Community Plugin

self-improvement

Self-improvement system for Claude with critic agent, quality analysis skills, automated conversation analysis, and feedback loops. Features automatic pattern tracking, learning reinforcement, and trend detection. Enables continuous improvement through honest self-assessment and iterative refinement.

2.0.0

Updated 19 days ago

AI Insight

Enables Claude to critique its own work through automated quality analysis, feedback loops, and pattern tracking for continuous learning.

Why this plugin

Provides honest self-assessment and iterative refinement, catching bugs and improving quality through automated analysis and learning from recurring mistakes.

Prerequisites

Requires Claude Code CLI installation. No external API keys or dependencies needed.

self-review

quality-analysis

meta-learning

Install

Add the repository(one-time)

/plugin marketplace add c0ntr0lledcha0s/claude-code-plugin-automations

Install the plugin

/plugin install self-improvement@claude-code-plugin-automations

Components

Commands

Analyze Component Quality

/analyze-component

claude-sonnet-4-5

2 tools

Analyze the quality of a Claude Code component (agent, skill, command, hook) with detailed scores and improvement suggestions

Diagnose self-improvement plugin health and configuration issues

Improve Component Quality

/improve-component

claude-sonnet-4-5

3 tools

Automatically apply quality improvements to a Claude Code component based on analysis

Quick quality assessment of recent work using the analyzing-response-quality skill

Invoke the self-critic agent to review Claude's recent work and provide feedback

Show Compliance Statistics

/show-compliance

2 tools

Display compliance statistics showing how often session advice is followed

Display tracked learning points from automated conversation analysis

Display conversation metrics and statistics from automated analysis

Display tracked patterns from automated conversation analysis

Agents

Expert critic and quality analyst for Claude's responses. Use after completing complex tasks, before final responses, or when the user requests review. Analyzes reasoning, completeness, accuracy, and communication quality.

Skills

analyzing-component-quality

4 tools

2 assets

Expert at analyzing the quality and effectiveness of Claude Code components (agents, skills, commands, hooks). Assumes component is already technically valid. Evaluates description clarity, tool permissions, auto-invoke triggers, security, and usability to provide quality scores and improvement suggestions.

analyzing-response-quality

3 tools

3 assets

Expert at analyzing the quality of Claude's responses and outputs. Use when evaluating response completeness, accuracy, clarity, or effectiveness. Auto-invokes during self-reflection or when quality assessment is needed.

creating-feedback-loops

4 tools

Expert at creating continuous improvement feedback loops for Claude's responses. Use when establishing self-improvement processes, tracking progress over time, or implementing iterative refinement workflows.

improving-components

2 tools

Expert at automatically applying improvements to Claude Code components based on quality analysis. Enhances descriptions, optimizes tool permissions, strengthens security, and improves usability. Works in conjunction with analyzing-component-quality skill.

suggesting-improvements

3 tools

Expert at suggesting specific, actionable improvements to Claude's responses and work. Use when Claude's output needs enhancement, when quality issues are identified, or when iterating on solutions.

Hooks

Review workflow modifications before installing

2 hooks across 2 events

Stats

Stars2

Installs2

MaintenanceExcellent

Last Commit19 days ago

Community Promotion

Collections

Links

View on GitHub

View README

Plugin Marketplace JSON

Homepage

Similar Plugins

everything-claude-code

56.9k

148

Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use

v1.7.0

payload

41.0k

Payload Development plugin - covers collections, fields, hooks, access control, plugins, and database adapters.

2mo

v0.0.1

agent-browser

16.8k

Automates browser interactions for web testing, form filling, screenshots, and data extraction

v0.15.1

planning-with-files

15.5k

Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, and 11+ AI coding assistants.

v2.21.0