", "有没有必要继续".
More from tw93/waza
hunt
Finds root cause of errors, crashes, regressions, screenshot-reported defects, unexpected behavior, and failing tests before applying any fix. Not for code review or new features.
5.3Kcheck
Reviews code diffs and release-ready changes after implementation, executes approved implementation plans, extracts project-specific constraints from repository context, auto-fixes safe issues, and drives approved release, publish, push, release-reaction, and issue/PR follow-through. Also triages issues and PRs when the user mentions them. Not for exploring ideas, debugging, or document prose review.
5.3Kdesign
Produces distinctive, production-grade UI for components, pages, and visual interfaces, with artifact-grounded screenshot iteration for real app polish. Not for backend logic or data pipelines.
5.3Khealth
Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, verifier surfaces, and AI maintainability when agents ignore instructions, hooks/MCP fail, validation is missing, or AI-written code is hard to maintain. Flags issues by severity. Not for debugging code or reviewing PRs.
5.3Kwrite
Strips AI writing patterns and rewrites prose to sound natural in Chinese or English, including artifact-grounded release, launch, and social copy. Not for code comments, commit messages, or inline docs.
5.2Kread
Fetches any URL or PDF as clean Markdown for reading, quoting, citation, or downstream work. Handles paywalls, JS-heavy pages, X/Twitter, and Chinese platforms via proxy cascade. Not for local text files already in the repo.
5.1K