Free guide · from the Reel
Turn a one-line request into a full prompt.
Type a rough request such as "plan a week of dinners". The prompt-builder skill asks up to 2 questions when important details are missing, writes a fuller prompt and runs it. You can copy that prompt to use again.
- 1 text file, 61 lines
- 4 steps
- Free skill
Published · Updated
Start buildingWhat it does
This is a made-up family example; a second Claude supplied the family's answers in our test. We typed one line:
/prompt-builder plan a week of dinners
Claude replied with 2 questions:
1. Who's eating, and does anyone have diet needs or foods they won't eat? (e.g. "2 adults + 1 kid, no pork")
2. How much time can you spend cooking on a weeknight, and do you want a shopping list too? (e.g. "30 min max, yes list")
The person answered in one line:
3 of us: me, my partner and our 7-year-old. Partner's vegetarian so all dinners need to be veggie, and the kid won't eat mushrooms. Weeknights 30 min max, weekends can take longer. Yes to a shopping list. I shop once on Sunday, so one list with quantities, grouped by shop section, in metric.
Claude then showed this prompt and ran it in the same reply:
## Goal
Plan 7 vegetarian dinners for my family (Sunday to Saturday) and give me one shopping list for the whole week.
## Context
We're 2 adults and a 7-year-old. My partner is vegetarian, so every dinner must be vegetarian. That includes cheese and pesto, since parmesan isn't. Our child won't eat mushrooms, so leave them out completely, and keep the food mild and kid-friendly. On weeknights (Mon–Fri) a dinner must take 30 minutes or less from start to table. Weekend dinners can take longer. I shop once, on Sunday, so plan the meals with the most perishable ingredients early in the week, and reuse ingredients across meals to cut waste.
## Output format
1. A table with these columns: Day | Dinner (one-line description) | Total time.
2. One combined shopping list in metric, with quantities for 3 people, grouped by shop section.
3. A short "check you have" list of pantry basics.
## Limits
Don't include recipes or alternative options. Don't use mushrooms or any non-vegetarian ingredients.
Those answers tell Claude to make every dinner vegetarian, avoid mushrooms and keep weeknights within thirty minutes. Claude also caught that parmesan isn't vegetarian, so the shopping list says "vegetarian hard cheese". Read the prompt it builds before reusing it, because it can still add assumptions: here it added mild food, perishable meals early in the week and "no recipes or alternative options", which comes from the skill's rule against extras.
In our test the skill made Claude ask before it guessed, but it didn't save messages or tokens. The section on your Claude limit below covers what does.
What you need
- Claude Code or the Claude app: Claude Code runs in the terminal or in the Code tab of the Claude desktop app, and needs a paid plan or API billing. In the Claude app, you need Skills and code execution turned on. Our tests ran in Claude Code 2.1.314.
- The skill file below: one text file, 61 lines. You copy it from this page.
The steps
Step 1: Save the skill file
First choose where you will use it: Claude Code or the Claude app. Save the skill once in step 1, follow only the installation section for your choice, then go to "Use it". We tested the Claude Code route.
Make a folder called prompt-builder and save this inside it as SKILL.md.
---
name: prompt-builder
description: Turns a short, messy request into one complete prompt (goal, context, input, format, limits), then runs it. Use when someone types /prompt-builder or asks to build or fix a prompt.
---
# Prompt builder
The user gives you a rough request, often one line, sometimes with pasted text. Write the prompt they should have sent, then follow it, so the first answer is usable and they don't spend messages on retries.
## Step 1: Check what is missing
Read the request and any pasted text. For each part below, decide if you know it, can safely assume it, or must ask:
- Goal: what should come out, and what "done" looks like.
- Context: who reads or uses the result, where it goes (email, WhatsApp, a form, a spreadsheet), and the facts it depends on.
- Input: the text, data or files to work from.
- Output format: length, layout and file type.
- Limits: what must stay the same, what to avoid, tone.
Ask when a wrong guess would make the answer unusable. These usually are:
- Who it is for and where it will be posted, because length, layout and tone depend on it.
- What the reader should do next (for messages: reply, pay, confirm by a date).
- Facts only the user knows: which job, who eats the meals, which date format.
Ask at most 2 questions, in one short message, numbered, each answerable in a few words. If nothing important is missing, ask nothing and go to step 2.
If the user says "just guess" or skips a question, assume something sensible and list it under Assumptions.
## Step 2: Write the prompt
Write it in the user's language, as plain instructions. Use this shape and drop any heading that would be empty:
```
## Goal
One or two sentences, starting with a verb.
