Use when need to analyze and document project architecture - auto-generates Technical Spec section in CLAUDE.md with token-efficient format

Use when committing changes mid-workflow with smart message generation. Triggers: commit, git commit, salvar progresso, checkpoint, conventional commits, push changes, commitar, fazer commit.

Hub de estilos de documentação. Roteia para o estilo correto. Inclui técnica de cache documental obrigatória.

Visao consolidada do ecossistema - commands, skills, relacoes e dependencias. Carregada pelo /add como source of truth.

Use when documenting feature requirements - creates/updates about.md with business rules, acceptance criteria, scope and decisions using Business Style

Internal skill for developing ADD framework artefacts (commands, skills, agents, scripts). Use when add.strategy analyzes viability of new framework features, when add.make implements framework artefacts, or when creating/modifying commands, skills, or agents. Always use this skill before proposing or implementing changes to the framework itself.

Tech health check: documentation, security, architecture, data analysis.

Use when investigating vague symptoms, suspicious behavior, or information-flow bugs that are not obvious. Enforces differential diagnosis before route recommendation. Consumed by add.diagnose and available to any command that needs rigorous root-cause analysis before acting (hotfix triage, audit deep-dive, review follow-up).

Use when creating landing pages for SaaS products - provides high-conversion patterns, copy frameworks, and aesthetic guidelines

Use when setting up Git on new machine, configuring aliases, or optimizing workflow - provides complete cfg for colors, performance, merge conflicts, and aliases

Use when implementing features that vary by subscription plan, adding new feature flags or limits, validating plan access in controllers, or modifying plan-gated functionality - provides the 3-layer PlanFeatures pattern and IPlanService integration

Use when creating technical implementation plans - creates/updates plan.md with tasks, file mappings, dependencies and complexity estimates using Technical Style

Use when starting new project - discovers founder profile and product blueprint through guided questionnaire, creates docs/owner.md and docs/product.md

Guide project creation from scratch: Node.js stacks (Express, Fastify, NestJS, Bun), two tiers (Starter monolith / Scale monorepo), NestJS-like module organization, stack-context.md generation, and Starter-to-Scale migration. Use when user wants to create a new project, scaffold a codebase, or migrate from monolith to monorepo.

Security audit: OWASP Top 10, multi-tenancy, injection, auth, XSS, dependencies.

Use when building UI components, pages, layouts, dashboards, charts, tables, forms, or any frontend interface. Use when styling, theming, or applying design direction to SaaS products. Triggers: design, UI, UX, component, page, layout, dashboard, mobile, responsive, dark mode, animation, skeleton, empty-state, loading-state, onboarding, settings, billing, auth.

Guide architectural decisions for backend projects. Language and framework agnostic.

Defines content rules for CLAUDE.md files generated by ADD commands (primarily `add.xray` STEP 7). Source: Anthropic official docs (code.claude.com/docs/en/memory).