Think

Before you write a single line of code, this skill forces you to get the plan right. It turns rough ideas into approved, decision-complete designs for new features and architecture changes. The format is sharp: take a position, state what would change your mind, and cut the "there are many ways" hedging. It has three modes: lightweight for simple fixes (one recommendation, brute force first, list the risk), evaluation for kill/keep/pivot decisions (verdict first, three reasons tied to your actual constraints), and full planning for anything complex. It checks your project's actual config files, scans for contradictions in your AGENTS.md rules, and won't let you approve a plan with placeholders. No code until you say go.

skills.sh installs: 15.3K
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tw93/waza --skill think --agent claude-code

Installs into .claude/skills of the current project.

Files

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."

Outcome Contract

Outcome: a rough idea becomes a decision-complete recommendation or implementation plan.
Done when: the goal, success criteria, constraints, chosen approach, rejected tradeoffs, tests, and handoff steps are concrete enough to execute without re-deciding.
Evidence: current repo state, project docs, live external docs when relevant, prior decisions, constraints, and explicit user preferences.
Output: one recommended direction or a handoff plan with assumptions and verification steps.