Don't just use AI tools; ask them to explain *why* they work. Prompt the AI to break down concepts (e.g., repository structure) and to critique your own setup against best practices. This metacognitive loop accelerates learning and continuous improvement.

Using AI to generate generic content creates shallow thought leadership. The truly powerful application is using AI as an analytical engine. Feed it your entire body of work—transcripts, articles, notes—to uncover hidden themes, patterns, and core ideas that you've forgotten or couldn't see yourself.

If you struggle to articulate your editing or design style, feed an AI examples of your work. It can identify patterns and generate a system prompt, or 'skill,' that codifies your unique taste for your entire team to use.

Instead of manually writing personal context files, engage an AI in an "interview to draft to revision" loop. By having the AI ask targeted questions, you can more effectively surface and articulate the tacit knowledge about your roles, preferences, and processes that you wouldn't think to write down otherwise.

'Taste' is a collection of specific preferences, not an abstract feeling. Document what makes an output 'good' by creating universal rules (e.g., 'write at a ninth-grade level,' 'avoid cheesy quotes,' 'no em dashes'). Feeding these documented rules to an AI transforms your subjective taste into repeatable instructions for consistent results.

"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.

To avoid generic AI-generated text, use the LLM as a critic rather than a writer. By providing a detailed style guide that you co-created with the AI, its feedback on your drafts becomes highly specific and aligned with your personal goals, audience, and tone.

An effective method for refining AI output is to instruct the model to adopt an expert persona, such as a "PhD economist," and critically evaluate its own work. This often leads the model to self-identify and correct its own flaws without further prompting.

Instead of pre-designing a complex AI system, first achieve your desired output through a manual, iterative conversation. Then, instruct the AI to review the entire session and convert that successful workflow into a reusable "skill." This reverse-engineers a perfect system from a proven process.