Skip to content
Agentic Levels

Everything starts here.

GuestLocal progress only
PreferencesSign in
01Start with one taskBest first move for beginners.02Check your LevelMeasure where you are.03Score an AI resultFind the habit to practice first.04Return to Your WorkScores, links, and checkpoints.
Start here

Begin

HomeThe main entry point.New to AIStart with one useful task.
Know where you are

Measure

Check your LevelUse this after you have tried AI.Fluency ScoreScore an AI result you can review.
Build the habit

Learn

LevelsLessonsTracks
Find the reference

Library

PromptsReferenceResourcesCompare Tools
Turn it into work

Apply

Your Next MoveChoose what AI should change next.Tool SetupGet the tools ready.
Come back later

Return

Your WorkScores, links, and checkpoints.My PathContinue from your level.Updates
Site

Site

PricingAboutFAQ & FeedbackPreferences

© 2026 Fuentes Studio

Privacy·Terms
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

← Resources

How to use Superpowers

A design-first, TDD-enforced development methodology for coding agents, skills that auto-activate across Claude Code, Cursor, Codex, and more.

Without a methodology, every coding session starts from scratch and quality gates exist only when you remember to apply them. Superpowers is not a plugin collection. It is a structured development methodology implemented as composable skills: design and clarification before planning, structured planning before implementation, test-driven RED-GREEN-REFACTOR execution, git worktree isolation for parallel subagent work, and mandatory code review gates. Skills auto-activate based on development stage across Claude Code, Cursor, Codex, OpenCode, and GitHub Copilot CLI. No manual invocation required.

L3L4L5L6
Before you startClaude Code must be installed. Superpowers installs as a Claude Code plugin. Run `claude plugin --help` to confirm plugin support before proceeding.

Steps

01

Install Superpowers: three paths

The fastest path is claude plugin install. If Superpowers is not yet in your marketplace, clone the repo and copy the skills folder into `~/.claude/skills/`. If you only need one skill immediately, copy its SKILL.md into your skills folder and add the rest later. Always restart Claude Code after install.

Option A: plugin install (fastest)
claude plugin install superpowers # Restart Claude Code, then verify: /superpowers --help
02

Use writing-plans for every multi-step build

Before writing code for any task spanning more than one file or thirty minutes, run writing-plans. It interviews you about scope, dependencies, and risks, then produces a structured plan with atomic tasks and phase gates. Plans produced by writing-plans are the format executing-plans and gsd:execute-phase expect.

Start a planning session
/writing-plans # Superpowers asks structured questions about the task. # Answer in your own words, it extracts the structure.
03

Use executing-plans to run the plan phase by phase

Hand the plan file to executing-plans. It reads the current phase, works through its tasks with explicit verification gates, and will not advance until the gate passes. This is what makes long builds survivable. You cannot drift into Phase 4 while Phase 2 is half-done.

Execute your plan
/executing-plans [PATH_TO_PLAN_FILE]
[PATH_TO_PLAN_FILE]Path to the plan writing-plans produced e.g. .planning/2026-05-11-auth-flow-PLAN.md
04

Run finishing-a-development-branch before every PR

Before opening a pull request, run finishing-a-development-branch. It runs a pre-PR checklist: tests pass, types clean, unused imports removed, CLAUDE.md current, changelog updated, PR description drafted. Three minutes. Catches the things that turn a review into a back-and-forth.

Run before every PR
/finishing-a-development-branch
05

Wire code-review and systematic-debugging into daily use

code-review runs a structured review pass on a file or diff. It checks for logic errors, security issues, and anti-patterns in a consistent format. systematic-debugging refuses to jump to fixes before identifying the root cause. Both fire automatically at the right moments via the CLAUDE.md rule set. But you can also invoke them manually any time.

Manual review or debug
/code-review [FILE_OR_DIFF] # or: /systematic-debugging
[FILE_OR_DIFF]File path or 'diff' for current git diff e.g. src/lib/auth.ts

How do you know it worked?

  • `/superpowers --help` runs without errors after install.
  • writing-plans produced a structured plan file for a real task.
  • executing-plans advanced at least one phase with a visible verification gate.
  • finishing-a-development-branch caught at least one thing before a PR.
  • code-review produced structured feedback on a file in your current project.

If something looks off

Running executing-plans without a writing-plans output
executing-plans reads structured plan files, not arbitrary markdown. If you hand it a plan you wrote by hand it may misparse the phases. Always produce plans with writing-plans to guarantee the format.
Skipping finishing-a-development-branch 'just this once'
The pre-PR checklist exists for the PRs you are most confident about: those are the ones most likely to have a stale type or a missing changelog entry. Run it every time.
Not restarting Claude Code after install
Skills load at session start. A plugin install in the middle of a session does not take effect until you restart.

Skills & Commands Reference

Superpowers skills are invoked by the agent automatically based on context. You don't call them directly. Each skill is a mandatory workflow with specific steps. Knowing what each one enforces helps you understand why the agent behaves the way it does.

Command / SkillWhat it doesWhen to use it
writing-plansbasicEnforces research → spec → task breakdown → appendix before any code is writtenAny feature, fix, or change that touches more than one file, this fires first
executing-plansbasicImplements from an approved plan, one task at a time, with verification between tasksAfter a plan is written and approved, the implementation gate
finishing-a-development-branchbasicPre-merge checklist: tests pass, types clean, docs updated, PR description writtenBefore merging any branch, enforces quality gates before the code lands
requesting-code-reviewbasicStructures a code review request with context, scope, and specific questionsWhen you want a focused review rather than a general pass
receiving-code-reviewbasicProcesses review feedback systematically, categorizes, addresses, and confirms resolutionAfter receiving review comments, prevents cherry-picking easy feedback
systematic-debuggingbasicRoot-cause analysis before fixing: hypothesis → evidence → fix → verify. No blind changesAny bug where the cause is not immediately obvious, fires before any edit is made
test-driven-developmentadvancedRed-green-refactor loop: write failing test → make it pass → refactor → repeatNew functionality where correctness is critical and the interface is known upfront
using-git-worktreesadvancedCreates isolated worktrees for parallel work, prevents branch contaminationMultiple features or fixes running concurrently, each gets its own worktree
dispatching-parallel-agentsadvancedLaunches multiple specialized agents simultaneously on independent subtasksLarge tasks with clearly separable pieces, research + implementation + testing in parallel
subagent-driven-developmentadvancedDelegates discrete subtasks to isolated subagents with clean contextLong sessions approaching context limits, or subtasks that need fresh context to execute cleanly
verification-before-completionbasicBlocks task completion until all success criteria are verified with actual tool output, not assertionsFires before any task is marked done. 'Should work' is not verification
brainstormingbasicStructured exploration of approaches before committing, surfaces trade-offs and alternativesBefore entering plan mode on any non-trivial task
writing-skillsadvancedGuides creation of a new Superpowers skill following the spec, eval, and test formatYou want to capture a workflow you've validated into a reusable skill

See also

  • Get Shit Done: phase-level orchestration that pairs with Superpowers plans
  • skill-creator: maintain Superpowers skills with graded evals

Was this helpful?

← Back to ResourcesView on GitHub