Desenvolvimento

Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.

Generate integration tests for APIs, databases, and external services. Auto-detects backend stack (Express, Fastify, NestJS, Django, FastAPI, Rails, Go), ORM (Prisma, TypeORM, SQLAlchemy, GORM), and database (PostgreSQL, MongoDB, Firestore), then creates tests covering endpoint CRUD, auth flows, DB transactions, and external service failures with proper fixtures and mocks. Self-heals failing tests

Feature discovery agent — mines project docs, memory, user feedback, and competitor gaps to surface the highest-leverage features to build next. Outputs a prioritized feature backlog.

Diagnose NaN losses, out-of-memory errors, and shape mismatches in deep learning or ML pipelines.

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Run independent work in parallel with explicit wave boundaries, lightweight coordination, and bounded verification. Use when latency matters and the work does not need a persistent completion loop.

Use when a user needs to build or refresh persistent graph memory from a mixed corpus and the right path may include graphify, incremental update, or helper conversion before ingestion.

Full-stack app pipeline — build, test, review, and deploy across one or ALL repos. Scans CLAUDE.md, MEMORY.md, TODOs, open PRs, and issues for shippable work. Supports 'ship all' for multi-repo. Use when: 'build and ship', 'ship it', 'ship all', 'deploy everything', 'full pipeline', 'what needs shipping', 'end to end'.

Run an anti-slop cleanup workflow on AI-generated code — regression-tests-first, smell-by-smell, behavior preserved.

Generate a comprehensive developer onboarding guide from your codebase. Analyzes tech stack, project structure, build commands, environment variables, code conventions, and git workflow to produce setup instructions, architecture overview, common task recipes, and troubleshooting guides. Use when you need a getting started guide, developer setup docs, CONTRIBUTING.md, new developer documentation,

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Audit manufacturing production optimization systems for OEE (Overall Equipment Effectiveness) calculation accuracy, Six Big Losses categorization, job shop and flow shop scheduling algorithms (LP, MIP, constraint programming, genetic algorithm), Theory of Constraints bottleneck detection, SMED changeover optimization, sequence-dependent setup matrices, finite capacity planning, Kanban WIP limits,