EasyGlobe EasyGlobe
Back to Skills Hub

Skill Detail

Superpowers Skill

Superpowers · github

Structures multi-step development with plans, subagents, and TDD.

Skill Overview

Structures multi-step development with plans, subagents, and TDD.

Superpowers Search Terms

This page targets users searching for Superpowers Skill, download, installation, README, Skill URL, and usage guide.

SuperpowersSuperpowers SkillSuperpowers skillsSuperpowers downloadSuperpowers installationSuperpowers usage guideSuperpowers READMESuperpowers Skill URLSuperpowers Claude SkillSuperpowers Codex Skill

Resource Type

Agent Skills

Categories

Development, Meta & Tools, Testing

Tags

Planning, Subagents, TDD

The download is a local Markdown skill file saved by EasyGlobe and deployable with the site to GitHub and Cloudflare.

Detailed Skill Introduction

What Superpowers is for

Superpowers is an AI agent skill resource for Development, Meta & Tools, Testing workflows. Based on the archived project material, its core value is: Structures multi-step development with plans, subagents, and TDD.. People landing on this page are likely searching for Superpowers, Superpowers download, Superpowers installation, Superpowers README, Superpowers Skill URL, or platform-specific terms such as Claude Skills, Codex Skills, Gemini Skills, Kimi Skills, and GLM Skills. This detail page brings those signals together so a user can understand what the skill does before opening the original project.

README summary

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.

README capability notes

**Testing**

  • **test-driven-development** - RED-GREEN-REFACTOR cycle (includes testing anti-patterns reference)

**Debugging**

  • **systematic-debugging** - 4-phase root cause process (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques)
  • **verification-before-completion** - Ensure it's actually fixed

**Collaboration**

  • **brainstorming** - Socratic design refinement
  • **writing-plans** - Detailed implementation plans
  • **executing-plans** - Batch execution with checkpoints
  • **dispatching-parallel-agents** - Concurrent subagent workflows
  • **requesting-code-review** - Pre-review checklist
  • **receiving-code-review** - Responding to feedback
  • **using-git-worktrees** - Parallel development branches...

README usage notes

1. **brainstorming** - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.

2. **using-git-worktrees** - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.

3. **writing-plans** - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.

4. **subagent-driven-development** or **executing-plans** - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints.

5....

README setup and configuration notes

Installation differs by harness. If you use more than one, install Superpowers separately for each one.

README setup and configuration notes

Superpowers updates are somewhat coding-agent dependent, but are often automatic.

Workflow fit and practical value

The current taxonomy places Superpowers under Development, Meta & Tools, Testing, with tags such as Planning, Subagents, TDD. That means the skill should be evaluated through the lens of repeatable work: what task it helps an AI agent perform, what context the agent needs, what output a user should expect, and whether the workflow can be reused as a team SOP. The archived README is used as the first source of truth whenever it includes feature lists, examples, setup notes, or usage guidance. The local Markdown download is useful for review, internal documentation, and adapting the instructions into your own agent skills repository.

Installation, usage, and platform notes

Installation differs by harness. If you use more than one, install Superpowers separately for each one. 1. brainstorming - Activates before writing code....

Installation

Installation differs by harness. If you use more than one, install Superpowers separately for each one.

Usage

1. **brainstorming** - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.

2. **using-git-worktrees** - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.

3. **writing-plans** - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.

4. **subagent-driven-development** or **executing-plans** - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints.

5. **test-driven-development** - Activates during implementation. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.

6. **requesting-code-review** - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.

7. **finishing-a-development-branch** - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.

**The agent checks for relevant skills before any task.** Mandatory workflows, not suggestions.

Capabilities

**Testing**

  • **test-driven-development** - RED-GREEN-REFACTOR cycle (includes testing anti-patterns reference)

**Debugging**

  • **systematic-debugging** - 4-phase root cause process (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques)
  • **verification-before-completion** - Ensure it's actually fixed

**Collaboration**

  • **brainstorming** - Socratic design refinement
  • **writing-plans** - Detailed implementation plans
  • **executing-plans** - Batch execution with checkpoints
  • **dispatching-parallel-agents** - Concurrent subagent workflows
  • **requesting-code-review** - Pre-review checklist
  • **receiving-code-review** - Responding to feedback
  • **using-git-worktrees** - Parallel development branches
  • **finishing-a-development-branch** - Merge/PR decision workflow
  • **subagent-driven-development** - Fast iteration with two-stage review (spec compliance, then code quality)

**Meta**

  • **writing-skills** - Create new skills following best practices (includes testing methodology)
  • **using-superpowers** - Introduction to the skills system

Supported Platforms

Use this skill as a reference template for these AI agents, model workflows, or team SOPs.

Claude SkillsCodex SkillsGemini SkillsKimi SkillsGLM SkillsChatGPT Skills

Configuration & Updates

Superpowers updates are somewhat coding-agent dependent, but are often automatic.

README Command Examples

bash
/plugin install superpowers@claude-plugins-official
bash
/plugin marketplace add obra/superpowers-marketplace
bash
/plugin install superpowers@superpowers-marketplace

Tags

PlanningSubagentsTDD

FAQ

What is Superpowers Skill?

Structures multi-step development with plans, subagents, and TDD.

Who should use Superpowers?

Use this skill if your team, operator, developer, or AI agent works on Development, Meta & Tools, Testing workflows.

When should you use Superpowers Skill?

Use it when a task involves Planning, Subagents, TDD, or when the workflow should become a Claude Skill, Codex Skill, Gemini Skill, Kimi Skill, GLM Skill, or team SOP.

How do you download Superpowers Skill?

Use the “Download Skill File” button near the top of the page or in the Skill Information panel. The local Markdown file saved by EasyGlobe is manual-superpowers.md.

How do you install Superpowers Skill?

Check the Installation section on this page. If the archived README does not include an explicit installation section, open the Skill URL and follow the official README, platform documentation, or marketplace instructions.

How do you use Superpowers Skill?

Check the Usage, Capabilities, and README summary sections. The page extracts usage notes, command examples, and workflow context from the archived README where available.

Does Superpowers Skill work with Claude, Codex, Gemini, Kimi, and GLM?

This page packages the resource as reusable AI agent skill material for Claude Skills, Codex Skills, Gemini Skills, Kimi Skills, GLM Skills, ChatGPT Skills or team SOPs. Actual runtime compatibility depends on the official instructions at the Skill URL.

Where is the Skill URL for Superpowers Skill?

The Skill URL is shown in the Skill Information panel. You can also use the “Open Original Skill” button near the top of the page to open the original project or official page.

What is the difference between the local download and the Skill URL?

The local download is an EasyGlobe-saved Markdown copy for archiving, reading, and reuse. The Skill URL points to the original project, official documentation, or marketplace page for the latest instructions.