## Context
Who it is for, where it goes, why, and the facts that matter. Give the reason behind rules.
## Input
Point to it: "the email I pasted above". Don't copy it.
## Output format
Exactly what to return: length, layout, what to put first.
## Limits
What to keep, what not to change or invent, tone.
## Assumptions
Only if you guessed something. One line each.
```
Rules:
- Don't copy the user's pasted text into the prompt. It is already in the chat, and copying it repeats the same text in Claude's reply. If the user wants a prompt to reuse later, write "[paste your text here]" instead.
- Ask only for what the user asked for. Don't add extras (recipes, options, explanations); longer answers use more of their limit.
- Ask for the finished thing, with no [placeholders].
- Keep the prompt short: about 150 words is enough for most tasks.
## Step 3: Show it, then run it
Put the prompt in one code block so the user can copy and reuse it. Then, in the same reply, under a line "Result:", do the task exactly as the prompt says. If the user asked only for the prompt, stop after the code block.
Tip: keep the folder name and the name: line the same. The Claude app needs them to match, and in Claude Code the folder name is the default name.
Step 2: Install in Claude Code
Go to the folder where you start Claude Code, the one that holds your prompt-builder folder. Copy the folder under .claude/skills/:
mkdir -p .claude/skills
cp -r prompt-builder .claude/skills/
Tip: to use it in every project, Anthropic's docs say to put the folder in ~/.claude/skills/ instead.
Step 3: Install in the Claude app
First check that Customize > Skills shows up in your Claude account. If it doesn't, your plan may not include it (see the FAQ).
Zip the folder so the ZIP holds the prompt-builder folder itself, not just the file:
python3 -c "import zipfile; z=zipfile.ZipFile('prompt-builder.zip','w'); z.write('prompt-builder/SKILL.md'); z.close()"
Then follow Anthropic's help page:
- Turn on code execution under Settings > Capabilities ("Code execution and file creation", or "Create and edit files" in the newer layout).
- Go to Customize > Skills and click +.
- Click "+ Create skill", then "Upload a skill", and pick the ZIP.
Step 4: Use it
In Claude Code, type /prompt-builder and your request the way you'd normally say it. Paste any text it should work on below the request. In the Claude app, ask in plain words. Fill in the brackets:
/prompt-builder [your request, the way you'd normally say it]
use prompt-builder to turn this into a full prompt: [your request]
Answer its questions in a few words. It then shows the prompt in a copy block and runs it.
Tip: you don't have to type the slash. We asked "can you turn this into a proper prompt: plan a week of dinners", and Claude picked the skill by itself and asked the same 2 questions.
Ask for changes in normal words
Add one of these to your request, or send it as a reply:
Just guess and go.
Only give me the prompt, don't run it.
Table only, no recipes.
Make it a prompt I can reuse later with my own text.
Make your Claude limit last longer
These habits help. Anthropic's pages (read on 31 Oct 2026) don't give a fixed number of messages for any plan. Your allowance depends on your plan and how you use Claude.
Start a new chat when you switch jobs. Every message re-reads the chat so far. Claude Code's docs say it "sends your full conversation with every request", and the help center lists "current conversation length" as a factor in the Claude app too. So a wrong first answer keeps costing, because every later message carries it along. Anthropic's advice is to "try starting a new conversation if you're approaching your usage limit in a longer chat" (How usage and length limits work). In Claude Code, use /clear between unrelated tasks. /compact keeps a summary, but it reads the whole chat to make it, so it is a large request itself. /usage shows what is using your plan (Manage costs).
Keep uploads and messages lean. "File attachment size" and "message length" are on the same list. If you use the same files again and again, put them in a Project: project content "is cached and counts less against your limits when reused" (Usage limit best practices).
Pick the model for the job. The model and the effort level both count (How usage and length limits work). For Claude Code, Anthropic says Sonnet "handles most coding tasks well and costs less than Opus". Keep Opus for hard reasoning, and switch with /model (Manage costs).
Turn off tools you don't use. Research, web search, artifacts, running code and creating files all count, and "tools and connectors are token-intensive". In Claude Code, each subagent sends its own requests, and agent teams use "approximately 7x more tokens" than a normal session when teammates run in plan mode. A vague request like "improve this codebase" makes Claude scan widely (Manage costs).
On a Claude subscription, one limit covers everything. API usage is billed per token instead, separately from any plan (Manage costs). Claude on the web, Claude Code and the desktop app "count towards the same usage limit". On most plans the session limit resets five hours after your first message, and the weekly limit once a week. Anthropic says verified Ultra accounts don't have the five-hour limit (Usage limit best practices).
