Agent: Claude Code, CursorLLM: Claude 3.5, Claude 3#prompt-engineering#writing-tools#ai-detection#content-quality#skill-file
A skill file that teaches Claude and other LLMs to identify and remove predictable AI writing patterns—throat-clearing phrases, structural clichés, and vague declaratives. Includes reference guides for banned phrases, structural patterns, and before/after examples. Works with Claude Code, Claude Projects, custom instructions, or API calls.