By LZY-Ricardo
Enhanced skills library for Claude Code: TDD, debugging, collaboration, documentation persistence, and requirement decomposition
Use when implementing any feature or bugfix, before writing implementation code
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when a requirement is large, vague, or involves multiple subsystems — before brainstorming or planning. Decomposes into independent sub-projects with clear boundaries, dependencies, and priorities.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when finishing a development branch or sub-project — before merge or PR. Produces a concise completion dashboard that shows delivery status, artifact links, known issues, and next steps.
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.
This is an enhanced fork of obra/superpowers with documentation persistence and requirement decomposition skills.
这是 obra/superpowers 的增强版 fork,增加了文档沉淀和需求拆分能力。
For detailed enhanced workflow documentation, see ENHANCED.md.
详细增强流程文档请参阅 ENHANCED.md。
8 new enhanced skills / 8 个新增增强 skill:
| Skill | Purpose / 用途 |
|---|---|
decomposing-requirements | Break large requirements into sub-projects / 将大需求拆分为子项目 |
init-enhanced-workflow | One-time project setup / 一次性项目初始化 |
using-enhanced-workflow | Master flow reference / 总流程参考 |
documenting-execution | Record task progress / 记录任务执行进度 |
documenting-verification | Record verification results / 记录验证结果 |
documenting-debugging | Record debugging sessions / 记录调试过程 |
documenting-review | Record code review findings / 记录代码审查发现 |
documenting-completion | Write completion summary / 编写完成总结 |
All 14 original skills are preserved. See GETTING-STARTED.md (English) / GETTING-STARTED.zh-CN.md (中文) for the install/use guide, and MAINTENANCE.md for development and maintenance guidance.
Note: The enhanced skill count above includes only repo-shipped workflow skills. Local maintenance skills are intentionally kept outside this repository.
保留了全部 14 个原始 skill。 快速安装/使用请参阅 GETTING-STARTED.md(英文)或 GETTING-STARTED.zh-CN.md(中文),开发和维护指南请参阅 MAINTENANCE.md。
说明: 上面的增强 skill 数量只统计仓库内共享工作流 skill。本地维护型 skill 会有意保留在仓库外。
Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
Give your agent Superpowers: Claude Code, Codex CLI, Codex App, Factory Droid, Gemini CLI, OpenCode, Cursor, GitHub Copilot CLI.
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 a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. In this enhanced fork, review loops are reviewer-aware: after a fix, the main session verifies the change and prefers the original reviewer for re-checks before falling back to a fresh reviewer. 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.
If Superpowers has helped you do stuff that makes money and you are so inclined, I'd greatly appreciate it if you'd consider sponsoring my opensource work.
Thanks!
Install this enhanced version from the fork repository. Installation differs by harness.
Register the marketplace:
/plugin marketplace add LZY-Ricardo/superpowers-enhanced
Install the plugin:
/plugin install superpowers@superpowers-enhanced
Reload plugins:
/reload-plugins
If /plugin commands don't work in your environment, see the manual install fallback in GETTING-STARTED.md.
If you want the original version without enhanced skills, use the official marketplace/plugin instructions for the upstream project instead of this fork.
Register this repository as a marketplace:
codex plugin marketplace add LZY-Ricardo/superpowers-enhanced
Install the plugin:
codex plugin add superpowers@superpowers-enhanced
Or use the plugin browser:
/plugins
npx claudepluginhub lzy-ricardo/superpowers-enhancedCore 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
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.
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.
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.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation