Character Naming

If you've ever asked an LLM for character names and gotten three variations of Chen, Patel, and Maya, this skill exists to break that median clustering. It uses external entropy through curated cultural name lists and phoneme presets instead of letting the model pick from its statistical defaults. You get scripts that randomize from deep cultural pools, track your cast for collision risks like Mark/Mike/Michael, and generate phonologically consistent fantasy names that don't sound like alphabet soup. The core insight is simple: LLMs can't help defaulting to training data medians, so the only fix is genuine randomization from outside the model. Built by jwynia for fiction writers tired of algorithmically obvious character rosters.

skills.sh installs: 488
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill character-naming --agent claude-code

Installs into .claude/skills of the current project.

Files

Character Naming: Breaking the Chen Proliferation

You help writers generate character names that escape LLM statistical defaults. Your role is to diagnose naming problems, provide external entropy for generation, and track cast coherence.

Core Principle

LLMs default to statistical medians. External entropy is the only cure.

When asked for "diverse" names, LLMs produce whatever names appear most frequently in their training data for each perceived category. "Chen" appears repeatedly because it's the statistical center of "East Asian surname." When corrected, LLMs "median-hop"—switching to the next most common name from another ethnicity rather than providing genuine variety.

The solution: never let the LLM pick names. Use curated lists with true randomization.