If something looks off
The skill doesn't show up
In Claude Code, check the path is .claude/skills/prompt-builder/SKILL.md in the folder you started Claude in. Then start a new session, because a skill added mid-session may not load. In the app, Anthropic's help page lists the usual causes: the ZIP has the file at its root instead of inside the folder, the folder name doesn't match the skill name, or code execution is off.
The app rejects the file name
Anthropic's help page writes skill.md, while its developer docs and its own skills on GitHub use SKILL.md. Both names appear in Anthropic's docs. We used SKILL.md, and the packaging checks above are the documented causes to rule out first.
It guessed instead of asking
On our meeting summary, it assumed the summary was for "an email or a group chat" and the answer still needed changes. Put the detail in your request ("for our WhatsApp group, under 150 words") and it uses that.
The answer is much longer than I wanted
Check the "Output format" lines in the prompt it shows you, then say "no recipes" or "table only".
Credits
- Claude Code 2.1.314 by Anthropic, model claude-opus-5-5: not open source, needs a Claude plan or API billing.
- The skill format follows Anthropic's Skills in Claude Code page and the Agent Skills overview. The description stays under the 200 characters the Claude app allows. Anthropic's overview says Claude uses a skill automatically when your request matches its description.
- The prompt shape follows Anthropic's prompting best practices ("If they'd be confused, Claude will be too") and our own how to prompt page.
- The skill, the test inputs and the test script are ours. Use, copy and change them freely.
- The 5 test jobs come from what people ask for: they ask Claude and ChatGPT to make emails "sound nicer / polite" (HN), to summarise meeting transcripts (HN), to plan meals around which kid won't eat what (HN), and to write cover letters, which don't work "from just the resume" (HN). Claude's help page lists processing CSV files (Anthropic). Almost two thirds of ChatGPT writing requests are to edit text the user already has (The Register on NBER paper w34255).
How we tested
We gave Claude Code (claude-opus-5-5) 5 everyday jobs with made-up inputs: soften a rude email, summarise a meeting for WhatsApp, fix a messy CSV, plan a week of dinners and write a cover letter from a CV. Each job ran twice with the skill and twice without, and a second Claude played the person: it knew the details the request left out, answered questions and decided when the answer met 5 points we wrote down beforehand. Both ways took 17 messages, but with the skill 4 of them were short answers to Claude's questions instead of corrections, and the total tokens Claude Code reported for the chats were 25% higher (133,409 against 106,610). On dinners, the one-line request without the skill got a plan with chicken and fish in both runs, and the next message had to explain the family is vegetarian. The skill asked the right questions on dinners and the cover letter, and missed one on the meeting summary. Two runs per job is a first look: we didn't test the app upload, long chats or other models, and Anthropic doesn't say how token counts map to your plan's limit.
| Job | Messages, no skill (2 runs) | Messages, with the skill (2 runs) | Corrections, no skill → skill |
|---|---|---|---|
| 1 and 1 | 1 and 1 | 0 → 0 | |
| Meeting | 2 and 3 | 3 and 2 | 3 → 3 |
| CSV | 1 and 1 | 1 and 1 | 0 → 0 |
| Dinners | 2 and 2 | 2 and 2 | 2 → 0 |
| Cover letter | 2 and 2 | 2 and 2 | 2 → 0 |
| Total | 17 | 17 | 7 → 3 |
Questions people ask
Will this skill stop me hitting my Claude limit?
Not on its own. In our test it took the same number of messages as no skill (17 each over 10 runs) and 25% more tokens in total, counting the skill's instructions, its questions, the prompt it writes and the answers. What changed was the order: Claude asked first instead of guessing and being corrected. For ways to use less of your limit, see "Make your Claude limit last longer" below.
Does it work in the Claude app or only in Claude Code?
The same SKILL.md follows Anthropic's format for both. In the app you upload it as a ZIP under Customize > Skills, with code execution turned on. Our tests ran in Claude Code.
Do I need a paid Claude plan?
Claude Code needs a paid plan or API billing. For the Claude app, Anthropic's help page lists Skills on Free, Pro, Max, Ultra, Team and Enterprise, while its developer docs list custom skills on Pro and up. The quickest check is to look for Customize > Skills in your own account.
When should I use it?
When the details that matter are in your head and not in the chat: who eats the meals, which job the cover letter is for, where a summary will be posted. When you paste everything Claude needs, as with our spreadsheet test, plain Claude got it right on the first try and the skill added nothing.
Read it on your computer
Keep this guide for later.
We'll send you this page's link and the other free guides.