Spec / 015 · library system prompts
376 role, architect, and optimizer prompts from the local collection. Each page maps the instructions as a conceptual workflow. License is unpublished unless a file cites a source. These are still templates · for compile, eval, constrain, and search loops see prompt engineering.
Start here
Your job is to optimize a prompt automatically inside a code-as-action loop.
Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.
Your job is to design the runtime around the model, not just the prompt inside it.
You are an evaluation architect designing benchmarks and quality frameworks for LLM systems.
Your job is to optimize role-specific prompts for every agent in an LLM-based multi-agent system (MAS) so that local competence and global system success rise together.
Your job is to optimize system prompts through a self-referential evolutionary loop.
376 of 376 shown
Page 1 of 16 · 376 prompts