self-evolve

Analyzes sprint outcomes to update CLAUDE.md, memory, and skill instructions for preventing repeat failures.

Updated Apr 18, 2026

Search Tags:#guardian #memory-management #sprint-retrospective #self-evolve #rule-updates #ai-guard

Ready to run

npx skills add https://github.com/Srujan0798/NRG --skill self-evolve-srujan0798

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: self-evolve
Source: https://github.com/Srujan0798/NRG/tree/main/.claude/skills/self-evolve
Command: npx skills add https://github.com/Srujan0798/NRG --skill self-evolve-srujan0798

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guardian Agent analyzes sprint outcomes to adapt rules, memory, and skill content to prevent repeat failures and strengthen system resilience.

Core Features & Use Cases

Evaluates sprint results and test outcomes to generate actionable improvements.
Updates CLAUDE.md, memory, and skill instructions to tighten guardrails and prevent regressions.
Use case: after a sprint, trigger /self-evolve to auto-tune the guardian's behavior and learning loop.

Quick Start

Run the evolution after each sprint to automatically update rules and memories.

Frequently Asked Questions about self-evolve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automatically update system rules after a sprint retrospective?▼

The skill analyzes sprint results and test outcomes to generate actionable improvements, updating CLAUDE.md and memories to strengthen system protections and prevent repeat failures.

What is automated rule refinement for memory management in AI agents?▼

Automated rule refinement evaluates sprint outcomes and memories to adapt system rules, updating CLAUDE.md and memory to strengthen guardrails, enhance self-healing capabilities, and prevent regressions.

How do I prevent repeat failures by updating CLAUDE.md guardrails?▼

Trigger an automated evolution after each sprint to auto-tune behavior, updating CLAUDE.md guardrails and memory based on analyzed sprint outcomes to prevent repeat failures.

Can I use self-evolve to auto-tune guardrails without manual rule updates?▼

Yes, triggering an evolution after each sprint automatically updates rules, memory, and skill instructions to tighten guardrails and strengthen system resilience without manual intervention.

When do I need to apply automated rule refinement for sprint retrospectives?▼

You need automated rule refinement for sprint retrospectives when evaluating sprint results and test outcomes to auto-tune behavior, update memories, and prevent regressions.

What are the limitations of using self-evolve for memory management?▼

The metadata does not specify limitations, but the tool is designed to analyze sprint outcomes and update CLAUDE.md to strengthen system protections and self-healing capabilities.