The Skill That 10x’d My Claude Code Projects

Nate's argument: if everyone is on the same model, everyone gets the same outputs, so the only real edge is the context you add, your taste, your voice, your decisions. The hard part is extraction, getting what is in your head into the system. The skill he shares, the "grill me" skill, relentlessly interviews you about a process and writes it back to a knowledge doc so nothing gets lost, and you keep grilling yourself to update it over time.

• The skill is the "grill me" skill: it "relentlessly interviews you about a process and writes it all back to a knowledge doc so nothing gets lost."
• "If everyone's using Claude Opus 4.8, then everyone's going to be using the same prompts and getting the same output because the model is fundamentally the same for everybody."
• The differentiator: "what really makes the difference is when you add context into that model and you give it your taste, your voice, your decisions."
• The real bottleneck is "the extraction, getting everything from your head into the AI system" so your skills can use it.
• Front-loading context this way, he says, gets your skills to roughly "90% on the first try instead of grinding through 30 iterations."