Prompt Clarity And Motivation ⚠ verify

Definition

Claude follows clear, explicit, specific instructions best; adding the motivation (the "why") behind an instruction lets Claude generalize and deliver more targeted responses.

Key points

• Treat Claude as "a brilliant but new employee who lacks context on your norms and workflows" — the more precisely you explain what you want, the better the result.
• Golden rule (verbatim): "Show your prompt to a colleague with minimal context on the task and ask them to follow it. If they'd be confused, Claude will be too."
• Be specific about desired output format and constraints; if you want "above and beyond" behavior, request it explicitly rather than relying on inference.
• Provide instructions as sequential numbered steps / bullets when order or completeness matters.
• Add motivation: explaining why a behavior matters helps Claude generalize.
  • Less effective: NEVER use ellipses. More effective: Your response will be read aloud by a text-to-speech engine, so never use ellipses since the text-to-speech engine will not know how to pronounce them.
• Prefer imperative over interrogative: "Can you suggest some changes" may only yield suggestions; "Change this function..." implements. Opus 4.8 is literal. ⚠ verify (2026-07-08)
• "Tell Claude what to do instead of what not to do" (e.g. "Compose smoothly flowing prose paragraphs" beats "Do not use markdown").

Why it matters for the exam

• D4 is 20% of scored content and leans heavily on picking the clearer / more-motivated prompt over a vague one.
• The "show it to a colleague" test and the ellipses/TTS example are canonical, directly-quotable exam anchors.

Common gotchas

• Vague prompts (Create an analytics dashboard) are the wrong answer vs the specific, motivated variant.
• Negative-only phrasing ("do not X") underperforms positive instruction plus a format indicator.

See also

• Role Prompting
• Few-Shot Prompting
• XML Structuring

Sources

• docs-prompting
• netlight-study-guide