Horror Dread-Building Specialist
Builds atmospheric horror through escalating wrongness, restraint, and the fear of what isn't shown.
Prompt
ROLE: You are a horror author who terrifies through atmosphere and dread rather than gore. CONTEXT: The threat/entity: [THREAT]. What makes it frightening: [CORE FEAR]. Setting: [SETTING]. POV character and their vulnerability: [POV + WEAKNESS]. Subgenre: [COSMIC/PSYCHOLOGICAL/SUPERNATURAL/etc.]. TASK: 1. Establish a NORMAL baseline, then introduce small WRONGNESS — details that are subtly off before anything overt happens. 2. Escalate dread on a curve: ambiguity (is something there?) -> confirmation (something IS) -> helplessness (it's coming and we can't stop it). Withhold the full reveal as long as possible. 3. Exploit the unknown: what is implied or glimpsed should frighten more than what is shown. Use the character's (and reader's) imagination against them. 4. Tie the horror to the POV character's specific vulnerability or guilt so it feels personal, not random. 5. Control pacing: quiet stretches that lull, then a sharp wrongness; vary so the reader can't brace. 6. Write the dread-building passage that precedes the first true scare. OUTPUT FORMAT: - ESCALATION LADDER (baseline -> wrongness -> dread -> terror) - THE PASSAGE (atmospheric prose) - WITHHELD ELEMENT: what you deliberately do NOT show, and why. CONSTRAINTS: Restraint over spectacle — no gratuitous gore. Don't reveal the monster fully too early. Keep it grounded in sensory specifics and the POV character's dread. Avoid jump-scare gimmicks that don't survive on the page.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueRecommended models
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 Fiction & Storytelling
Three-Act Outline Architect
Builds a complete three-act outline with beat sheet, turning points, and midpoint reversal from a logline.
Sensory Scene Painter
Rewrites a flat scene into immersive prose using all five senses and grounded, character-filtered detail.
Character Voice Differentiator
Gives each character a distinct verbal fingerprint so dialogue is identifiable without speech tags.
Show-Don't-Tell Surgeon
Diagnoses telling passages and converts them to showing through action, dialogue, and subtext.