A publication-grade Chinese novel writing skill pack designed for long-form fiction using a distributed multi-agent architecture.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install novel-master-probe
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install novel-master-probe using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is novel-master?
novel-master is a professional-grade content creation skill pack built to handle the entire lifecycle of publishing-quality long-form fiction, bridging the gap between web fiction and literature standards. It guides authors and AI agents from initial worldbuilding and deep character arc definition through detailed plotting, chapter drafting, and multi-layered quality control.
In its v2 iteration, the skill introduces an advanced distributed architecture that treats distinct narrative components as isolated sub-processes. By moving away from monolithic context limits and leveraging modular tracking files, it ensures consistency across millions of words, preventing common AI long-form issues like dropped subplots, breaking out-of-character (OOC) barriers, or trailing off into narrative dead ends.
novel-master Use Cases
- Creating high-quality long-form web or print novels across suspense, romance, sci-fi, historical, fantasy, and realism genres.
- Structuring multi-arc book plots systematically using three-act paradigms and structural dramaturgy frameworks.
- Maintaining flawless continuity in deep narrative universes with complex character rosters, distinct voice profiles, and multi-volume timelines.
- Tracking, embedding, and retrieving intricate subplots and foreshadowing setups over extensive structural distances.
How novel-master Works
- Project Initiation & Planning: Loads narrative foundations, configures structural rule frameworks, builds the directory workspace, and outputs a highly comprehensive Book Creation Proposal containing character arcs and world properties.
- Outline Architecture: Drafts global multi-volume plotlines and breaks them down into fine-grained chapter segments (5 to 10 chapters at a time) specifying character viewpoints and emotional trajectories.
- Distributed Execution (v2 Loop): The Chapter Daemon reads perspective biases, generates the prose, updates character state-machines via a unified Plot Bus, and commits factual nodes to a compressed narrative graph.
- Quantum Auditing: Intercepts completed drafts to cross-check dimensional criteria (naming consistency, timeline progression, geographic accuracy, and open subplots) blocking and revising any execution errors automatically.
- State Finalization: Synchronizes persistent structural states inside the tracking workspace tracking metrics, unrecovered subplots, and total words.
novel-master Setup
To deploy this skill within your workspace environment, ensure you have the required runtime dependencies and execute the script tasks as shown below:
# Navigate to your workspace context
cd ~/.qclaw/workspace/
# Initialize a brand new character state-machine process with specific behavioral bias profiles
python scripts/char_state.py init "YourNovelName" "CharacterName" --bias 101
# Run a quantum gateway audit over the latest chapter drafts to confirm system integrity
python scripts/auditor.py gate "YourNovelName" 5
novel-master Data Schema & Taxonomy
Every narrative project manages its structured taxonomy across a strict workspace folder hierarchy:
| Directory / File | Format | Analytical Purpose |
|---|---|---|
settings/world.md |
Markdown | Comprehensive world-building overview and environmental parameters. |
settings/characters/ |
Markdown | Individual character sub-files defining specific voice lines and psychological parameters. |
outline/arc-outline.md |
Markdown | Global long-term narrative direction separated by thematic volumes. |
tracker/foreshadowing.json |
JSON | Relational data tracking subplot index, trigger chapters, visibility layers, and target recovery milestones. |
tracker/conflicts.json |
JSON | Analytical record tracking active physical or psychological narrative friction points. |
state.json |
JSON | Dynamic orchestration ledger recording global metadata metrics, target volumes, and current resolution tracking states. |
novel-master Advanced Features
- Process-per-Character (PpC): Treats core entities as independent state machines interacting solely through an explicit Plot Bus pipeline to eliminate homogeneous AI outputs.
- Node-Compressed Graph (NCG): Synthesizes structural chapter facts into tightly bound delta nodes (<= 200 words) allowing long-range plot tracing without expanding context windows.
- Fault Recovery Engine: Restores corrupted, lost, or drifting agent context windows by replaying sequential Plot Bus event logs directly from compressed snapshots without re-running the entire book script.
- Cognitive Bias Injection: Enforces dynamic sensory filtering and psychological blindspots to create authentic characters that react with flawed human logic rather than generic AI omniscience.
SKILL.md
Loading
Related Openclaw Skills
biaoshu-writer-corp
An AI-powered bidding assistant that automates document parsing, docx generation, and strict compliance risk analysis via an asynchronous API connection.
novel-master
A publication-grade Chinese long-form novel creation framework powered by a unique distributed multi-agent architecture.
Taiwan Stock Exchange (TWSE) API
A developer integration that enables programmatic retrieval and analysis of Taiwan Stock Exchange open data without authentication.
AI Sidekick
A comprehensive configuration and runtime optimization system to manage persona, memory, and security for OpenClaw agents.
TKSeller
TKSeller is an interactive automation skill designed to integrate custom TikTok seller SaaS platforms directly with messaging clients.
DXF Generation and Validation
An AI agent skill to programmatically generate, update, and validate 2D DXF drawings and CAD projections from Python sources.
Featured*
