automatic-stateful-prompt-improver

When this skill is active, I MUST follow these rules:

I AUTOMATICALLY call mcpprompt-learningoptimizeprompt BEFORE responding when:

| Factor | Low (3-5) | Medium (5-10) | High (10-20) |

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed). Source: curiositech/some_claude_skills.