automatic-stateful-prompt-improver
CommunityAuto-optimize prompts and learn from results.
Authorerichowens
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the tedious process of crafting and refining prompts. It automatically intercepts user requests, optimizes prompts using a persistent stateful learning loop via an MCP server, and stores performance data to improve future outcomes. It reduces time spent on trial-and-error prompting and increases result quality by learning from feedback across conversations and tasks.
Core Features & Use Cases
- Auto-intercept and optimize prompts before responding to complex tasks
- Stateful learning through embedding-indexed history and performance metrics
- Integration with MCP servers and Claude Code for persistent learning
- Clear convergence thresholds and iterative budgets for predictable improvements
- Suitable for system prompts, templates, and multi-step instructions
- Supports feedback and analytics to continuously improve prompt quality
Quick Start
- Ensure your prompt-learning MCP server is running and properly configured in Claude Code.
- Invoke with: "optimize this prompt: [your prompt here]".
- Review the optimized prompt and improvement details, then use the refined prompt for your task.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: automatic-stateful-prompt-improver Download link: https://github.com/erichowens/some_claude_skills/archive/main.zip#automatic-stateful-prompt-improver Please download this .zip file, extract it, and install it in the .claude/skills/ directory.