Self Improving Agent

Curates agent memory and turns repeated lessons into reviewed rules: memory health checks, pattern extraction, feedback and regression analysis. Use when managing auto-memory or building agents that learn from their own sessions.

1,157 stars 217 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add borghei/Claude-Skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add borghei/Claude-Skills --skill self-improving-agent
Manual install
git clone --depth 1 https://github.com/borghei/Claude-Skills.git /tmp/Claude-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skills/engineering/self-improving-agent ~/.claude/skills/self-improving-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Self-Improving Agent

The agent captures what went wrong or right in a session, curates it in memory, and proposes promoting a lesson into a permanent rule only when it has recurred and a person has approved it. Rules compound: a wrong rule repeats its mistake in every later session, so promotion is a reviewed change, never an automatic one.

## Core Capabilities

- **Memory curation** — a layered memory stack (CLAUDE.md → MEMORY.md → session), review protocol, and promotion criteria for graduating learnings into enforced rules.
- **Feedback loops** — outcome classification, signal extraction, and a capture template that turn every task result into a structured learning.
- **Regression detection** — metrics, thresholds, and a response protocol that flags performance degradation within a few sessions.
- **Skill extraction** — criteria and a 4-step process to graduate proven patterns into standalone skill packages.
- **Meta-learning** — adaptive capture strategy and anti-pattern detection so the agent learns *what* is worth learning.
- **Continuous calibration** — confidence scoring and belief revision for resolving contradictions across learned knowledge.

## When to Use

- Building agents intended to improve over time rather than stay stateless.
- Managing auto-memory (MEMORY.md) and deciding what to keep, promote, or retire.
- Designing self-correcting feedback loops and regression alarms for agent behavior.
- Graduating recurring solutions into reusable skill packages.
Read the full skill on GitHub

Details

Skill name
self-improving-agent
Path
engineering/self-improving-agent/SKILL.md
Repo updated
8 November 2026

FAQ

What does the Self Improving Agent skill do?

Curates agent memory and turns repeated lessons into reviewed rules: memory health checks, pattern extraction, feedback and regression analysis. Use when managing auto-memory or building agents that learn from their own sessions.

How do I install the Self Improving Agent skill?

Claude Code plugin: /plugin marketplace add borghei/Claude-Skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Self Improving Agent popular?

It lives in borghei/Claude-Skills, which has 1,157 GitHub stars and 217 forks, and is included in 1 curated skill list.

Related skills

Cto Advisor

1.2k

borghei/Claude-Skills

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, or making architecture decisions.

Software DevelopmentIn 1 list217

Customer Success Manager

1.2k

borghei/Claude-Skills

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success

Marketing, Sales & BusinessIn 1 list217

Financial Analyst

1.2k

borghei/Claude-Skills

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Finance & CryptoIn 1 list217

Senior Computer Vision

1.2k

borghei/Claude-Skills

Computer vision engineering for object detection, segmentation, and visual AI, covering CNN and Vision Transformer architectures and ONNX/TensorRT deployment. Use when building detection pipelines, training models, or optimizing inference.

AI, LLMs & AgentsIn 1 list217

Scenario War Room

1.2k

borghei/Claude-Skills

Cross-functional what-if modeling for compound adversity -- shows how one problem cascades into the next. Use when facing complex risk scenarios, strategic decisions with major downside, or multi-variable threats.

AI, LLMs & AgentsIn 1 list217

Senior Data Scientist

1.2k

borghei/Claude-Skills

Experiment sizing, feature profiling with leakage checks, and model evaluation from saved predictions, plus causal-inference workflows. Use when sizing an A/B test, vetting features, or scoring a model before release.

AI, LLMs & AgentsIn 1 list217

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.