Write character dialogue that serves voice, relationship, subtext, pacing, and scene purpose without exposition-heavy speech.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill dialogue-writing --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Dialogue Writing?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-dialogue-writing)More formats (shields.io, HTML) on the badges page.
---
name: dialogue-writing
description: Write character dialogue that serves voice, relationship, subtext, pacing, and scene purpose without exposition-heavy speech.
---
# Dialogue Writing
Use for games, interactive fiction, scripts, narrative scenes, and character exchanges.
## Procedure
1. Define what each speaker wants in the scene and what they are unwilling or unable to say directly.
2. Anchor vocabulary, rhythm, formality, humor, and verbal habits in established character voice.
3. Let dialogue create action: reveal pressure, change relationships, deliver choices, or move the scene.
4. Hide exposition inside conflict, desire, misunderstanding, or concrete circumstance rather than information dumps.
5. Read exchanges for turn-taking rhythm and remove lines that restate what the audience already understands.
6. Check continuity with lore, character history, and branching state where applicable.
## Quality gate
Speakers should remain distinguishable without name labels, and the scene should be different at the end than at the beginning.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.