dialogue-polish

Solid

Dedicated dialogue editing pass — ensures distinct character voices, subtext, natural rhythm, and correct dialogue-to-prose ratio. Runs AFTER prose-craft and BEFORE chaos-engine.

AI & Automation 132 stars 40 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
71
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Dialogue Polish ## PURPOSE This skill performs a focused, dialogue-only editing pass on completed chapter drafts. It does NOT touch narrative prose, description, or internal monologue — only spoken dialogue and immediately surrounding dialogue mechanics (tags, beats, attribution). The goal: every line of dialogue in the manuscript should pass the **Cover-the-Name Test** — if you hide who is speaking, the reader can still identify the character from voice alone. ## WHEN TO RUN - **After:** prose-craft (the chapter draft exists) - **Before:** chaos-engine (chaos markers may adjust dialogue placement) - **Trigger:** Orchestrator calls this skill per-chapter or in batch after prose-craft completes a section - **Re-run:** After any major revision that rewrites dialogue-heavy scenes ## REQUIRED INPUTS 1. **Chapter draft** — the prose-craft output file (e.g., `chapters/chapter-03.md`) 2. **voice-dna.md** — must contain: - Character voice cards with speech patterns, vocabulary, verbal tics, sentence length preferences - Dialogue-to-prose ratio target for the genre - Any character-specific dialogue rules (e.g., "Marcus never uses contractions when angry") 3. **foundation.md** — for character profiles (wound, lie, want, need) to inform subtext decisions 4. **outline.md** — for the chapter's subtext layer definition ("surface conversation vs. REAL conversation") ## PROCESS ### PHASE 1: AUDIT (Read-only) Read the chapter and produce a diagnostic before making any cha...

Details

Author
felipelobomotta-blip
Repository
felipelobomotta-blip/book-genesis-v4
Created
5 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category