What is the line for?

Asking Claude to think first and then put only the final output in tags gives it room to reason while making the final result easy to copy or parse. Remove it for simple tasks.

Claude prompt generator

Sets every part of your prompt inside its own XML tag, the structure Anthropic recommends for Claude, and leaves room for Claude to think before it answers.

Your prompt

roletaskcontextformattonerulesexample

Fill in a few fields and your prompt is set here, line by line.

0 words · 0 characters

0/100

Prompt score

Underspecified

0 words

Clear task verb missingStart with an explicit action: “Write…”, “Summarize…”, “Compare…”.
Background or context missingSay who it is for and why you need it; models fill gaps with generic guesses.
Role or perspective missingGive a perspective: “You are a senior UX writer…”. It sets vocabulary and depth.
Output format stated missingName the shape of the answer: table, bullets, JSON, 3 paragraphs.
Length or scope limit missingCap the length: “under 150 words”, “5 bullets”.
Constraints or rules missingAdd rules: what to avoid, what must be included, reading level.
Example or reference missingShow one example of the output you want. Few-shot beats description.
Specific, not vague missingReplace vague words (good, nice, interesting) with concrete criteria.

Let AI polish it

Sends your filled-in fields to the AI helper, which writes a complete prompt and marks gaps as [placeholders].

Prompting Claude well

Anthropic’s prompt engineering docs list a clear order of techniques: be clear and direct, use examples, let Claude think, use XML tags, give Claude a role, and chain complex prompts. This generator applies four of them automatically. The role line becomes “You are…”, facts go in <context>, rules in <constraints>, and your sample in <example>.

Long documents belong at the top of the prompt, above the instructions; Anthropic reports better answers on long-context tasks that way. Paste them into the Context field and they will be placed first.

Questions

Why does Claude like XML tags?

Anthropic’s documentation recommends XML tags such as <context>, <instructions> and <example> because they separate the parts of a prompt unambiguously. Claude was trained with this structure, so it follows tagged instructions reliably and can refer back to them by name.

Do the tag names matter?

Not much. Anthropic notes there are no special “magic” tag names. Consistency matters more: use the same tag for the same thing and refer to it by name, e.g. “using the facts in <context>”.

What is the <answer> line for?

Asking Claude to think first and then put only the final output in <answer> tags gives it room to reason while making the final result easy to copy or parse. Remove it for simple tasks.

Will this work in the Claude API and in Claude.ai?

Yes. Paste it as a message in Claude.ai, or use the role line as the system prompt and the tagged sections as the user message in the API.