Dialogue Naturalness Reviewer — Testing & QA agent for Claude Code
Seventh of book-forge's QA reviewers.
How to install Dialogue Naturalness Reviewer
Installs to ~/.claude/agents/jayping23-book-forge-dialogue-naturalness-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/JayPing23/book-forge/HEAD/agents/dialogue-naturalness-reviewer.md -o ~/.claude/agents/jayping23-book-forge-dialogue-naturalness-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Dialogue Naturalness Reviewer does
name: dialogue-naturalness-reviewer description: Seventh of book-forge's QA reviewers. Asks whether dialogue sounds like people talking rather than like a model writing dialogue — stiffness, report-speech, over-tagging, and unstaged exchanges. Owns GATE-001. Distinct from voice-consistency-reviewer, which asks whether each line sounds like its speaker; a cast can be perfectly distinct and uniformly robotic. tools: Read, Grep
dialogue-naturalness-reviewer
Identity
You exist becaus
Alternatives in Testing & QA
- Ad Onboard Reviewer — Independent reviewer for AutoDeploy model onboarding 14.5k ★
- Writ Reviewer — Reviews an implementation diff in two passes (spec-compliance first, then code quality) 187 ★
- Test Coverage Agent — Use this agent to analyse an entire module or directory for missing test coverage, then generate the missing t 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Voice Consistency Reviewer
One of book-forge's seven QA reviewers. Checks every dialogue line against its speaker's Voice Profile, flags
Motivation Agency Reviewer
One of book-forge's seven QA reviewers. Checks whether each character action traces to their Motivation Core a
Python Test Quality Reviewer
Analyzes git staged and unstaged changes to test files to detect unfocused tests, missing markers, weak assert
Flutter QA
Use after a feature is implemented and its tests are written, to verify it on a real simulator like a user wou
Mutation Survivor Triage
Classifies mutmut survivors and produces a per-file action list. Use after uv run mutmut run when survivors 0,
Engine QA Review Usability
After a change you've asked for is built, checks whether it actually works well for the people who use it — is
Related Skills
Gen Avatar
Generate a talking-avatar (lip-sync) video from an image + speech audio
Debate Run
Run debate exchanges between proposition and opposition
UnabatedPM Coaching
The first coaching-depth PM skills for AI. 27 skills with scoring rubrics, behavioral markers, real coaching e
