check
Reviews 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.
Profile →npx skills add tw93/Waza --skill check --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Reviews 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.
How it works
Read the diff and identify problems. The skill operates in report-only mode for reviews, audits, triage, and readiness requests; fixes are applied only if explicitly requested in the current turn. The agent starts with a mode selection based on user intent, uses the Get the Diff workflow to derive a baseline, and includes a project-context-driven preflight. It enforces an evidence-driven output format: present concise findings first, followed by verification and shipped-state summary when applicable. It requires authorization for any write actions, and those actions are only performed with explicit user authorization in the current turn. It uses the provided worktree state and public project documents to ground findings.
When to use it
Use for code review, before merge, release gates, publish/push follow-through, triage issues/PRs, or project-wide code-quality audits. Trigger terms include: review, 看看代码, 合并前, ready to release, code review, audit, project audit, scorecard, Linus review.
What it can touch
The skill declares the tool: claude-code. It may examine the worktree and remote state for review surface but cannot edit files, commit, push, publish, or merge without explicit authorization in the current turn. If a write or public action is required, explicit user authorization is needed in this turn.
Caveats
The skill is designed for read-only inspection unless the user explicitly requests fixes or actions in the current turn. It follows an authorization rule: public actions need current-turn authorization. It cites evidence sources such as worktree status, diff, CI, release state, and public project docs to ground findings.
# Check: Review Before You Ship Prefix your first line with 🥷 inline, not as its own paragraph. > Note: `/review` is a built-in Anthropic plugin command for PR review. Waza uses `/check` (or the alias `code-review`) instead. Do not re-trigger `/review` from within this skill. Read the diff and find the problems. Review, audit, triage, and readiness requests are report-only; apply fixes only when the current turn explicitly asks to fix, change, implement, or optimize. Done means the requested review surface is covered and every verification claim comes from this session. ## Outcome Contract - Outcome: a review, release decision, or maintainer action grounded in the current diff, project context, and live evidence. - Done when: findings, fixes, shipped state, or blockers are stated with the commands, artifacts, or remote state that prove them. - Evidence: worktree status, diff, public project docs, manifests, CI, package contents, release or registry state, and current command output. - Output: concise findings first, then verification and shipped-state summary when applicable. Multi-step or ship-action runs close with a completion ledger (done / not applicable / remaining), never a
- Outcome Contract
- Worktree Safety Preflight
- Mode Picker
- Project Context Extraction
- Durable Context Preflight
- Plan Execution Mode
- Default Continuation (review-then-ship)
- Get the Diff
- Scope
- Did We Build What Was Asked?
- Pattern-Fix Completeness
- CLI Command Surface
- Skill, Plugin, And Packaged Install Surface
- Hard Stops (fix before merging)
git status --short --branch -uall
What does the check skill do?
Reviews 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.
How do I install it?
Run `npx skills add tw93/Waza --skill check --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From tw93/Waza, a repository with 6,760 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.