在任何创造性工作之前你必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前探索用户意图、需求和设计。
当面对 2 个以上可在无共享状态或顺序依赖下独立处理的任务时使用
当你有一份已编写完成的实现计划,需要在独立会话中执行并设置审查检查点时使用
当实现完成、所有测试通过、且需要决定如何整合工作时使用 - 通过提供合并、PR 或清理的结构化选项,指导完成开发工作
在接收代码评审反馈、实施建议之前使用,尤其是当反馈看起来不清晰或在技术上有疑问时 - 要求技术严谨性和验证,不是表演性赞同或盲目实施
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Superpowers 是一套面向编程 agent 的技能集,包含完整的软件开发方法论(头脑风暴 → 计划 → TDD → 代码评审等)。本仓库是 Superpowers 的中文翻译版,支持 OpenCode、Claude Code 与 Codex。
各平台需分别安装。即使已在其他平台安装,也需在每个平台单独安装一次。
在 opencode.json(全局或项目级)中添加:
{
"plugin": ["~/code/superpowers-zh"]
}
或从 git 安装:
{
"plugin": ["superpowers-zh@git+https://github.com/SameTrouble/superpowers-zh.git"]
}
重启 OpenCode 后,发送「告诉我你的超能力」验证安装。
注册市场:
/plugin marketplace add SameTrouble/superpowers-zh
安装插件:
/plugin install superpowers-zh@superpowers-zh-dev
重启 Claude Code 后,发送「告诉我你的超能力」验证安装。
本翻译版未提交到 Codex 官方市场,需先添加本仓库为市场源,再安装插件。
添加本仓库为市场源:
codex plugin marketplace add SameTrouble/superpowers-zh
打开插件目录:
/plugins
切换到 superpowers-zh-dev 市场标签,找到 Superpowers 中文版,选择 Install plugin。
superpowers-zh-devSuperpowers 中文版,点击 + 按提示完成安装安装后,发送「告诉我你的超能力」验证安装。
注:Codex 不提供 SessionStart hook,依靠 Codex 自身的技能触发机制加载 bootstrap。
本仓库翻译自 obra/superpowers,独立演进,手动同步上游更新。
MIT
npx claudepluginhub sametrouble/superpowers-zh --plugin superpowers-zh31 curated Swift and Apple platform agent skills for SwiftUI, SwiftData, Swift concurrency, testing, and more.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.