superpowers-antigravity
Structured planning, testing, debugging, and code review workflows
All Skills in This Repository (15)
Pure Emerald Level Indicatorsusing-git-worktrees
Create isolated Git workspaces with branches and project setup scripts.
test-driven-development
Automates the Red-Green-Refactor cycle for writing and executing TDD tests.
systematic-debugging
Implement a 4-phase debugging process to identify and resolve root causes.
using-superpowers
Invoke coding skills in a logical sequence before starting tasks.
dispatching-parallel-agents
Dispatch multiple agents to execute independent tasks in parallel.
executing-plans
Execute implementation plans with review checkpoints and generate artifact summaries.
finishing-a-development-branch
Automates finishing development branches with test verification, merge/PR options, and cleanup.
browser-testing
Automate UI verification with screenshots, DOM inspection, and user flow recording.
brainstorming
Guide design exploration with clarifying questions and design documentation.
writing-plans
Create and review implementation plans for complex multi-step tasks.
requesting-code-review
Automate code review for Git commits using a reviewer subagent.
receiving-code-review
Verify code review feedback against the codebase and respond systematically.
Frequently Asked Questions
FAQPage SchemaHow to install superpowers-antigravity?โผ
Run `npx skills add roundpilot/superpowers-antigravity --all -g -y` in your terminal to install all skills in this suite globally.
What does superpowers-antigravity do?โผ
It gives your coding agent a structured workflow: brainstorm the idea, write a spec and plan, implement with test-driven development, and verify with code review before merging.
Which platforms does this suite support?โผ
This fork is built natively for Google Antigravity 2.0 only. For Claude Code, Codex, or Cursor support, use the upstream obra/superpowers repository instead.
How does it prevent bad fixes and flaky tests?โผ
The systematic-debugging skill forces root-cause investigation before any fix, and the test-driven-development skill requires a failing test before any production code is written.
Do I need to trigger the skills manually?โผ
No. The skills trigger automatically based on your request, so your agent follows the full workflow without any special commands from you.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core