antigravity-agent-factory

Automated governance, hook installation, pre-commit validation, branch isolation, and safe commit operations.

Enforcement of safety guardrails, axiom verification, secret scanning, and mutability protections.

Building and managing premium statistical dashboards, RAG explorer UIs, warehouse log monitors, and real-time visualization centers.

Integration of agent systems with blockchain protocols, contracts, event stores, reputation networks, and collective verification engines.

AI model configuration, LLM memoization, agentic RAG search, and vector library maintenance.

Catalog generation, reference link verification, workshop documentation building, and knowledge gap analysis.

Master system orchestration, blueprint rendering, project scaffolding, multi-agent debates, and SDLC stage validators.

FastAPI backend orchestration, MCP infrastructure servers/clients, and community integrations.

Unified management of episodic, semantic, procedural, and relational memory within the factory workspace.

High-performance management of Plane PMS using specialized scripts, persistent context, Jinja2 templates, and memory MCP integration.

Platform Application Bundle Protocol (PABP) management, MCP config generators, bundle importers, and compliance verifiers.

Systematic maintenance, debugging, updating, and health reporting for the agent factory codebase.

Validation of workspace schemas, JSON syntax verification, dependency audits, workflow structure checks, and catalog consistency.

Safe commit and release workflow with auto-sync, changelog updates, and learning from failures

Manage the Antigravity Dual-Storage Memory system (SQL + Vector) and implement cognitive lifecycle hooks.

Actively retrieve context from the Dual-Storage Cognitive Memory system (Qdrant & SQLite) for seamless IDE integration.

Platform-specific shell command considerations for Windows PowerShell and Unix shells

Use when you have a spec or requirements for a multi-step task, before touching code. Enforces bite-sized task granularity.

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

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Automated release management using semantic versioning and automated changelog maintenance.

Use when starting feature work that needs isolation from the current workspace - creates isolated git worktrees. Good for @Operator (PROPS).

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

Standardized agent creation and evaluation with mandatory schema validation

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

Standardized knowledge file creation and validation with mandatory schema validation

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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

Standardized workflow creation and evaluation with mandatory schema validation

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR.

Use when about to claim work is complete, fixed, or passing, before committing or closing tasks - requires running verification commands and confirming output before making any success claims.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

Use when implementing any feature or bugfix, before writing implementation code. Enforces the Iron Law of TDD.

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.

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

Send emails using the cached Google Workspace credentials.

Specialized skill for ingesting rag content

Send emails using the cached Google Workspace credentials.

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.

Parses an Agentic PRD (knowledge/prd.md) to extract structured configuration for automated project generation. Extracts Epics, Stories (with JSON acceptance criteria), NFRs, and AI components. Use when initializing a project or feature implementation from a verified PRD.