Korean | 한국어

Superpowers Plus는 Claude Code, Codex, OpenCode 및 Gemini CLI와 같은 코딩 에이전트 환경을 위해 설계된 업스트림 superpowers]에서 진화 한 향상된 워크플로 기술입니다. 그것은 “설계 → 계획 → 실행 → 확인” 코어 워크플로우를 유지하지만 실행 라우팅, 서브 시약 컨텍스트 컨트롤, 그리고 업스트림에 의존하는 대신이 저장소 내의 설치 항목 포인트.

어떻게 작동합니까?

그것은 순간부터 시작 당신은 당신의 코딩 에이전트를 불. 당신이 무언가를 짓는 것을 볼 때, 그것은 doesn’t 그냥 코드를 작성하려고. 대신, 그것은 다시 단계를하고 당신이 정말로해야 할 일을 묻습니다.

대화에서 spec을 볶아지면 실제로 읽고 소화하기에 충분히 펑크에서 당신을 보여줍니다.

디자인에 서명 한 후, 에이전트는 가난한 맛과 열정적 인 주니어 엔지니어를 위해 충분히 명확한 구현 계획을 함께 넣어, 심사, 프로젝트 컨텍스트 없음, 그리고 다음을 테스트에 전환. 그것은 진실한 빨강/녹색 TDD, YAGNI (You Aren’t Gonna 필요 그것) 및 DRY를 강조합니다.

Superpowers Plus

English | 中文

Superpowers Plus is an enhanced workflow skill set evolved from upstream superpowers, designed for coding agent environments like Claude Code, Codex, OpenCode, and Gemini CLI. It retains the “design → plan → execute → verify” core workflow but unifies execution routing, subagent context control, and installation entry points within this repository instead of relying on the upstream.

How it works

It starts from the moment you fire up your coding agent. As soon as it sees that you’re building something, it doesn’t just jump into trying to write code. Instead, it steps back and asks you what you’re really trying to do.

Once it’s teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.

After you’ve signed off on the design, your agent puts together an implementation plan that’s clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren’t Gonna Need It), and DRY.

Next up, once you say “go”, it launches an executing-plans process that automatically chooses parallel or serial subagent routing based on task dependency, then inspects and reviews the work as it goes. It’s not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together.

There’s a bunch more to it, but that’s the core of the system. And because the skills trigger automatically, you don’t need to do anything special. Your coding agent just has Superpowers Plus.

Key Changes from Upstream Superpowers

Superpowers Plus tracks upstream superpowers closely — including its full execution model (executing-plans for parallel-session execution and subagent-driven-development for same-session execution). On top of upstream, this fork adds the following.

Additional skills (available, invoke explicitly when relevant):

• bootstrapping-repository-memory / curating-repository-memory — initialize and maintain durable, repository-level memory.
• acceptance-testing / writing-acceptance-criteria — derive acceptance criteria from an approved spec and verify against them.
• distilling-lessons — capture reusable lessons into memory.

These extra skills are not wired into the default workflow automatically — invoke them by name when you need them.

Localization and multi-harness install:

• Chinese documentation (README.zh-CN and install guides).
• Install entry points unified to this repository for Claude Code, Cursor, Codex, OpenCode, and Gemini CLI.

This is not a complete changelog, but rather the differences users need to know.

Installation

Superpowers Plus installation entry points are unified to this repository:

• GitHub: https://github.com/xhyqaq/superpowers-plus