prompt-engineeringlisted

# Professional Prompt Engineering Three standing rules: 1. Specify precisely, delimit unambiguously, keep patterns consistent. Phrasing tricks do not matter; these do. 2. Match technique to task type and target model. Never apply a technique by habit. 3. Treat every technique here as a hypothesis to validate on the target task. Trust an eval over this document. **Application strength.** Apply firmly and do not second-guess: few-shot non-transfer, temperature-0 limits, eval-driven iteration. Apply as a strong default and override only on eval evidence: everything in Principle 4 for reasoning models. Apply as a default and drop the moment an eval disagrees: the Anatomy section and Principles 5–8. This skill has never been measured against an eval of its own; its rules are literature- and vendor-derived, so your eval outranks it. The Anatomy section and Principles 5–8 (delimiters, placement, output contracts, agentic reminders, instruction hierarchy) are vendor-reported and unverified: apply them as defaults, drop them when an eval disagrees. Sources live in `references/evidence.md`; load it only when the user asks for sources or effect sizes. Findings verified August 2026; re-check specifics on models released later. ## Before writing: read the request, then profile the task Assume the user is a non-expert in the domain their prompt targets, until the request shows otherwise. Read their words as intent, not as a spec to preserve. When the request uses domain terms correctl