11 KiB
Antigravity Workflows
Workflow playbooks to orchestrate multiple skills with less friction.
What Is a Workflow?
A workflow is a guided, step-by-step execution path that combines multiple skills for one concrete outcome.
- Bundles tell you which skills are relevant for a role.
- Workflows tell you how to use those skills in sequence to complete a real objective.
If bundles are your toolbox, workflows are your execution playbook.
How to Use Workflows
- Install the repository once (
npx antigravity-awesome-skills). - Pick a workflow matching your immediate goal.
- Execute steps in order and invoke the listed skills in each step.
- Keep output artifacts at each step (plan, decisions, tests, validation evidence).
You can combine workflows with bundles from bundles.md when you need broader coverage.
Workflow: Ship a SaaS MVP
Build and ship a minimal but production-minded SaaS product.
Related bundles: Essentials, Full-Stack Developer, QA & Testing, DevOps & Cloud
Prerequisites
- Local repository and runtime configured.
- Clear user problem and MVP scope.
- Basic deployment target selected.
Steps
-
Plan the scope
- Goal: Define MVP boundaries and acceptance criteria.
- Skills:
@brainstorming,@concise-planning,@writing-plans - Prompt example:
Use @concise-planning to define milestones and acceptance criteria for my SaaS MVP.
-
Build backend and API
- Goal: Implement core entities, APIs, and auth baseline.
- Skills:
@backend-dev-guidelines,@api-patterns,@database-design - Prompt example:
Use @backend-dev-guidelines to create APIs and services for the billing domain.
-
Build frontend
- Goal: Ship core user flow with clear UX states.
- Skills:
@frontend-developer,@react-patterns,@frontend-design - Prompt example:
Use @frontend-developer to implement onboarding, the empty state, and the initial dashboard.
-
Test and validate
- Goal: Cover critical user journeys before release.
- Skills:
@test-driven-development,@browser-automation,@go-playwright(optional, Go stack) - Prompt example:
Use @browser-automation to create E2E tests for the signup and checkout flows. - Go note: If the QA project and tooling are in Go, prefer
@go-playwright.
-
Ship safely
- Goal: Release with observability and rollback plan.
- Skills:
@deployment-procedures,@observability-engineer - Prompt example:
Use @deployment-procedures for a release checklist with rollback steps.
Workflow: Security Audit for a Web App
Run a focused security review from scope definition to remediation validation.
Related bundles: Security Engineer, Security Developer, Observability & Monitoring
Prerequisites
- Explicit authorization for testing.
- In-scope targets documented.
- Logging and environment details available.
Steps
-
Define scope and threat model
- Goal: Identify assets, trust boundaries, and attack paths.
- Skills:
@ethical-hacking-methodology,@threat-modeling-expert,@attack-tree-construction - Prompt example:
Use @threat-modeling-expert to map critical assets and trust boundaries for my web app.
-
Review auth and access control
- Goal: Detect account takeover and authorization flaws.
- Skills:
@broken-authentication,@auth-implementation-patterns,@idor-testing - Prompt example:
Use @idor-testing to verify unauthorized access on multitenant endpoints.
-
Assess API and input security
- Goal: Uncover high-impact API and injection vulnerabilities.
- Skills:
@api-security-best-practices,@api-fuzzing-bug-bounty,@top-web-vulnerabilities - Prompt example:
Use @api-security-best-practices to audit auth, billing, and admin endpoints.
-
Harden and verify
- Goal: Convert findings into fixes and verify evidence of mitigation.
- Skills:
@security-auditor,@sast-configuration,@verification-before-completion - Prompt example:
Use @verification-before-completion to prove that the mitigations are effective.
Workflow: Build an AI Agent System
Design and deliver a production-grade agent with measurable reliability.
Related bundles: Agent Architect, LLM Application Developer, Data Engineering
Prerequisites
- Narrow use case with measurable outcomes.
- Access to model provider(s) and observability tooling.
