Self Improving Agent
Skill Verified ActiveCurate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
To curate Claude Code's auto-memory into durable, structured project knowledge, ensuring that valuable learnings are captured, promoted to enforced rules, and extracted into reusable skills.
Features
- Analyzes AI auto-memory (`MEMORY.md`) for patterns
- Promotes proven learnings to project rules (`CLAUDE.md`, `.claude/rules/`)
- Extracts recurring solutions into reusable skills
- Checks memory health and capacity
- Provides explicit knowledge saving to auto-memory
Use Cases
- Reviewing what Claude has learned about your project
- Graduating a pattern from notes to enforced rules
- Turning a debugging solution into a reusable skill
- Checking memory health and capacity
Non-Goals
- Directly managing AI conversation history
- Replacing the core functionality of Claude Code's auto-memory
- Generating entirely new AI models or agents
Workflow
- Analyze MEMORY.md for promotion candidates, stale entries, consolidation opportunities
- Approve and promote a pattern from MEMORY.md to CLAUDE.md or `.claude/rules/`
- Extract a proven pattern into a standalone skill
- Check memory health dashboard (line counts, topic files, recommendations)
- Explicitly save important knowledge to auto-memory
Practical Utility
- info:Edge casesThe SKILL.md mentions limitations of auto-memory (e.g., 200-line limit, lack of judgment) which are indirectly addressed by the skill's purpose, but specific failure modes and recovery steps for the skill's own operations are not detailed.
Installation
First, add the marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install self-improving-agent@claude-code-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Ctx Doctor
100Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor
Typescript Advanced Types
100Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
Validate Plugin
100Validate a Claude Code plugin structure, frontmatter, and MCP tool references
Migrate Validate
100Validate pending migrations for foreign key consistency, rollback safety, and best practices
Lean Ctx
100Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.
Semgrep Rule Creator
100Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.