Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

superpowers-lab — Claude Code skill: what it does, how to install

Sets an evaluation workflow to test experimental upstream skills against a baseline in an isolated environment before adopting them.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add sickn33/agentic-awesome-skills --skill superpowers-lab -a claude-code
Open on GitHub

What superpowers-lab does

This skill standardizes the evaluation of experimental workflows before adopting them. The skill itself does not bundle experiments or fixtures, so you need to fetch them directly from the upstream superpowers-lab repository. Testing begins by setting a bounded task with explicit acceptance criteria, time limits, and disposable fixtures without production credentials.

The process relies on direct comparison. First, run the representative task using your baseline setup and record all failures alongside raw outputs. Next, inspect the experimental workflow files, verify every command, and run the same task in an isolated workspace under identical constraints.

Experimental guidance gives no production guarantees. Any differences in model parameters or tooling count as confounders rather than proven gains. Because adoption must remain separate from lab trials, you must prepare a rollback plan before rolling any workflow out.

What it helps with

  • benchmark experimental agent skills against a baseline configuration
  • test external workflow prompts in an isolated workspace using disposable fixtures
  • capture concrete failure modes and outputs before adopting community skills
  • prepare a rollback and removal plan for experimental agent additions

Example prompts for the agent

  • Evaluate an experimental workflow from superpowers-lab on a disposable bug fixture against our baseline.
  • Run the baseline task configuration without the experimental skill and record all observed failures.
  • Compare the isolated test run outputs and check if model settings caused the observed differences.

How to install superpowers-lab

1Skills CLI (Vercel)

npx skills add sickn33/agentic-awesome-skills --skill superpowers-lab -a claude-code

2Manually: put the files in place

~/.claude/skills/superpowers-lab/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/superpowers-lab/

From the same set80

The whole set →
docker-expert sickn33 A skill that turns your AI agent into a Docker reviewer for Dockerfiles, multi-stage builds and container security. Useful when images and Compose files need a second look. Claude Code CX Codex Cursor +1 27,200installs typescript-expert sickn33 A skill for TypeScript and JavaScript work: it reads your project setup, fixes type errors and speeds up type checking. Useful once a TS codebase gets big. Claude Code CX Codex Cursor +1 12,600installs browser-automation sickn33 This skill builds browser checks around observed UI state and explicit outcomes. Use it for UI workflows, timing failures, or authorised page-data collection. Claude Code CX Codex Cursor +1 6,700installs nextjs-supabase-auth sickn33 This skill wires Supabase Auth into the Next.js App Router with clients, middleware, OAuth callbacks, and Server Actions. Use it when you need protected routes and session handling. Claude Code CX Codex Cursor +1 6,500installs 3d-web-experience sickn33 Helps build and debug web 3D scenes, product configurators, and portfolios. Covers stack choice, model loading, scroll interaction, and performance checks. Claude Code CX Codex Cursor +1 5,200installs prisma-expert sickn33 This skill helps inspect Prisma schemas, migrations, and queries. Use it to investigate an error or review database changes before deployment. Claude Code CX Codex Cursor +1 4,200installs playwright-skill sickn33 Write and run Playwright browser tests directly in Claude Code: responsive design checks, login flows, form submissions, screenshots. Executes locally via Node with a visible browser window. Claude Code CX Codex Cursor +1 3,900installs game-development sickn33 Guides game architecture decisions, platform choices, and core loop structure. Directs the assistant to specialized sub-skills for web, mobile, PC, or VR. Claude Code CX Codex Cursor +1 3,800installs

Similar

tavily-research tavily-ai Runs deep web research via the Tavily CLI and returns a structured report with source citations. Useful for market reviews and multi-source technical comparisons. Claude Code CX Codex Cursor +1 21,900installs remembering-conversations obra Forces the assistant to search past conversations before claiming ignorance or guessing. It reads relevant snippets instead of entire transcripts, saving context window space. Claude Code CX Codex Cursor +1 9,200installs concept-workflow leonardomso Orchestrates end-to-end JavaScript concept documentation from research and drafting to testing and SEO checks. Useful when writing new guides or rebuilding existing pages. Claude Code CX Codex Cursor +1 322installs cli-anything-obsidian HKUDS Manage an Obsidian vault from the terminal: read, create, search, and update notes or run editor commands. It suits agents that need to work without the GUI. Claude Code CX Codex Cursor +1 917installs game-feel gamedev-skills Teaches the agent to add feedback to game actions: camera shake, hit-stop, eased tweens, squash and stretch, knockback. For mechanics that work but feel weightless. Claude Code CX Codex Cursor +1 9,400installs loading-assets phaserjs This skill guides Phaser 4 asset loading through the Loader plugin. Use it when working with preload(), spritesheets, audio, tilemaps, or load progress. Claude Code CX Codex Cursor +1 901installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about superpowers-lab

How to install superpowers-lab in Claude Code?

Run npx skills add sickn33/agentic-awesome-skills --skill superpowers-lab -a claude-code. You can also place the file directly at ~/.claude/skills/superpowers-lab/SKILL.md.

What is the purpose of superpowers-lab?

It provides a structured protocol to test, measure, and validate experimental skills against an isolated baseline before deciding to adopt or reject them.

Are the upstream experimental skills included in this package?

No, this skill does not bundle upstream experiments or fixtures. You must inspect and load them separately from the external repository.

Source text

SKILL.md · MIT 
---
name: superpowers-lab
description: "Evaluate experimental Claude workflow skills in an isolated lab with reproducible tasks, observed results, and explicit adoption criteria."
risk: safe
source: "https://github.com/obra/superpowers-lab"
date_added: "2026-02-27"
---

# Superpowers Lab

## When to Use
- You want to evaluate an experimental workflow from the upstream Superpowers lab before adopting it.
- You need a reproducible comparison of baseline behavior and a proposed skill.

## Workflow
1. Select one experiment from the [upstream lab](https://github.com/obra/superpowers-lab). Read its instructions, status, prerequisites, and license before using it; this entry does not bundle the lab's experiments.
2. Define a small representative task, success criteria, time/cost limits, and the files/tools each run may access. Use disposable fixtures and no production credentials.
3. Record the baseline agent/tool configuration and run the task without the experimental skill. Capture outputs, observed failures, and validation results.
4. Review the experiment's complete content and any commands before loading it. Run the same task with the experimental skill in an isolated workspace under the same permissions and acceptance criteria.
5. Compare the actual outputs and failures. Separate observed improvements from subjective preferences; record changed model/tool settings as confounders.
6. Decide whether to retain, revise, or reject the experiment. Keep production adoption separate from the lab run, and include a rollback/removal plan if adoption is proposed.

## Example
> Compare one lab workflow against our baseline on a disposable bug-fix fixture. Report tests and failure modes without installing it globally.

## Limitations
- Experimental guidance is not a production guarantee. Do not infer compatibility or improvement without a controlled run.
- The original experiment and its fixtures are external prerequisites; report unavailable materials.
- Do not execute unreviewed scripts, expand permissions, or use private production data for the experiment.

© sickn33 · MIT · sickn33/agentic-awesome-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor