aeonAutoresearch / aeon skill
AI agent that evolves its own skills
Evolve a skill by generating variations, evaluating them, and updating the best version
- Skill
- Autoresearch
autoresearch - Category
- Evolution
- Default schedule
- On demand
- Last updated
commit e1d9284- Source
- aeonfun/aeon/skills/autoresearch/SKILL.md MIT licensed, one prompt file
What it does
Autoresearch is an aeon skill: Evolve a skill by generating variations, evaluating them, and updating the best version. Like every aeon skill it is one SKILL.md prompt file that runs unattended on your own GitHub Actions, on a schedule or when you trigger it, and sends what it finds to Telegram, Discord, Slack or email.
Improve an existing skill by researching better approaches, generating 4 distinct variations, scoring them against a rubric, and committing the winning version as a PR.
Input: the var setting
Every aeon skill takes one optional text input, var, set in aeon.yml or typed in when you run it by hand. It picks the target or the mode for that run.
Name of the skill to evolve (e.g. token-movers). Required.
What it needs
No extra API keys or MCP servers. It runs on the model you connected to aeon (a Claude subscription token, an API key, or another login).
Install and run it
Easiest: open Aeon Connect, sign in with GitHub and turn on Autoresearch. No clone, no terminal. To add it to an existing aeon repo from a shell, run:
Then switch it on in aeon.yml (the default schedule is filled in):
skills:
autoresearch: { enabled: true, schedule: "workflow_dispatch", var: "" }New to aeon? Read the docs for how skills, schedules and memory fit together, or browse all skills.