first-fluke/fullstack-starter
Overview
This skill is an automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates state via MCP Memory, and monitors progress end-to-end. It is built for production monorepos and handles planning, execution, verification, retries, and result collection. The orchestrator enforces verification gates and uses retry and clarification-debt policies to maintain quality.
How this skill works
On request it decomposes work into tasks, creates a session and task board in memory, and spawns subagents as independent CLI processes (gemini -p ... --approval-mode=yolo) without exceeding MAX_PARALLEL. It polls progress at configured intervals, runs mandatory verification (oh-my-ag verify) for each completed agent, applies retry logic on failures, and collects result files into a final summary. Memory reads/writes go through configurable MCP tools and ownership rules ensure clear file responsibilities.
When to use it
- When a feature requires multiple specialized agents working in parallel
- When you want end-to-end automated execution without manual agent management
- When delivering full-stack changes spanning backend, frontend, mobile, and QA
- When the user requests “run automatically” or “run in parallel”
- When reproducible session metrics and postmortems are required
Best practices
- Keep MAX_PARALLEL small for resource-constrained CI runners and increase in dedicated environments
- Provide structured task specifications so planners can decompose reliably
- Never bypass the verification gate—automated verify is mandatory for acceptance
- Attach relevant workspace context and previous artifacts to reduce clarification debt
- Monitor CD (Clarification Debt) and trigger RCA if CD thresholds are exceeded
Example use cases
- Implement a full-stack feature: spawn backend, frontend, mobile, QA agents in parallel and collect results
- Run a multi-component migration across services with coordinated verification and retries
- Automated release smoke test: spawn test agents for API, UI, and mobile then aggregate pass/fail reports
- Perform scoped refactor across repo modules where each subagent handles a specific package
- Generate a consolidated developer handoff with lessons-learned if clarification debt is high
FAQ
The orchestrator polls status, runs verification for completed agents, and follows retry logic (30s then 60s waits). After retries are exhausted it reports failure and asks whether to continue or abort.
How is shared state managed between agents?
Shared state is stored via MCP Memory tools configured in mcp.json. Orchestrator owns session and task-board files; agents own their progress and result files, which orchestrator reads.
17 skills
This skill automates multi-agent orchestration by spawning parallel subagents, coordinating via memory bus, and monitoring progress for complex workflows.
This skill conducts comprehensive QA reviews for security, performance, accessibility, and test coverage, guiding remediation with concrete file-level fixes.
This skill streamlines monorepo development workflows by automating mise tasks, CI/CD, and migrations to boost productivity across multi-language apps.
This skill helps you create conventional commits with project-specific branch rules and proper scope, ensuring consistent history across the monorepo.
This skill helps you build cross-platform mobile apps with Flutter and React Native, enforcing clean architecture, offline-first design, and platform-specific
This skill helps product managers decompose complex requests into actionable tasks with priorities and dependencies for faster, clearer delivery.
This skill helps you build accessible, design-faithful React and Next.js UI using shadcn/ui, server components, and design tokens for performance.
This skill guides multi-agent coordination for complex projects, decomposing tasks with PM Agent, spawning parallel tasks, and ensuring QA review.
This skill helps you create, schedule, and optimize social media content across platforms to boost engagement and achieve growth goals.
This skill helps you design, standardize, and reuse Terraform modules with best practices for structuring, naming, and documentation.
This skill automates pull request creation using GitHub CLI, generates conventional-commit-based titles and bodies for clear, high-quality PRs.
This skill helps you safely manage Terraform state by importing, moving, or removing resources while preserving stability.
This skill scaffolds new Terraform modules following library standards, creating structure, basic files, and README to accelerate module development.
This skill guides modular and file-based FastAPI routing to improve maintainability and scalability across complex APIs.
This skill provides production-ready FastAPI project templates and patterns to accelerate starting new services and standardize architecture.
This skill guides designing and operating cloud infrastructure with IaC, CI/CD, observability, and SRE practices for reliable deployments.
This skill guides you through migrating GCP projects end-to-end, including databases, buckets, container images, and Terraform configurations for a seamless
