52 prompts

Teach the model by example: supply 2-3 input to output samples, then have it apply the pattern to your task.

#fewshot
View

Force explicit step-by-step reasoning before the answer to reduce errors on harder problems.

#cot
View

Solve a problem several independent ways, then reconcile the attempts into one trusted answer.

#consistency
View

Break a big, vague goal into clear, ordered, dependency-aware subtasks with done-when checks.

#decompose
View

Design a multi-step prompt pipeline where each stage's output cleanly feeds the next.

#chain
View

Lock output to a strict format and schema with explicit, checkable rules and a self-check.

#constrain
View

Steer output by naming what to avoid, each paired with the positive alternative to do instead.

#negative
View

Splits one complex prompt into a sequence of linked prompts that pass outputs forward.

#prompt-chaining#pipeline#modular
View