Multi-Agent Novel Creation System
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md and install @user_6d9676ae/novel-multi-agent-skill into your AI assistant.
About this skill
Problem Addressed
Long-form novel writing often breaks down on setting drift, inconsistent character behavior, unstable chapter quality, and missing acceptance criteria between outlines and prose. A single model generating text in one pass tends to produce only plot summaries, making it hard to keep chapters within word-count, pacing, and safety requirements.
How the Skill Works
This skill decomposes novel production into specialized agent roles: director, world-building, character design, plot planning, chapter writing, and quality review. The pipeline starts by initializing a project, then generates world rules, character profiles, and a chapter outline before producing chapters of 1800–2200 words. Review scores each chapter across prose, character, pacing, logic, and creativity, and triggers revision suggestions when the score is below 40.
Boundaries and Notes
It fits long-form genres such as urban romance, fantasy, and sci-fi, but depends on file read/write access and a configured large-model API. Creative models are better suited for prose generation, while rigorous models are better for review. Content involving real place names, real personal names, or sensitive events is treated as a hard restriction, so it is not suitable for sensitive real-world subject matter.
Use Cases
- A web-novel writer splits a rebirth story into world rules, characters, and chapter outlines, then generates reviewable drafts.
- An editor converts existing settings into 1800–2200-word chapters and requests revision notes from a five-dimension score.
- A content team batches 20–30 chapter drafts, then checks character consistency, pacing, and sensitive-content boundaries.
- A planner sets chapter hooks for romance, mystery, or sci-fi projects while enforcing word-count and score thresholds.
Best For
- Long-form novel writers who need to turn outlines into chapter drafts while keeping characters and settings consistent.
- AI application developers who want to build a configurable novel pipeline with OpenClaw and multiple LLMs.
- Content editors who need to review logic, pacing, characterization, and sensitive content against scoring rules.
- Independent creators who want to split character design, world-building, plotting, and prose writing into reusable workflows.
Related Skills
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.
A hybrid-evolution agent for OpenClaw developers that offers tiered-confirmation and rollback-safe capability optimization.