S

Superpowers

A shell-based agentic skills framework and dev methodology

PriceOpen SourceReviewed2026-04-17
Verdict — Ship
3 Ships1 Skips
Visit github.com

The Panel's Take

Superpowers is an open-source agentic skills framework and software development methodology built around shell-native tooling. Created by obra (Jesse Vincent), it earned the top trending spot on GitHub today with 1,645 stars — one of the highest single-day star velocities seen in April 2026. The project defines a collection of reusable "skills" — self-contained, composable capabilities that AI coding agents can call as shell commands. The philosophy emphasizes simplicity: rather than building complex Python orchestration layers, Superpowers bets on Unix-native scripts and a clean methodology that any agent (Claude Code, Cursor, etc.) can consume without framework lock-in. What makes Superpowers compelling is its timing and positioning. As the "CLAUDE.md skills" pattern popularized by Karpathy and others takes hold, Superpowers offers a structured, opinionated approach to organizing those skills at scale. The shellcode-first design means low overhead and near-universal compatibility — any agent that can run bash can use it.

Share this verdict

Superpowers verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/superpowers-obra-agentic-skills-shell-methodology-github-2026

Weekly AI Tool Verdicts

Get the next verdict in your inbox

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

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-obra-agentic-skills-shell-methodology-github-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/superpowers-obra-agentic-skills-shell-methodology-github-2026" alt="Superpowers Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![Superpowers Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/superpowers-obra-agentic-skills-shell-methodology-github-2026)](https://shiporskip.io/api/badge-click/superpowers-obra-agentic-skills-shell-methodology-github-2026)
Iframe widget
<iframe src="https://shiporskip.io/embed/superpowers-obra-agentic-skills-shell-methodology-github-2026" title="Superpowers ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

This is exactly the tooling I didn't know I needed. The shell-native approach means zero framework lock-in — works with Claude Code, Cursor, or whatever agent comes next. Jesse Vincent has been building great dev tools for decades and this has the same clean opinionated feel.

Helpful?

The documentation is still thin and the methodology isn't fully documented yet — this is really an early-stage release riding GitHub trending momentum. The skills ecosystem only has value once there's a critical mass of community-contributed skills, and we're not there yet.

Helpful?

Shell as the lingua franca of AI agents is an underrated bet. Unix pipelines have composed elegantly for 50 years — there's no reason that paradigm shouldn't extend to agentic skills. This could become the 'npm for agent capabilities' if the community rallies around it.

Helpful?

As someone who wants agents to actually do things without spending three hours configuring an orchestration framework, the shell-first approach is refreshing. I can write a skill in 10 lines of bash and it just works. That accessibility matters a lot for non-engineers trying to automate their workflows.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later