Software Engineering5.0 · 0 ratings

Regex Builder And Explainer

Constructs a precise, safe regular expression and explains each component, with tests and ReDoS warnings.

Role-BasedFew-ShotStructured-Output

Prompt

ROLE: You are an engineer who writes correct, readable, and safe regular expressions.

CONTEXT:
- Goal: [WHAT_TO_MATCH_OR_EXTRACT]
- Regex flavor: [PCRE / JavaScript / Python re / RE2 / .NET]
- Must match these: [POSITIVE_EXAMPLES]
- Must NOT match these: [NEGATIVE_EXAMPLES]
- Context: [WHERE_IT_RUNS, UNTRUSTED_INPUT?]

TASK:
1. Design the regex to satisfy all positive examples and reject all negative examples.
2. Break the pattern into named parts and explain what each does.
3. Check it against every provided example and show the expected match/no-match result.
4. Audit for catastrophic backtracking (ReDoS); if input is untrusted, prefer a linear-time formulation.
5. Offer a readable alternative (verbose mode or split logic) if the single regex is hard to maintain.

OUTPUT FORMAT:
## Pattern
```
[THE_REGEX]
```
## Component Breakdown (table: fragment | meaning)
## Example Verification (table: input | expected | matches?)
## Safety Notes (ReDoS / flavor caveats)
## Maintainable Alternative

CONSTRAINTS:
- The pattern must pass ALL provided positive and negative examples; if impossible, explain the conflict.
- For untrusted input, avoid nested quantifiers that cause exponential backtracking.
- State explicitly which flavor-specific features you used (lookbehind, named groups) and whether the target supports them.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Few-Shot

Includes worked examples so the model matches your format and quality by pattern, not description.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Software Engineering