Hard-Constraint Prompt

Name: Hard-Constraint Prompt
Author: Rishi Jain

When the AI keeps drifting, lock it down. Word limits, banned phrases, mandatory sections, exact format.

Step 1

Get the skill

Pick one. Copy to paste straight away, or download constraint-prompt.md to keep.

Step 2

Paste it into your AI

Use when you keep getting "almost right" outputs. Banned-word lists are the highest leverage constraint.

Open Claude ↗Open ChatGPT ↗Open Gemini ↗

▸Preview the skill· what gets copied

Generate the output under these HARD constraints.

Task: {{TASK}}

Constraints (any violation is a fail, re-generate):
- Word count: between {{MIN}} and {{MAX}}
- Banned words: {{LIST}}
- Mandatory sections: {{LIST}}
- Tone: {{TONE}}
- Format: {{FORMAT}}
- Must NOT mention: {{LIST}}

Before returning, do a constraint check. If anything fails, fix it silently and return only the compliant output.

Works with: Claude · ChatGPT · Gemini · Any model

By Rishi Jain

More skills like this

📐

Output Format Forcer

Stops the AI from giving you walls of text. Forces JSON, tables, CSV, or numbered lists. Every single time.

⚡

CRAFT Prompt Framework

Rishi Jain's 5-part prompt structure. Context, Role, Action, Format, Tone. Works across every AI model.

🧩

Chain-of-Thought Prompt

Force the AI to think step-by-step before answering. Reduces hallucination, surfaces reasoning, catches mistakes.