🧬
AI EngineeringHTML

Evolving AI Agents

by majiayu000

Evolving AI Agents is an AI Engineering skill for Claude Code, published by majiayu000 in claude-skill-registry.

575 stars88 forkson majiayu000/claude-skill-registryAdded 2026/08/25+1% in starsRepository updated 2026/08/25
ai-skillsclaude-codegenerated-artifactgithub-pagesskill-registryskills
Install in seconds
Install Evolving AI Agents
Copy Evolving AI Agents into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/majiayu000/claude-skill-registry/tree/main/skills/agent/a-evolve ~/.claude/skills/a-evolve

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/majiayu000/claude-skill-registry.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/agent/a-evolve/SKILL.md in majiayu000/claude-skill-registry
Installs to
~/.claude/skills/a-evolve
Collection
One of 23 skills cataloged from this repository
Category
AI Engineering — 3670 skills

What Evolving AI Agents does

Evolving AI Agents provides guidance for automatically improving AI agents with LLM-driven evolution loops. Use it to optimize prompts, skills, memory, and tools against benchmarks or build self-improving agent systems.

Evolving AI Agents is cataloged under AI Engineering on DirSkills. Evolving AI Agents comes from a repository tagged ai-skills, claude-code, generated-artifact, github-pages and skill-registry.

Documentation

README

Evolving AI Agents with A-Evolve

Overview

A-Evolve is universal infrastructure for evolving any AI agent across any domain using any evolution algorithm with zero manual engineering. It represents all evolvable agent state as files (prompts, skills, memory, tools), runs iterative solve-observe-evolve cycles against benchmarks, and uses LLM-driven mutation to improve agent performance automatically.

Benchmark results (Claude Opus 4.6):

  • MCP-Atlas: 79.4% (#1)
  • SWE-bench Verified: 76.8% (~#5)
  • Terminal-Bench 2.0: 76.5% (~#7)
  • SkillsBench: 34.9% (#2)

When to Use A-Evolve

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Evolving AI Agents

  • What else does majiayu000 publish alongside Evolving AI Agents?

    Evolving AI Agents is one of 23 skills that DirSkills catalogs from majiayu000/claude-skill-registry, the repository it ships in. Its siblings there include AC Autonomous Orchestrator, AC Checkpoint Manager and AC Commit Manager. Each one is a separate skill with its own page in this directory, installs the same way Evolving AI Agents does, and is maintained by majiayu000 in that same repository. The rest of the collection is listed on the majiayu000/claude-skill-registry page.

  • How does Evolving AI Agents compare to other AI Engineering skills?

    Evolving AI Agents ranks #2007 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Evolving AI Agents against them. Open each page to compare what they document and how they install.

More from majiayu000/claude-skill-registry

Evolving AI Agents is one of 23 skills cataloged on DirSkills from majiayu000/claude-skill-registry.

See all 23 skills →
🤖
2026/08/25

AC Autonomous Orchestrator

AC Autonomous Orchestrator coordinates autonomous coding operations from initialization through planning, execution, validation, and commit. Use it to run full-session implementations or manage multiple components together.
AI Engineering
57588
🗂️
2026/08/25

AC Checkpoint Manager

AC Checkpoint Manager creates and restores checkpoints for safe rollback during autonomous development. Use it to save state before risky changes, recover known-good points, or return to a previous checkpoint.
DevOps
57588
📝
2026/08/25

AC Commit Manager

AC Commit Manager creates structured git commits after completed features and verifies the commit was created. Use it to stage changes, generate descriptive messages, and manage version control for autonomous coding.
DevOps
57588
✅
2026/08/25

AC Criteria Validator

AC Criteria Validator checks implemented features against acceptance criteria and reports whether they pass. Use it to verify test results, code completeness, and other feature completion checks.
Quality
57588
🧩
2026/08/25

AC Handoff Creator

AC Handoff Creator packages current progress, decisions, blockers, and next actions so a later session can resume work. Use it when ending a session or saving resumable context.
AI Engineering
57588
📝
2026/08/25

AGENTS Md Generator

AGENTS Md Generator creates AGENTS.md files for Java repositories through a step-based interactive process. Use it to document conventions, commands, workflow, and contributor boundaries for agent instructions.
Writing
57588