Instead of using single prompts like "write a blog post," build a custom AI "skill." Codify your entire creative process by breaking the task into sub-steps (e.g., research, synthesis, outlining), with human-in-the-loop approvals to guide the output and inject your unique taste.

Research shows that using AI to complete a task, like rewriting a cover letter, can improve a person's underlying skill. The AI-generated output acts as a high-quality example, much like a coach demonstrating a technique, which accelerates learning more than practicing alone.

Instead of generating copy from scratch, write your own draft first. Then, prompt an AI to review and improve it based on the known principles and styles of famous copywriters. This turns the AI into a personalized, expert thought partner for refining your work.

"Skills" are markdown files that provide an AI agent with an expert-level instruction manual for a specific task. By encoding best practices, do's/don'ts, and references into a skill, you create a persistent, reusable asset that elevates the AI's performance almost instantly.

Spiral's redesign was driven by the principle that "good writing is downstream of good thinking." Instead of just generating content, the tool focuses on helping users explore and clarify their own ideas through an interactive, question-based process, making the AI a partner in thought.

Most AI writing tools produce generic content. Spiral was rebuilt to act as a partner. It first interviews the user to understand their thoughts and taste, helping them think more deeply before generating drafts. This collaborative process avoids "slop" and leads to more authentic writing.

After receiving feedback that his writing was too long, a PM built a custom GPT to make messages more concise. He fed it newsletters and books on effective writing from experts, creating a personalized coach that helped him apply the feedback in his daily work, leading to better engagement from colleagues.

Treat AI skills not just as prompts, but as instruction manuals embodying deep domain expertise. An expert can 'download their brain' into a skill, providing the final 10-20% of nuance that generic AI outputs lack, leading to superior results.

An effective skill goes beyond a simple instruction. It should be structured like an expert's toolkit, including established frameworks (e.g., AIDA for copywriting), a scoring system for evaluation, and a defined output template for consistency and clarity.