S

Superpowers

Composable skill framework that forces coding agents to do it right

PriceFree / Open Source (MIT)Reviewed2026-04-03

Expert verdict

Ship

3-1
3 Ships1 Skips
Visit github.com

The Panel's Take

Superpowers is an open-source agentic skills framework by Jesse Vincent and Prime Radiant that enforces software engineering best practices on AI coding agents. Rather than hoping your agent follows TDD or writes a plan before coding, Superpowers makes these workflow steps mandatory through composable skills that any Claude Code, Cursor, or Codex agent must execute. The framework guides agents through seven sequential phases: design refinement, workspace setup with git worktrees, planning, execution with subagent delegation, testing with enforced RED-GREEN-REFACTOR, code review against the plan, and branch finalization. Skills are automatically checked for relevance at task start, not left as suggestions. With 134k total stars and 16k new this week — the most stars of any trending repo — Superpowers has struck a nerve. As AI-generated code proliferates without consistent quality controls, a framework that imposes software craftsmanship on agents has obvious appeal for teams trying to maintain codebases they can actually understand and maintain.

Share this verdict

Superpowers verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/superpowers-agentic-skills-coding-agents

Weekly AI Tool Verdicts

Get the next verdict in your inbox

7 critics review a new AI tool every day. Weekly digest — free.

Looking for Superpowers alternatives?

Compare Superpowers with every other Developer Tools tool reviewed by our panel.

See all Developer Tools alternatives

Embed this verdict

Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.

Ship · 7.5/10
HTML badge
<a href="https://shiporskip.io/api/badge-click/superpowers-agentic-skills-coding-agents" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/superpowers-agentic-skills-coding-agents" alt="Superpowers Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![Superpowers Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/superpowers-agentic-skills-coding-agents)](https://shiporskip.io/api/badge-click/superpowers-agentic-skills-coding-agents)
Iframe widget
<iframe src="https://shiporskip.io/embed/superpowers-agentic-skills-coding-agents" title="Superpowers ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

This solves the real problem with AI coding agents: they work great in isolation but create a mess at scale because they skip the boring engineering discipline. Mandatory planning, git worktrees for parallel work, and enforced test cycles are exactly the guardrails teams need.

Helpful?

Frameworks that force 'best practices' on AI agents add latency and overhead, and the best practices baked in here reflect one team's opinions. Mandatory RED-GREEN-REFACTOR on every task is overkill for many workflows, and the seven-phase pipeline will feel like bureaucracy for simple changes.

Helpful?

Superpowers is the first mature answer to 'how do organizations maintain software quality when AI writes most of the code?' Expect to see this pattern — agent constraint frameworks — become a standard layer in every serious engineering organization's AI toolchain.

Helpful?

Even for side projects and personal tools, having a structured workflow that catches problems before they compound is worth the overhead. The brainstorming skill alone — which asks clarifying questions before any implementation — has saved me from building the wrong thing multiple times.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later