Self-hosted alternatives to superpowers-lab
5 self-hosted AI Skills apps to use instead, best rated first.
Top picks
- C

claude-to-deerflow
Launchclaude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code
Self-hosted
- O

open-notebook
Launchopen-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O
Self-hosted
- R

Reactive Resume
LaunchReactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish
Open sourceSelf-hosted
- S

self-hosted-funnel-launch
LaunchSelf-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a
Self-hosted
- G

get-convex/convex-backend
LaunchConvex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca
Self-hosted
About superpowers-lab

superpowers-lab
Evaluate experimental Claude workflow skills in an isolated lab
superpowers-lab is an agent skill for evaluating an experimental Claude workflow skill in an isolated lab before you adopt it. It is for comparing an experiment from the upstream Superpowers lab with your current baseline, using a reproducible task. The skill's workflow picks one experiment, reads its instructions, status, prerequisites and licence, then defines a small representative task with success criteria, time and cost limits, and the files and tools each run may access. It runs the task first with the baseline setup and records the outputs and failures, then runs it again with the experimental skill in an isolated workspace under the same permissions. It compares the actual results, separates observed improvements from subjective preferences, and decides whether to keep, revise or reject the experiment, with a rollback plan if adoption is proposed. The entry does not bundle the lab's experiments, so you must obtain them from the upstream lab and review their full content and any commands before you load them. Use it when you are deciding whether a new workflow skill is worth adopting.
- Price
- Free
- Made by
- sickn33
- Category
- AI Skills
- Website
- github.com/sickn33/agentic-awesome-skills/superpowers-lab