rebelytics

rebelytics / one-skill-to-rule-them-all

Public

The meta-skill that builds and improves all your skills, including itself. A Claude skill that watches your work sessions, captures corrections and judgment calls, and turns them into skill improvements automatically. Open-source, domain-agnostic, CC BY 4.0.

31
6
100% credibility
Found Feb 25, 2026 at 20 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

A Claude-compatible skill that observes user interactions during work sessions to suggest creating new skills and improving existing ones.

How It Works

1
🔍 Discover the helper

You hear about a smart helper skill that watches your work and makes your other AI skills better over time.

2
💾 Get the skill

Download the simple skill file from the guide.

3
➕ Add it to your AI

Place the skill into your AI assistant's collection so it can start watching.

4
💼 Do your normal work

Carry on with your tasks and projects just like always, chatting with your AI.

5
👁️ It quietly observes

While you work, the helper notices patterns, fixes, and ideas for better skills without interrupting.

6
📋 Review suggestions

At the end of your session, you get a clear list of new skill ideas and tweaks to existing ones.

7
✨ Make improvements

Pick the suggestions you like and update your skills easily.

🎉 Skills grow smarter

Your AI toolkit keeps improving automatically with every session, including the helper itself.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 31 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is one-skill-to-rule-them-all?

One Skill to Rule Them All is the meta-skill that builds and improves all your skills, including itself—a Claude tool that watches work sessions, captures corrections and judgment calls, and generates improvements automatically. It spots repeating patterns to draft new skills and suggests tweaks to existing ones based on your adjustments and gaps. Domain-agnostic under CC BY 4.0, it keeps your Claude skill library evolving without manual audits, just drop it into Cowork or Claude.ai as a custom skill.

Why is it gaining traction?

It stands out as a self-improving observer that runs alongside tasks in Claude, automatically flagging gaps, corrections, and its own blind spots for better methodology over time. Unlike static skills or checklists, it produces reviewable logs or handoff docs you approve, making your setup smarter with zero config. The hook: work normally in Cowork for filesystem-persisted gains, or get structured outputs in Claude.ai web.

Who should use this?

Claude users building skills for writing, research, client analysis, or content workflows who hate frozen tools. Power users in Cowork managing 5+ skills and wanting them to adapt to personal judgment calls. Beginners with empty libraries—it drafts domain-agnostic starters from your sessions.

Verdict

Early release with 19 stars and 1.0% credibility score signals low maturity and limited testing beyond Cowork/Claude.ai, but strong docs and self-improvement promise make it worth a spin for heavy Claude folks. Test it via skills CLI if your platform matches; contribute observations to help it grow.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.