ForkFree

Prompts / Other

Turn a Vague Request Into a Sharp Prompt

You get a single, well-structured prompt in place of a vague request, so the target AI is far more likely to get it right first time. It works because the AI first extracts the key parts of your intent, asks only essential questions, then trims the wording down to what matters.

Worked in our testThe reply gives one copyable prompt block with an objective, firm constraints, a "done when" checklist, concrete values, and a single "Strategy:" line. It leaves out the step 1 extraction and any note on missing items, and it doesn't state that no questions were needed. It also adds invented details such as hex codes, a 40-line JS cap and a subfolder path, though these are reasonable.

The prompt

Act as an expert prompt engineer who writes tight prompts for AI tools.

Task: Turn my rough request into one precise, ready-to-paste prompt for {target_tool}.

Rough request: {rough_request}
Background details: {background_details}
What a finished result must look like: {success_criteria}

Steps:
1. Pull out the task, input, output format, constraints, audience and success criteria from what I wrote. Note anything critical that is missing.
2. If something essential is missing, ask at most 3 short questions and wait. Otherwise carry on.
3. Draft the prompt using the structure that suits {target_tool}, with a clear objective, firm constraints and a "done when" checklist.
4. Cut every word that does not change the result, and replace vague terms with concrete values.

Output:
Give the final prompt in one copyable block. Under it, add a single line starting "Strategy:" explaining the main choice you made.

Change the parts in curly braces. Use it before sending a long or costly request to a coding or image tool, when you suspect your first attempt would need several rounds of correction.

What happened when we ran it

We sent

Act as an expert prompt engineer who writes tight prompts for AI tools.

Task: Turn my rough request into one precise, ready-to-paste prompt for Claude Code.

Rough request: Build me a landing page for my bakery's online ordering. It should look warm and friendly, work on phones, and let people pick a collection time. Keep it simple because I will edit it myself afterwards.
Background details: The bakery is called Hearth & Crumb, based in Leeds. We sell sourdough, pastries and celebration cakes. Brand colours are cream, terracotta and dark brown. I know basic HTML but not any frameworks.
What a finished result must look like: One HTML file with embedded CSS and light JavaScript. Looks right at 375px and 1440px wide. Has a menu section, a collection time picker, and a contact footer. Opens in a browser with no console errors.

Steps:
1. Pull out the task, input, output format, constraints, audience and success criteria from what I wrote. Note anything critical that is missing.
2. If something essential is missing, ask at most 3 short questions and wait. Otherwise carry on.
3. Draft the prompt using the structure that suits Claude Code, with a clear objective, firm constraints and a "done when" checklist.
4. Cut every word that does not change the result, and replace vague terms with concrete values.

Output:
Give the final prompt in one copyable block. Under it, add a single line starting "Strategy:" explaining the main choice you made.

The model replied

``` Build a single-file landing page for Hearth & Crumb, a Leeds bakery selling sourdough, pastries and celebration cakes, to promote online ordering. OUTPUT Create `hearth-and-crumb/index.html` in the current directory. It is one file with embedded <style> and <script>. Do not create any other files. PAGE SECTIONS (in order) 1. Header: bakery name, tagline, and a button that scrolls to the collection picker. 2. Menu: three groups (Sourdough, Pastries, Celebration Cakes), each with 3 placeholder items showing name, one-line description and price in £. 3. Collection time picker: - A date <select> offering the next 7 days. - A time <select> with 30-minute slots from 08:00 to 16:00. - A "Confirm collection time" button that shows a plain-text confirmation, e.g. "Collection: Sat 31 Oct, 10:30". - No backend, no data sent anywhere. 4. Footer: address, phone, email and opening hours, all clearly marked placeholders such as "[Add street address], Leeds". DESIGN - Colours as CSS variables in :root: cream #F7EFE2 (background), terracotta #C65D3B (buttons, accents), dark brown #3B2416 (text, footer). - Warm and friendly feel: Georgia for headings, system sans-serif for body, rounded corners of 8–12px, generous spacing. - Mobile-first. Menu is one column at 375px and three columns at 1440px. Content max-width is 1100px, centred. - Text contrast of at least 4.5:1. Buttons are at least 44px tall. CONSTRAINTS - Plain HTML, CSS and vanilla JS only. No frameworks, libraries, CDNs, external fonts or images. - The owner knows basic HTML but no frameworks, so: - Use semantic tags and readable class names. - Put an HTML comment above each section saying what to edit. - Put the opening time, closing time, slot length and days ahead as named constants at the top of the <script>. - Keep the JS under about 40 lines with short comments. - Do not invent real business details (address, phone, email, prices are placeholders). DONE WHEN - [ ] Only `hearth-and-crumb/index.html` was created. - [ ] At 375px and 1440px wide there is no horizontal scroll and no overlapping or clipped text. - [ ] The date and time pickers work, and the confirmation text updates correctly. - [ ] The browser console shows no errors or warnings on load or on interaction. - [ ] All three brand colours are used via the CSS variables. - [ ] Every placeholder is easy to find (search for "[Add"). - [ ] Verify the layout and console at both widths using a headless browser if one is available. If not, say exactly what you could not check. When finished, reply with a 3-line summary: what was built, where the editable constants are, and anything unverified. ``` Strategy: I turned the vague "warm", "simple" and "works on phones" into hex colours, fonts, breakpoints, tap-target sizes and a roughly 40-line JS cap, and added a verifiable "done when" checklist, so Claude Code has nothing to guess and you get a file you can edit easily.

Run on Claude Sonnet 5.5, 29 Oct 2026. Automatic check: 4 out of 5.

Mentioned for

Claude, ChatGPT, Gemini, Claude Code, Cursor

Where it came from

Found on GitHub, shared by nidhinjs: nidhinjs/prompt-master.

This is our own version of the idea, written and tested by us. The original may differ.

More other prompts

Other Worked in our test
Goal, effort and self-check prompt

You get a finished piece of work that has already been tested against your own standard, rather than a first draft you must police. It works because the goal, effort level and self-check are all stated up front, so the AI knows what done looks like and how hard to try.

Found on Web, shared by Mahnoor Faisal (XDA Developers), reporting advice from Boris Cherny