- Initial dataset or knowledge corpus.
Steps
-
Define target behavior and KPIs
- Goal: Set quality, latency, and failure thresholds.
- Skills:
@ai-agents-architect,@agent-evaluation,@product-manager-toolkit - Prompt example:
Use @agent-evaluation to define benchmarks and success criteria for my agent.
-
Design retrieval and memory
- Goal: Build reliable retrieval and context architecture.
- Skills:
@llm-app-patterns,@rag-implementation,@vector-database-engineer - Prompt example:
Use @rag-implementation to design chunking, embedding, and retrieval pipelines.
-
Implement orchestration
- Goal: Implement deterministic orchestration and tool boundaries.
- Skills:
@langgraph,@mcp-builder,@workflow-automation - Prompt example:
Use @langgraph to implement the agent graph with fallbacks and human-in-the-loop flows.
-
Evaluate and iterate
- Goal: Improve weak points with a structured loop.
- Skills:
@agent-evaluation,@langfuse,@kaizen - Prompt example:
Use @kaizen to prioritize fixes for the failure modes identified by testing.
Workflow: QA and Browser Automation
Create resilient browser automation with deterministic execution in CI.
Related bundles: QA & Testing, Full-Stack Developer
Prerequisites
- Test environments and stable credentials.
- Critical user journeys identified.
- CI pipeline available.
Steps
-
Prepare test strategy
- Goal: Scope journeys, fixtures, and execution environments.
- Skills:
@e2e-testing-patterns,@test-driven-development - Prompt example:
Use @e2e-testing-patterns to define a minimal but high-impact E2E suite.
-
Implement browser tests
- Goal: Build robust test coverage with stable selectors.
- Skills:
@browser-automation,@go-playwright(optional, Go stack) - Prompt example:
Use @go-playwright to implement browser automation in a Go project.
-
Triage and harden
- Goal: Remove flaky behavior and enforce repeatability.
- Skills:
@systematic-debugging,@test-fixing,@verification-before-completion - Prompt example:
Use @systematic-debugging to classify and resolve flaky behavior in CI.
Workflow: Design a DDD Core Domain
Model a complex domain coherently, then implement tactical and evented patterns only where justified.
Related bundles: Architecture & Design, DDD & Evented Architecture
Prerequisites
- Access to at least one domain expert or product owner proxy.
- Current system context and integration landscape available.
- Agreement on business goals and key domain outcomes.
Steps
-
Assess DDD fit and scope
- Goal: Decide whether full DDD, partial DDD, or simple modular architecture is appropriate.
- Skills:
@domain-driven-design,@architecture-decision-records - Prompt example:
Use @domain-driven-design to evaluate if full DDD is justified for our billing and fulfillment platform.
-
Create strategic model
- Goal: Define subdomains, bounded contexts, and ubiquitous language.
- Skills:
@ddd-strategic-design - Prompt example:
Use @ddd-strategic-design to classify subdomains and propose bounded contexts with ownership.
-
Map context relationships
- Goal: Define upstream/downstream contracts and anti-corruption boundaries.
- Skills:
@ddd-context-mapping - Prompt example:
Use @ddd-context-mapping to model Checkout, Billing, and Inventory interactions with clear contract ownership.
-
Implement tactical model
- Goal: Encode invariants with aggregates, value objects, and domain events.
- Skills:
@ddd-tactical-patterns,@test-driven-development - Prompt example:
Use @ddd-tactical-patterns to design aggregates and invariants for order lifecycle transitions.
-
Adopt evented patterns selectively
- Goal: Apply CQRS, event store, projections, and sagas only where complexity and scale require them.
- Skills:
@cqrs-implementation,@event-store-design,@projection-patterns,@saga-orchestration - Prompt example:
Use @cqrs-implementation and @projection-patterns to scale read-side reporting without compromising domain invariants.
Machine-Readable Workflows
For tooling and automation, workflow metadata is available in data/workflows.json.