claude-code-contextstellar

Analyze recent prompt patterns and suggest optimizations. Use when the user wants to improve their prompting patterns, reduce token costs, or see what the RLM flywheel has learned about their project.

Score a prompt for context engineering quality. Use when the user asks to score, analyze, or optimize a prompt, or when reviewing prompt quality before sending to an LLM.

Set up ContextStellar cloud mode for RLM learning and dashboards. Use when the user wants to configure an API key, connect their project, or upgrade from local-only scoring.

Show ContextStellar scoring statistics, RLM learning progress, and grade distribution for the current project. Use when the user asks about their scoring stats, prompt quality trends, or RLM weight learning.