Antigravity Workflows
Chain multiple Antigravity skills in order for SaaS MVP delivery, security audits, agent builds, or browser QA without hand-picking each skill.
Overview
Antigravity Workflows is an agent skill most often used in Build (also Ship, Validate) that turns a complex objective into an ordered sequence of Antigravity skill invocations with validated artifacts at every step.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill antigravity-workflowsWhat is this skill?
- Confirms objective and scope, then selects the best-matching Antigravity workflow before any steps run
- Executes workflow steps strictly in order with one concrete artifact per step (plan, build, test, release)
- Ships a five-part completion report: completed steps, artifacts, validation evidence, open risks, suggested next action
- Hard guardrails: no destructive actions without explicit approval; explicit authorization for security testing; gap call
- Built-in patterns for SaaS MVP delivery, security audits, AI agent builds, and browser QA
- One concrete artifact required per workflow step
- Four step artifact types: plan, build, test, release
- Five-part completion format: steps, artifacts, validation, risks, next action
Adoption & trust: 631 installs on skills.sh; 40.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a multi-skill objective in the Antigravity ecosystem but no ordered workflow, per-step artifacts, or validation gates before moving on.
Who is it for?
Solo builders running Antigravity-backed SaaS MVP, security audit, AI agent, or browser QA objectives who want step-by-step artifacts and guardrails.
Skip if: Single-skill tasks, builders outside the Antigravity skill set, or runs where you refuse per-step validation or explicit approval for destructive or security-sensitive actions.
When should I use this skill?
Use when the user wants to combine several skills without manually selecting each one, or when the goal is SaaS MVP delivery, security audits, AI agent builds, or browser QA through guided Antigravity workflows.
What do I get? / Deliverables
You complete a guided workflow with documented artifacts per step, validation evidence, surfaced risks, and a clear suggested next action—without manually picking each skill.
- Per-step workflow artifacts (scope/milestone docs, implementation notes, test triage, rollout checklist)
- Validation evidence recorded before advancing steps
- Workflow completion report with open risks and suggested next action
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The playbook centers on plan-build-test-release orchestration and milestone artifacts, which solo builders typically invoke once they are executing a multi-step product delivery rather than doing one-off research. PM is the best shelf because the skill’s contract is sequencing work, scope confirmation, per-step deliverables, and completion reporting—not a single integration or test harness.
Where it fits
Produce a scope document or milestone checklist as the first workflow artifact before build and test steps begin.
Run plan-build-test-release in order for a SaaS MVP without manually choosing each Antigravity skill between steps.
Guide an AI agent build through sequential skill invocations with implementation notes captured each step.
Execute browser QA workflow steps and record test results plus failure triage before continuing.
Chain a security audit workflow only after explicit authorization and document risks in the completion report.
How it compares
Use instead of manually invoking Antigravity skills one at a time without ordered steps, artifacts, or completion reporting.
Common Questions / FAQ
Who is antigravity-workflows for?
Solo and indie builders (and small teams) who already use Antigravity skills and need orchestrated plan-build-test-release style runs for MVPs, audits, agents, or browser QA.
When should I use antigravity-workflows?
Use it when combining several Antigravity skills without hand-selection: during Build/PM to sequence MVP implementation, Ship/testing for browser QA with triage artifacts, Ship/security for authorized audits, or Build/agent-tooling for guided agent construction—with scope confirm
Is antigravity-workflows safe to install?
The skill declares risk none and emphasizes explicit approval for destructive actions and security testing; review the Security Audits panel on this Prism page and only authorize security workflows you own.
SKILL.md
READMESKILL.md - Antigravity Workflows
# Antigravity Workflows Implementation Playbook This document explains how an agent should execute workflow-based orchestration. ## Execution Contract For every workflow: 1. Confirm objective and scope. 2. Select the best-matching workflow. 3. Execute workflow steps in order. 4. Produce one concrete artifact per step. 5. Validate before continuing. ## Step Artifact Examples - Plan step -> scope document or milestone checklist. - Build step -> code changes and implementation notes. - Test step -> test results and failure triage. - Release step -> rollout checklist and risk log. ## Safety Guardrails - Never run destructive actions without explicit user approval. - If a required skill is missing, state the gap and fallback to closest available skill. - When security testing is involved, ensure authorization is explicit. ## Suggested Completion Format At workflow completion, return: 1. Completed steps 2. Artifacts produced 3. Validation evidence 4. Open risks 5. Suggested next action --- name: antigravity-workflows description: "Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA." risk: none source: self date_added: "2026-02-27" --- # Antigravity Workflows Use this skill to turn a complex objective into a guided sequence of skill invocations. ## When to Use This Skill Use this skill when: - The user wants to combine several skills without manually selecting each one. - The goal is multi-phase (for example: plan, build, test, ship). - The user asks for best-practice execution for common scenarios like: - Shipping a SaaS MVP - Running a web security audit - Building an AI agent system - Implementing browser automation and E2E QA ## Workflow Source of Truth Read workflows in this order: 1. `docs/WORKFLOWS.md` for human-readable playbooks. 2. `data/workflows.json` for machine-readable workflow metadata. ## How to Run This Skill 1. Identify the user's concrete outcome. 2. Propose the 1-2 best matching workflows. 3. Ask the user to choose one. 4. Execute step-by-step: - Announce current step and expected artifact. - Invoke recommended skills for that step. - Verify completion criteria before moving to next step. 5. At the end, provide: - Completed artifacts - Validation evidence - Remaining risks and next actions ## Default Workflow Routing - Product delivery request -> `ship-saas-mvp` - Security review request -> `security-audit-web-app` - Agent/LLM product request -> `build-ai-agent-system` - E2E/browser testing request -> `qa-browser-automation` - Domain-driven design request -> `design-ddd-core-domain` ## Copy-Paste Prompts ```text Use @antigravity-workflows to run the "Ship a SaaS MVP" workflow for my project idea. ``` ```text Use @antigravity-workflows and execute a full "Security Audit for a Web App" workflow. ``` ```text Use @antigravity-workflows to guide me through "Build an AI Agent System" with checkpoints. ``` ```text Use @antigravity-workflows to execute the "QA and Browser Automation" workflow and stabilize flaky tests. ``` ```text Use @antigravity-workflows to execute the "Design a DDD Core Domain" workflow for my new service. ``` ## Limitations - This skill orchestrates; it does not replace specialized skills. - It depends on the local availability of referenced skills. - It does not guarantee success without environment access, credentials, or required infrastructure. - For stack-specific browser automation in Go, `go-playwright` may require the corresponding skill to be present in your local skills repository. ## Related Skills - `concise-planning` - `brainstorming` - `workflow-automation` - `verification-before-completion`