Adapt superpowers for GigaBrain SuperAgents

[0xchetan]

Summary

• Forked from obra/superpowers (MIT license)
• Removed 9 IDE/git-specific skills that don't apply to SuperAgent containers
• Kept and adapted 5 core reasoning/development skills: systematic-debugging, test-driven-development, writing-plans, executing-plans, verification-before-completion
• Adapted examples to Python/pytest, removed platform plugin configs, updated cross-references

Test plan

• Verify skill loader picks up SKILL.md files from this repo when added to skills_manifest.yaml
• Test list_skills() shows the 5 new skills
• Test load_skill("systematic-debugging") returns full content
• Verify no broken cross-references in skill content

🤖 Generated with Claude Code

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the 'Superpowers' library for integration with GigaBrain SuperAgents. The primary goal is to streamline the skill set, making it highly relevant and efficient for autonomous agent operations by focusing on fundamental development and reasoning processes. The changes ensure that the adapted skills are aligned with the operational context of SuperAgents, promoting systematic debugging, test-driven development, and robust plan execution.

Highlights

• Skill Adaptation: Removed 9 IDE/git-specific skills that are not applicable to SuperAgent containers, focusing the library on core reasoning and development.
• Core Skills Retained: Kept and adapted 5 essential skills: systematic-debugging, test-driven-development, writing-plans, executing-plans, and verification-before-completion.
• Python/Pytest Examples: Updated all skill examples to use Python and Pytest, replacing previous TypeScript/npm examples for better relevance to SuperAgent workflows.
• Platform Agnostic: Removed all platform-specific plugin configurations (e.g., .claude-plugin, .cursor-plugin) and updated cross-references to ensure broader compatibility.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request significantly refactors the Superpowers project, adapting it for GigaBrain SuperAgents and OpenCode. Key changes include removing platform-specific configurations and skills (e.g., for Claude Code, Cursor, Git workflows), simplifying the brainstorm server to use zero-dependency Node.js built-ins, and updating documentation across various files like README.md, RELEASE-NOTES.md, and installation guides. The executing-plans skill has been streamlined, and the systematic-debugging and test-driven-development skills have been updated with Python examples and refined guidance. The visual-companion for brainstorming has been refactored for a non-blocking browser-terminal interaction model, and a document review system has been introduced for specs and plans. A review comment highlights a concern regarding the removal of valuable guidance on 'Integration Tests as Afterthought' and related anti-patterns from testing-anti-patterns.md, suggesting its re-instatement to maintain comprehensive TDD guidance.

[gemini-code-assist]

This file has been simplified, which is good for conciseness. However, the removal of 'Anti-Pattern 5: Integration Tests as Afterthought' and its related sections ('When Mocks Become Too Complex', 'TDD Prevents These Anti-Patterns') is a significant loss of valuable guidance. The principle that testing is an integral part of implementation, not an optional follow-up, is fundamental to TDD. I recommend re-instating this section to maintain the quality of the guidance for the agent. Additionally, the 'Quick Reference' table is missing the 'Over-complex mocks' anti-pattern, which was present before and is valuable.