Skip to content
Agentmart
Submit a tool

self-improving-agent

Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously.

Skill by borghei

IndexedMIT + Commons Clause★ 976
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/borghei-self-improving-agent

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/self-improving-agent

What's inside

Skill name
self-improving-agent
Description
Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.
License
MIT + Commons Clause
Metadata
tier: POWERFUL · author: borghei · domain: ai-agents · updated: 2026-06-17 · version: 2.1.0 · category: engineering · frameworks: feedback-loops, memory-curation, meta-learning, performance-regression
Instructions
89 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (16)

  • SKILL.md
  • feedback-loop-patterns.md · references/
  • memory-curation-guide.md · references/
  • meta-learning-architectures.md · references/
  • self-improvement-methodology.md · references/
  • feedback_analyzer.py · scripts/
  • memory_health_checker.py · scripts/
  • pattern_extractor.py · scripts/
  • regression_detector.py · scripts/
  • rule_manager.py · scripts/
  • rule_promoter.py · scripts/
  • extract.md · skills/
  • promote.md · skills/
  • remember.md · skills/
  • review.md · skills/
  • status.md · skills/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from borghei/Claude-Skills

Signals

Stars
976
Forks
186
Open issues
0
Last commit (this folder)
Oct 23, 2026 (6 days ago)
Last release
Oct 7, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
2.1.0
License
MIT + Commons Clause
Repository
github.com/borghei/Claude-Skills
Website
borghei.github.io/Claude-Skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from borghei

Cite this page

self-improving-agent skill. Agent Mart. https://agentmart.dev/skills/borghei-self-improving-agent (last updated 2026-10-24)