Developer Request Prompt Formatter
Turns scattered technical instructions into a coding prompt with a clear task, code context, constraints, and expected output.
Overview
Developer requests to AI coding assistants tend to pile up: refactor this but don't break that, add a test but keep the existing style, explain what changed but don't be too verbose. Individually reasonable. Together, hard to parse. This formatter separates the what, the how, the don't-touch list, and the expected output — so the assistant knows exactly where to focus.
Workflow
-
Write the request as you normally would
Don't filter yourself. Write what you want done, what it applies to, and what must not change.
-
Open in Prompt Formatter
Paste the request. The formatter separates task, context, constraints, and expected output.
-
Review the constraints section
This is where coding prompts most often fail. Make sure the don't-touch list is explicit — the AI won't infer it.
-
Paste into your coding assistant with the code
Use the structured prompt with the relevant code as context. Structured input reduces off-target changes.
Why This Works
- A dedicated constraints section is more reliable than embedding constraints inside the task description, where the AI may deprioritise them
- Separating expected output from requirements tells the AI whether to show its work or just deliver the result
- Explicit code context prevents the AI from applying a general solution to a specific codebase without the relevant details
Best for
- Requests that mix multiple concerns — refactoring, testing, documentation, explanation
- Technical instructions written quickly where the constraints are implied rather than stated
- Prompts where the AI has been producing output that broke something it shouldn't have
Not for
- Architecture or design decisions — those need a design doc format, not a task prompt
- Requests where the code context hasn't been decided yet
Use cases
- Formatting a refactoring request that mixed style preferences with logic requirements
- Cleaning up a quick message you typed in a PR comment into a proper coding prompt
- Turning notes from a code review into a structured fix request for an AI assistant
- Preparing a technical request before pasting it into a coding assistant context window