dialogue-polish

dialogue-polish is a skill for Claude Code, Codex from felipelobomotta-blip/book-genesis-v4. It costs 39 tokens per session (2,436 once invoked), scanned A, original, MIT.

A focused editing pass for spoken lines in a finished book chapter. It checks that each character has a recognisable voice, natural rhythm, and meaningful subtext without rewriting narration or inner thoughts.

In plain words
What is it for?
Use it to review character speech, word choices, speech habits, dialogue tags, and surrounding action beats after a chapter draft is written.
Why use it?
It helps when characters sound alike or conversations feel forced. It also keeps the amount of dialogue appropriate for the intended genre.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review character speech, word choices, speech habits, dialogue tags, and surrounding action beats after a chapter draft is written.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add felipelobomotta-blip/book-genesis-v4 --skill dialogue-polish
Clone the repo
git clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dialogue-polish

README.md
[![agentmods](https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish/github.svg)](https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish)
Your own site
<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dialogue-polish

Your own site · 80×15
<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/dialogue-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.02436
Opus 5 $0.00019 $0.01218
Sonnet 5 $0.00008 $0.00487
Haiku 4.5 $0.00004 $0.00244

Measured 13d ago against content hash 9feb6b8dd243, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dialogue-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

legacy/skills/deprecated/dialogue-polish/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 changes.

1.1 Dialogue Ratio Check

  • Count total words in chapter
  • Count words inside dialogue (between quotation marks)
  • Calculate dialogue-to-prose percentage
  • Compare against voice-dna.md target range
  • Flag if outside range: RATIO_LOW or RATIO_HIGH

1.2 Voice Distinctiveness Scan For each conversation (2+ characters speaking), perform the Cover-the-Name Test:

  • Remove all attribution (names, tags, beats)
  • Read only the dialogue lines in sequence
  • For each line, attempt to identify the speaker from voice alone
  • Score: DISTINCT (immediately identifiable), WEAK (identifiable with effort), INDISTINCT (could be anyone)
  • Any INDISTINCT line is flagged for revision

Read the full file on GitHub · 195 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 195 lines · 39 tokens per session scan A 9feb6b8dd243

Subscribe to this mod's changes

dialogue-polish is a skill published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 2,436 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

humanizer

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…

Aboudjem/humanizer-skill · 139 tokens

clarity

Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…

addyosmani/clarity · 76 tokens

voiceprint

Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words…

charlie947/voiceprint · 83 tokens

red-pen

A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…

wpgaurav/claude-code-skills · 147 tokens

slop-detector

Score a draft, page, or caption set for AI slop with a four-tier severity model instead of a flat banned-words list. Exact production narration fails outright, rhetorical scaffolds warn only when repeated, lexical tells become review prompts, and document-level patterns are diagnosed. Use when the user asks to score…

wpgaurav/claude-code-skills · 96 tokens

monograph-writing

A workflow for managing the writing of long books, textbooks, academic monographs, technical books, or dissertations in small, checkable batches.

newdeme/monograph-writing · 489 tokens