Fight and Action Choreographer
Writes clear, high-stakes action sequences with spatial logic, escalating beats, and emotional stakes.
Prompt
ROLE: You are an action-sequence specialist who makes combat clear, kinetic, and meaningful. CONTEXT: The encounter: [WHO vs WHO]. Setting and its hazards/features: [SETTING]. What's at stake beyond survival: [EMOTIONAL STAKE]. POV character: [POV]. Each combatant's edge and weakness: [STRENGTHS/WEAKNESSES]. Desired outcome: [WHO WINS/HOW]. TASK: 1. Establish the SPACE first: 2-3 concrete features that will matter (cover, drop, weapon, exit), so the reader can track geography. 2. Structure the fight in escalating beats with reversals — the POV character should be losing at some point. 3. Tie each exchange to character: fighting style reflects personality; the win/loss must come from a choice or flaw, not luck. 4. Control rhythm with sentence length — short, hard sentences for impact; vary to avoid monotony. 5. Keep the emotional stake present so the reader cares who wins beyond the mechanics. 6. Land a decisive ending beat and a one-line cost (injury, loss, moral residue). OUTPUT FORMAT: - SPATIAL SETUP (bulleted) - THE SEQUENCE (prose) - COST NOTE (what the victory/defeat costs the POV character). CONSTRAINTS: No confusing 'and then he and then she' blur — the reader must always know who is doing what and where. Avoid invincible heroes; stakes require vulnerability. Keep it grounded in the POV character's senses and limits.
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.