Techniques

Mental models tell you where to push. Techniques are the phrases that do the pushing. Chess players build a repertoire of openings, tactics, and endgame studies, most of it learned from other players and none of it secret. The same vocabulary is forming for prompting. Some moves worth stealing:

Before you start

What questions should you ask me before starting?

Surfaces ambiguity instead of guessing. The model returns a list of things it's uncertain about; you answer them, then it goes. Saves a lot of clarifying turns later. Especially good with smaller, faster models.

What's the smallest version of this that ships?

Scopes down before delegating. Ten lines instead of a thousand. The model is happy to grow scope; you have to ask it to shrink.

Open the options

Give me 3 options, rank them, name the trade-offs.

Forces breadth before depth. The model defaults to its first plausible idea; asking for three pushes it past that. Useful for any decision where you don't already know the right answer: algorithm choice, library choice, schema design.

Argue against your last suggestion.

Surfaces hidden assumptions. Especially useful right after a plan; much cheaper to discover its weaknesses now than after you've implemented it.

Pressure-test it

What did you skip?

After a delegated task, ask what was glossed over. The model often owns up to things you'd have missed: tests, error handling, the "TODO: revisit" it left on line 47. Cheap two-second move, high hit rate.

How would a senior engineer review this?

Triggers review-mode output, a different vibe than implementation-mode: more critical, more "but consider" tradeoffs, more willing to call out things its implementation-self would have left in.

Pay it forward

Match the style of components/PostCard.tsx.

Anchor on something concrete: a path, a screenshot, a doc, a working example. "Match this" beats "make it look nice" by a wide margin. Models are imitators first; give them something to imitate.

Update CLAUDE.md with what you just learned.

Capture the lesson in the project rules so the next agent (or future-you) doesn't have to relearn it. Five minutes of work that saves every future session.

Lift them into skills

Once you find a move that works, stop typing it manually. Every serious agent tool lets you write project-level instructions that the agent reads on every task. You write the lesson once; the agent has it forever.