.Agent

Tactical Blueprint for production-grade Next.js 15+ applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.

Tactical Blueprint for production-grade Spring Boot 3+ applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.

Patterns for using FAISS MCP tools to ingest documents and perform semantic retrieval.

Conducts a multi-perspective adversarial review of knowledge/prd.md using a structured debate pattern. Activates three reviewer personas — Product Critic, AI Systems Engineer, and Security Auditor — to surface gaps, contradictions, missing edge cases, and AI-specific failure modes. Use when the user wants to validate requirements, check the PRD, find gaps, stress-test the spec, or says "review the requirements", "what are we missing", "is this complete", or "let's pressure-test this". Requires knowledge/prd.md. Writes findings to knowledge/review-findings.md.

Tactical Blueprint for production-grade FastAPI applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.

Use when facing 2+ independent tasks or failures that can be worked on without shared state or sequential dependencies.

Detailed CrewAI agent design patterns - role design, backstories, collaboration, hierarchical vs sequential processes, tool integration

Execute plan by dispatching specialized subagents per task. Ensures isolated context and high precision.

Skill for coordinating experimental interactions including agent-to-agent handoffs and voice-to-PRD workflows.

SQLAlchemy 2.0 patterns (mapped_column, Mapped types), Async engine and sessions, Relationship patterns, Alembic migrations, Repository pattern, Query optimization, Connection pooling

Verify understanding and alignment before major implementations

Uses the Factory project generation engine to create core file structures and basic implementation logic from parsed PRD requirements. Orchestrates the ProjectGenerator and uses builder agents for initial implementation.

Service decomposition, API Gateway with YARP, inter-service communication (gRPC, REST, message bus), distributed caching, health checks, circuit breakers

Spring Cloud microservices patterns with gateway, discovery, and resilience

Universal two-pass verification for LLM grounding using confidence delta comparison

Build multi-agent workflows using CrewAI patterns

Systematic code quality review using SOLID principles, code smell detection, and refactoring patterns

Use when executing implementation plans with independent tasks in the current session. Subagents follow a two-stage review loop.

Core Web Vitals optimization, code splitting, and React performance patterns

Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches the code-reviewer agent.

Verifying the structural integrity of knowledge JSON and workflow markdown files.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires running verification commands and confirming output before making any success claims; evidence before assertions always.

Spawning subagents dynamically, parent-child agent communication, task delegation and result aggregation, resource management and cleanup

Build stateful agents and workflows with LangGraph 1.x

Onboard existing repositories into the Antigravity Agent Factory ecosystem

Convert team workshop outputs to project management artifacts

Statistical analysis, predictive modeling, and automated insight generation