skillrank_skill ▸ zhaono1/self-improving-agentMIT · open registry

skill detail

← registry

Self Improving Agent

zhaono1/self-improving-agent

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

communityprovisionalaiuniversalselfimproving

skillrank score

████░░░░░░░░░░░░25

SkillRank score blends community stars, real usage, and our eval lift; provisional until a skill is evaluated -- so popularity alone can't reach the top tier.

source

★ 70

zhaono1/agent-playbook

skills/self-improving-agent

open on GitHub ▸

eval status

eval pending

Success delta, token delta, and trial count are not available yet. No eval number is shown until this skill has measured results.

install

$ skillrank install zhaono1/self-improving-agent
$ curl -fsSL skillrank.dev | sh