This diagnostic catches the stuff that makes dialogue feel dead: same-voice characters, on-the-nose exchanges, and single-function conversations. It's built around Sloane's principle that dialogue must do multiple things at once or it's too inert for fiction. You get six diagnostic states covering everything from exposition dumps to pacing mismatches, each with checklists and concrete interventions. The three-layer framework (text, subtext, context) is clean, and the double-duty test is a fast filter for whether an exchange is pulling its weight. Useful when your characters all sound like the same person or when conversations are just moving plot pieces around without revealing anything.

skills.sh installs
692
GitHub stars
182
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

Dialogue: Diagnostic Skill

You diagnose dialogue-level problems in fiction. Your role is to identify why conversations feel flat and guide writers toward dialogue that does multiple things simultaneously.

Core Principle

Dialogue must do more than one thing at a time or it is too inert for the purposes of fiction. (Sloane, 1979)

Good dialogue simultaneously advances plot, reveals character, builds tension, establishes relationship dynamics, and creates subtext. If dialogue is only delivering information, it's failing.


The Three Layers

Every line of dialogue operates on three layers:

LayerDefinitionCheck
TextWhat's literally saidIs it character-specific? Efficient? Natural rhythm?
SubtextWhat's meant beneath the wordsIs there a gap between said and meant?
ContextWhat shapes the exchangePower dynamics? History? What each character wants?

When dialogue fails, it usually fails at Layer 2 (no subtext) or Layer 1 (undifferentiated voices).


The Dialogue States

State D1: Identical Voices

Sponsors

Details

Repository
github.com/jwynia/agent-skills
Categories
AI & Agent Building, Debugging
First seen
Jun 3, 2026

More from jwynia/agent-skills

All 118
1jwynia avatarnovel-revisionjwynia/agent-skillsManage multi-level novel revisions while preventing cascade problems. Use when editing novels, when changes at one level break things at others, when you need s691skills.sh installs
2supabase avatarskill-creatorsupabase/agent-skillsGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabil691skills.sh installs
3rstackjs avatarrspack-best-practicesrstackjs/agent-skillsRspack best practices for config, CLI workflow, type checking, CSS, bundle optimization, assets and profiling. Use when writing, reviewing, or troubleshooting R689skills.sh installs
4theqtcompanyrnd avatarqt-qml-testtheqtcompanyrnd/agent-skills>-689skills.sh installs
5mukul975 avataracquiring-disk-image-with-dd-and-dcflddmukul975/anthropic-cybersecurity-skillsCreate forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD688skills.sh installs
6openai avatarcodex-result-handlingopenai/codex-plugin-ccInternal guidance for presenting Codex helper output back to the user688skills.sh installs