ship

Analyze Git diff and generate Conventional Commits format messages. Use when user mentions コミットして, コミット作成, commit changes.

Analyze Git changes and suggest appropriate branch names. Use when user mentions ブランチ名, ブランチ作成, branch name.

Analyze branch changes and generate comprehensive PR description. Use when user mentions PR作って, プルリクエスト, pull request, PR作成.

Generate GitHub Issue with structured title and body. Use when user mentions Issue作って, Issue書いて, Issue作成, GitHub Issue.

Compose feature architecture from codebase exploration (yomu preferred) with blueprints, components, and build sequences.

Challenge audit findings to reduce false positives.

Challenge design proposals to expose hidden weaknesses.

Verify audit findings with positive evidence.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Synthesize static findings, outcome evidence, and adversarial results into root causes and Trust Score for /verify.

Score test quality against Spec T-NNN scenarios. 5 metrics → 0-100 composite score.

Analyze codebase features by tracing execution paths, mapping architecture, and documenting patterns.

Analyze Git changes and generate branch names following conventional patterns.

Analyze staged Git changes and generate Conventional Commits format messages.

Generate Playwright E2E tests from Spec Test Scenarios (Type: e2e). Drives a live app via agent-browser.

Generate well-structured GitHub Issues from descriptions.

Analyze branch changes and generate comprehensive PR descriptions.

Generate tests from Spec Test Scenarios. Does not implement code.

TypeScript/build error resolution with minimal changes. No architectural modifications.

WCAG 2.2 compliance review.

Code quality review. Structure and readability analysis.

React design patterns and component architecture review.

Technical documentation review for quality, clarity, structure.

Cross-file code duplication detection. DRY analysis specialist.

Code efficiency review. Unnecessary work, concurrency, hot-path analysis.

Operational readiness review. Error boundaries, loading states, logging, performance budgets.

React rendering, bundle size, and runtime performance review.

CSS-first approach review. Identify JS overuse.

LLM prompt file quality review. Token efficiency, structure, format, clarity.

Existing code reuse opportunity detection. Find replaceable new code.

5 Whys root cause analysis. Detect patch-like solutions.

OWASP Top 10-based security vulnerability detection.

Silent failure detection. Empty catches, unhandled rejections.

SOW/Spec quality review. 100-point scoring, 90-point pass threshold.

Test coverage quality review. Behavioral gaps and test robustness.

Testable code design review. Identify test-hostile patterns.

Type design quality review. Encapsulation, invariants, enforcement.

TypeScript type safety review. any usage, coverage gaps, strict mode.

Reconcile challenge and verification results into cross-domain root causes.

Non-blocking QA participant via peer DM. Observes and comments on design and implementation quality.

Implements a work unit using RGRC cycle for assigned files and tests.

Access Google Sheets and Docs via gcloud CLI. Use when user shares a Google Sheets/Docs URL or mentions スプレッドシート, Sheets, Docs, Google ドキュメント.

Create Architecture Decision Records (ADR) in MADR format with auto-numbering. Use when user mentions ADR作成, 技術決定, アーキテクチャ決定, decision record.

Root cause analysis with 5 Whys. Use when: root cause, 5 Whys, なぜなぜ分析, 根本原因, 原因分析, symptom fix, 対症療法.

Fundamental software principles - SOLID, DRY, Occam's Razor, Miller's Law, YAGNI, Readable Code. Use when: 原則, シンプル, 複雑, リファクタリング, 保守性, clean code, best practice.

Framework-agnostic frontend component design patterns. Use when: component patterns, Container/Presentational, フロントエンドパターン, コンポーネント設計.

Orchestrate specialized review agents for code quality assessment. Use when user mentions レビューして, コードレビュー, 品質チェック, code review, quality check. Do NOT use for quick PR screening (use /preview instead).

Challenge proposals, designs, plans, or analyses with devil's advocate. Use when user mentions devils advocate, 反論, チャレンジ, challenge, 叩いて, 穴探し. Do NOT use for code review findings (use /audit which has built-in challenger).

Analyze Git changes and suggest appropriate branch names. Use when user mentions ブランチ名, ブランチ作成, branch name.

Implement code following TDD/RGRC cycle with real-time test feedback. Use when user mentions 実装して, コード書いて, implement, coding. Do NOT use for small bug fixes or error resolution (use /fix instead).

Analyze Git diff and generate Conventional Commits format messages. Use when user mentions コミットして, コミット作成, commit changes.

Structured ADR creation in MADR format. Use when: ADR, Architecture Decision, 決定記録, 技術選定, アーキテクチャ決定, deprecation, 非推奨化.

Slack conversation harvesting and term extraction. Internal module for /glossary. Use when: ユビキタス言語, 用語集, glossary, ドメイン用語.

Comprehensive feature development with exploration, architecture, TDD, and quality gates. Use when user mentions 機能開発, 新機能, 機能追加, feature development. Do NOT use for implementation without planning (use /code), bug fixes (use /fix), or planning only without implementation (use /think).

