Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints.
Start a fresh conversation. Replace the highlighted placeholders.
Use antigravity-workflows to run the best-fit multi-phase workflow for [concrete outcome] on [target application or repository], and deliver the resulting artifacts, validation evidence, risks, and next actions.
Required inputs
[concrete outcome]
[target application or repository]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: antigravity-workflowsdescription: "Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints."risk: nonesource: selfdate_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:
docs/users/workflows.md for human-readable playbooks and recorded cases.
data/workflows.json for machine-readable workflow metadata.
Those paths belong to the AAS repository, not necessarily the user's project.
When they are absent from a standalone installation, use the bundled
workflow cards. Do not invent missing files,
fetch a moving replacement silently, or create AAS documentation in the project.
How to Run This Skill
Identify the user's concrete outcome.
Propose the 1-2 best matching workflows.
Follow an already specified workflow; ask only when the choice materially changes scope.
Execute step-by-step:
Announce current step and expected artifact.
Invoke recommended skills for that step.
Verify completion criteria before moving to next step.
If a check fails, retain the failure, fix the relevant input or implementation,
rerun that check, and continue only after it passes. If a prerequisite is
unavailable, report that exact blocked step and continue independent work.
Review the exact skill IDs and their support files before installation. Use the
supported direct installer's --dry-run with the selected IDs and destination;
install only within the user's authorization. Core composition and immutable
plans remain review artifacts and do not install the skills.
If preview fails, correct the ID, release, prerequisite or destination and
preview again. A failed preview never authorizes installation.