
Architecture Decision Record companion. Guides the user through a structured Socratic dialogue to think through an architectural decision, then writes the ADR. Use when the user wants to make an architectural decision, write an ADR, or reason about a technical choice.
Launch CI/CD pipeline review (security, reliability, performance, maintainability). Use when the user asks to review pipelines, GitHub Actions, GitLab CI, deployment scripts, or CI/CD configuration.
Launch code quality review (safety, performance, developer experience). Use when the user asks to review code quality, check code, or after writing backend/logic code.
Launch DDD architecture review (strategic, tactical, layer isolation). Use when the user asks to review architecture, domain model, or bounded contexts.
Bootstrap project-specific Claude Code rules and product documentation by analyzing the codebase structure, dependencies, and conventions. Use when setting up Claude Code for a new project, or when the user asks to initialize rules, configure Claude for a project, or bootstrap project settings.
Analyze the current project state and suggest the most relevant next move. Use when the user asks "what next?", "next move?", feels stuck, or wants guidance on priorities.
Launch UX review (visual hierarchy, interaction, user flow). Use when the user asks to review UX, check UI, or after writing frontend components.
Full project health audit. Reviews the entire codebase against its own standards — code quality, architecture, UX, CSS, documentation coherence, and internal consistency. Use when the user wants a global assessment, health check, or état des lieux of the project.
Kill orphaned Claude Code processes, remove old versions, and report memory/disk usage. Use when the system feels slow or after crashes.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Launch CSS/Design System review (tokens, consistency, browser compatibility). Use when the user asks to review CSS, styles, Tailwind, or design system usage.
Create, suggest, or maintain easter eggs in the codebase. Use when the user wants to add a personal touch, a hidden surprise, or a signature to the project. Also use when the work is polished and deserves a finishing touch.
Implement a feature guided by product documentation in docs/. Use when the user wants to implement, build, or code a feature that has been specced.
Launch infrastructure review (security, FinOps, reliability). Use when the user asks to review Terraform, IaC, infrastructure code, or cloud resources.
Spec a new feature with product documentation. Use when the user wants to define, spec, or plan a new feature. Creates user stories, acceptance criteria, and business rules in docs/.
Manage product documentation in docs/. Use when the user asks to create, update, or audit product documentation, specs, or requirements.
Launch ALL four review agents in parallel (code, DDD, UX, CSS). Use when the user wants a comprehensive full review of everything.
Audit product documentation coherence against the codebase. Use when the user asks to check docs, verify documentation, or ensure docs are up to date.
Smart review that detects file types and launches the right review agents. Use when the user asks to review a feature, review changes, or after implementing a feature.
Deep security audit of the codebase. Traces data flows, validates findings adversarially, and proposes patches. Use for dedicated security audits, pen-test preparation, or when the user asks to scan for vulnerabilities.