Rapidly fix small bugs and minor improvements in development environment. Use when user mentions バグ修正, 直して, 修正して, fix bug, 不具合. Do NOT use for new feature implementation or large-scale changes (use /code instead).

100-point scoring for SOW/Spec design review. Use when: 設計書レビュー, 品質スコア, document scoring.

TDD with RGRC cycle and Baby Steps. Use when: TDD, テスト駆動, Red-Green-Refactor, Baby Steps.

Extract ubiquitous language from Slack and generate domain glossary. Use when user mentions 用語集, glossary, ユビキタス言語, ドメイン用語, Slack から用語.

Storybook integration with spec.md. Auto-generates Stories from Component API. Use when: storybook, stories, props, argTypes, variants, CSF3.

Generate GitHub Issue with structured title and body. Use when user mentions Issue作って, Issue書いて, Issue作成, GitHub Issue.

Proofread and auto-fix Japanese text using textlint. Use when user mentions 校正して, kousei, textlint, 日本語チェック, 文章チェック.

Frontend performance optimization. Use when: performance, Web Vitals, LCP, FID, CLS, パフォーマンス最適化, 速度改善, bundle size.

Workflow orchestration for /code, /fix, /audit. Use when: /code ワークフロー, /fix ワークフロー, quality gates, 品質ゲート, RGRC サイクル.

Light review + cleanup with optional Codex cross-check, slop removal, and test audit. Use when user mentions 整理して, きれいにして, コード整理, slop除去, ポリッシュ, テスト整理, テスト監査, クロスチェック, crosscheck, Codex レビュー. Do NOT use for deep multi-reviewer audits (use /audit).

Analyze branch changes and generate comprehensive PR description. Use when user mentions PR作って, プルリクエスト, pull request, PR作成.

AI screening review for PRs - preliminary check before human review. Use when user mentions スクリーニング, PRレビュー, プレビュー, preview PR, pre-review. Do NOT use for deep multi-reviewer code quality audits (use /audit instead).

Perform project research and technical investigation without implementation. Use when user mentions 調査して, 調べて, リサーチ, investigate, 分析して, issueやろう, issue見て. Do NOT use for design planning or SOW/Spec generation (use /think instead).

Code readability review. Use when: 可読性, 明確, 命名, 変数名, 関数名, ネスト, 関数設計, コメント, 複雑, Miller's Law, ミラーの法則, 認知負荷, AI-generated, 過剰設計. Do NOT use for security (reviewing-security), type errors (reviewing-type-safety), error handling (reviewing-silent-failures), or test design (reviewing-testability).

OWASP Top 10 security review. Use when: security, OWASP, XSS, SQL injection, セキュリティ, 脆弱性, cloud security, AWS, IAM, Terraform, クラウドセキュリティ, インフラ. Do NOT use for readability (reviewing-readability), type errors (reviewing-type-safety), or test design (reviewing-testability).

Silent failure detection. Use when: silent failure, empty catch, エラーハンドリング, 握りつぶし, swallowed error. Do NOT use for security (reviewing-security), readability (reviewing-readability), or type safety (reviewing-type-safety).

Testable code design review. Use when: テスト容易性, モック, mock-friendly, DI. Do NOT use for type safety (reviewing-type-safety), security (reviewing-security), or readability (reviewing-readability).

TypeScript type safety review. Use when: type safety, any, 型安全, 型カバレッジ, strict mode. Do NOT use for testability (reviewing-testability), security (reviewing-security), or readability (reviewing-readability).

PR screening review before human review. Use when: スクリーニングレビュー, PRレビュー支援, レビュー前チェック, PR screening, pre-review.

Large-scale parallel implementation with multi-agent swarm. Architect + QA + Implementer(s) collaborate via peer DM. Use when user mentions 大規模実装, 並列実装, swarm, チーム実装.

Tailwind CSS v4 design decisions. Use when: Tailwind, utility-first, container query, design tokens, dark mode strategy.

Design exploration with SOW and Spec generation. Use when user mentions 計画して, 設計して, アプローチ検討, 方針決め, planning, design exploration. Do NOT use for codebase investigation without planning intent (use /research instead).

CLI tools guide (git, gh, npm). Use when: git操作, gh コマンド, npm スクリプト, HEREDOC コミット, CHANGELOG.

SOW/Spec cross-document consistency validation. Use when: 整合性チェック, consistency check, spec validation, 仕様検証.

React/Next.js performance rules from Vercel Engineering. Triggers on: React components, Next.js pages, data fetching, bundle optimization.

Independent outcome-based verification with Codex + audit reviewers. Use when user mentions 検証して, verify, 独立検証, outcome verification, trust score, adversarial testing. Do NOT use for quick code review (use /polish) or static-only audit (use /audit).

Start Discord auto-response loop. Use when user mentions watch, discord watch, auto-response.