In the first three months of using this meta-skill, it **logged and applied over 600 improvements across my 40 skills**, most of which were themselves created based on observations by the meta-skill.
This meta-skill, called "task-observer", is a practical application of the [Augmented Expertise](https://www.rebelytics.com/augmented-expertise/) methodology, an AI framework for knowledge workers. However, users have reported successful integrations into their Hermes and Openclaw setups, so it works equally well with autonomous agents.
1.**Creates new skills for you** — it spots repeating patterns in your work and drafts skill candidates automatically, so you get skills without the upfront effort of writing them from scratch
2.**Improves your existing skills** — it notices corrections you make, preferences you express, and gaps in your current skills, then suggests specific updates
You work normally. It watches. Your skill library grows and gets better over time.
This is the detail that makes the task observer truly beautiful in my opinion. Because it runs during every session and observes all active skills — including itself — it captures improvements to its own methodology over time.
If it misses something, or if its observation format could be clearer, or if it's triggering in contexts where it shouldn't — it notices, and it logs that too. The skill that improves all your skills also improves itself.
1.**Corrections and adjustments** — if you adjust the AI's output or steer it in a different direction, that's a signal that a skill could be clearer or more complete
During each session, it produces a structured observation log: what it noticed, which skills are affected, and specific suggested improvements. You review, approve, and your skills evolve.
Some observations reveal patterns that aren't specific to one skill. These get captured as **cross-cutting principles** in a separate log — and new skills are automatically checked against them whenever they're created or updated. The more you use the system, the higher the quality floor across your whole skill library.
You don't need to be a developer. If you use skills in any capacity and you want those skills to get better over time instead of staying frozen, this is for you.
If you're a builder, you can easily integrate this skill, or even just the methodology, into your existing setup. Just point your agent at the repo and let it guide you towards the ideal implementation for your specific setup.
The task observer is particularly valuable if you've built multiple skills and want a systematic way to maintain and improve them without manually auditing each one. But it's equally useful if you don't have any skills yet: the observer will start identifying and drafting them for you.
**The best way to get started with this work setup in any environment is probably to grab the skill, readme and user guide, feed them to your AI and let it guide you towards the best setup for your particular environment** - No matter which AI system you use. As long as skills are supported, you should be able to use this approach with some adjustments. And even without skills, the methodology should work with any other type of knowledge base that your AI has access to.
**In Claude Cowork (including Dispatch) or Claude Code in the desktop app:** Full experience. The observer writes observation logs to your filesystem, so improvements persist between sessions and can be actioned easily. Observations land in `[your shared folder]/skill-observations/`; proposed skill updates land in `[your shared folder]/skill-updates/`. You don't normally need to look at these directly — Claude handles them — but they're there if you want to inspect what's been captured.
**In Claude.ai web or Claude Chat in the desktop app / mobile app:** Handoff doc mode. Since there's no filesystem access, the observer produces a structured handoff document at the end of your session that you can use to update your skills in a dedicated session.
- Claude Code without desktop app — the methodology and format should translate directly, but I haven't verified it in practice - users have reported seamless experiences with this.
- Other skills-compatible platforms (ChatGPT, Gemini CLI, Cursor, etc.) — the skill uses Claude-centric concepts like `<available_skills>` and skill-creator references that other systems would need to interpret or adapt. The SKILL.md format is cross-platform, but the content assumes Claude's architecture.
1. Read the user guide at [https://github.com/rebelytics/one-skill-to-rule-them-all/blob/main/USER-GUIDE.md](https://github.com/rebelytics/one-skill-to-rule-them-all/blob/main/USER-GUIDE.md)
2. Give the content of this repo (skill, readme and user guide) to the AI system of your choice and let it guide you towards the ideal configuration for your individual setup.
4. Try to remember to ask "Any observations logged?" when you finish a session (I do this every time I archive a session). Often, the skill then finds additional improvement potential that it didn't log before.
5. Schedule a recurring review session that applies all open observations. Mine runs Monday, Wednesday and Friday morning, but you should adapt this to your needs.
You're free to use, adapt, and redistribute — even commercially — as long as you give appropriate credit: Link to the original repo (https://github.com/rebelytics/one-skill-to-rule-them-all/) and name the author (Eoghan Henn / rebelytics.com).
If you want to learn more about the methodology behind this skill, please read the [Augmented Expertise manifesto](https://www.rebelytics.com/augmented-expertise/).
