AI Agent Workflow Collection

Use when documenting project architecture — generates Technical Spec section in…

Guides backend architecture decisions — over-engineering, folder structure, slices, layers, feature organization, where code goes.

Backend API architecture: Clean Architecture, SOLID, DTOs, Services, Repositories, RESTful — stack-agnostic.

Use when generating or updating CLAUDE.md files — defines what belongs vs. what stays in skills/docs, format rules (JSON for data, markdown for rules/instructions), and line budget. Load before any CLAUDE.md write.

Code review: IoC, RESTful, Contracts, Security (OWASP), Clean Architecture, SOLID.

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

Product validation: Requirements 100% implemented, prerequisites exist, acceptance criteria pass.

Use when bash/git/jq/gh CLI are missing or VS Code terminal is not WSL — detects OS, diagnoses gaps, installs missing tools.

Use when reviewing a just-written ADD doc as a fresh stakeholder — surfaces gaps, clarity, and scope questions.

Source of truth for ADD doc rules, depth floors, IDs, refs, validation gate. Load before any doc write.

Use when analyzing codebase for a specific feature - creates/updates discovery.md with technical analysis, patterns, files mapping and caches for future…

Document feature requirements - creates/updates about.md with business rules, scope,…

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

Frontend architecture consultant for project structure, folder organization, feature boundaries, and scaling decisions. Framework-aware (React, Vue, Angular). Use when user asks about frontend folder structure, "components folder is a mess", "where should this go", over-engineering, slices, feature folders, or starting/refactoring a frontend project. Guides decisions only — does not implement (use add-frontend-development) or design UI (use ux-design).

Frontend architecture: state, data fetching, components, forms, routing. Stack-agnostic.

Use when a task needs structural/relational code navigation — call graph, references, blast-radius, trace flows, safe refactors — and the GitNexus plugin is enabled. Routes intent to the native gitnexus- skills.

Tech health check: documentation, security, architecture, data analysis. Use when user requests project audit, tech debt review, or health check.

Use when allocating feature/hotfix/refactor/chore/docs IDs or creating branches — canonical [NNNN][L] format that the scripts (next-id.sh, get-branch-metadata.sh, done.sh)…

Use when investigating vague symptoms or information-flow bugs requiring differential diagnosis before fixes. Applies to hotfix triage, audit deep-dive, review follow-up. Consumed by add.diagnose.

Use at the context/discovery step of add.plan, add.hotfix, add.new, add.diagnose, add.review — consult the project wiki (and code knowledge graph) for minimal token cost before dispatching agents.

Git global cfg setup — colors, performance, merge conflicts, aliases for new…

Use when adding plan-gated features, flags, limits, or validating plan access via…

Create/update plan.md with sequenced tasks, file mapping, dependencies and S/M/L…

Use when starting a new project — discovers founder profile and product blueprint, writes docs/owner.md +…