SuperPowers
Give Claude Code a spine.

14 skills. One plugin install. Your coding agent goes from eager junior to disciplined engineer.

claude-code — superpowers active

The problem

Vanilla Claude Code is brilliant and undisciplined.

The model is great. What's missing is the scaffolding a senior engineer takes for granted.

It jumps straight to code

You ask for a feature. It starts typing files before asking what you're actually building.

It re-explains itself every session

Skills, conventions, style: all wiped at /clear. You become a human README read aloud.

It claims done without checking

"It should work now." Did you run the tests? Did you read the output? Probably not.

It writes tests after the fact

Or never. Vanilla Claude treats TDD as a suggestion. Superpowers treats deleting your pre-test code as a feature.

It debugs by vibes

Hypotheses stacked three deep, none verified. Symptom fixes. Shotgun refactors.

It reviews its own work

Single model, single pass, "looks good to me." No skeptical second reader.

How it works

From prompt to PR

Watch the full Superpowers workflow, or step through it manually.

15 steps from prompt to merged PR

Philosophy

Four beliefs, enforced.

Not aspirations. Not best practices. Iron laws with delete buttons and gates that stop the agent mid-turn.

01

Test-Driven Development

Write tests first. Always. Code written before a failing test gets deleted — not kept 'for reference.'

02

Systematic over ad-hoc

Process over guessing. Four debugging phases, one hypothesis at a time, no vibes-based fixes.

03

Complexity reduction

Simplicity as the primary goal. YAGNI, DRY, and tasks small enough a junior can follow them.

04

Evidence over claims

Run the command. Read the full output. Then claim the result. "Seems," "probably," "should" are red flags.

These aren't aspirations. They're gates. The agent is stopped, mid-response, until the rule is satisfied.

Install

One command. Done.

Pick your host, copy the command, reload. Skills are active on the next session.

claude code

The Anthropic marketplace. Single command.

What happens next

1. Plugin manifest registered
2. SessionStart hook wired
3. Next session loads all 14 skills
4. Ask to build something — brainstorming fires

Architecture

Five layers. One hook to rule them all.

No runtime orchestrator. The LLM steers itself, guided by the session-start injection and the 1% rule.

SessionStart hook
fires at startup, /clear, /compact
using-superpowers
bootloader, injects all skills
writing-skills
authoring guide
Workflow skills (10)
brainstormingwriting-plansexecuting-plansSDDparallel-agentsTDDdebuggingverificationcode-reviewgit-worktrees
code-reviewer agent
6 review activities, 3 severity buckets

What's not here:

no runtime orchestratorno MCP serverno telemetryno third-party depsno CLAUDE.md rewrites

Skills catalog

All 14 skills, grouped by what they actually do.

Tap a card for the trigger, iron law, collaborators, and the files it ships. Every claim is pulled from the actual SKILL.md in obra/superpowers.

14 of 14

Vanilla vs Superpowers

Same prompt. Different species of output.

The prompt below goes to vanilla Claude Code and to Claude Code with Superpowers installed. Watch the difference unfold.

prompt

Build me a rate limiter for our API.

Vanilla Claude Code
no skills, no plan, eager-to-please
jumps to code
Waiting for prompt...
  • No clarifying questions
  • No failing test first
  • No persistence / scale discussion
  • "Let me know if you want tests!"
Claude Code + Superpowers
skills auto-fire, process enforced
earns the code
0 → 0
skills auto-invoked
0 → 0
tasks with failing tests first
0 → 0
subagents reviewing work

Honest caveat: Superpowers isn't for everything.

  • One-off throwaway scripts? Overkill. Skip the skill.
  • Your team doesn't want TDD? The iron law will fight you.
  • No subagent support (e.g. Gemini CLI)? Two-stage review collapses to one pass.

How it compares

The discipline slot,not the capabilities slot.

Different tools, different angles. Superpowers gives your agent judgment — pair it with anything.

Superpowers

this page

Engineering methodology

Scope14 skills + 1 agent + 1 hook
OpinionHigh

Teams wanting disciplined agent-coding habits

Get Shit Done (GSD)

Spec-driven phase machine

Scope50+ commands, phase pipeline
OpinionVery high

Solo devs shipping long features reliably

anthropics/skills

The Skill format itself

ScopeReference set + spec
OpinionLow

Learning what a Skill is

wshobson/agents

Domain specialists (breadth)

Scope184 agents / 78 plugins
OpinionLow per-agent

On-demand domain experts

Impeccable

Frontend design quality

Scope1 skill + 18 commands
OpinionHigh within domain

Designers fighting AI-ugly UI

claude-code-templates

Meta-installer / dashboard

Scope100+ aggregated components
OpinionLow

Discovery / multi-source setup

Your workshop host

This page is a Datasense artifact.

Datasense runs hands-on workshops for teams adopting agentic coding. We distill frameworks like Superpowers down to what works in production, teach the mental models, and walk teams through real features together.

Resources & FAQ

Go deeper. Verify everything.

Frequently asked

Blunt answers.