novel-forgeLong-form novel workflow for creating, continuing, resuming, and repairing serialized fiction with externalized project state, role-to-model mapping, worldbu...
Install via ClawdBot CLI:
clawdbot install 228998098/novel-forgeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Sep 27, 2026
Independent authors and small studios use novel-forge to run a long-running web novel pipeline with externalized project state, chapter batches, and consistency review. The role-to-model mapping lets them assign stronger reasoning models to outlining and cheaper fast models to high-volume drafting.
Writers who lost context to truncation or long gaps can resume a draft from a specific chapter with canon and memory tracking restored. The recovery role plus persisted outlines and character sheets rebuild the story state before new chapters are drafted.
Teams of writers and editors configure separate roles for worldbuilding, characters, outlining, style, drafting, and review, with each stage gated on the previous one being stable. The orchestrator routes spawned sessions rather than authoring canon itself, enforcing separation of duties.
Model vendors and researchers compare how different LLMs perform in planner, prose, review, and fast-draft roles within a controlled novel workflow. The recommended mapping draft and alternates make it easy to score models on real long-form creative tasks.
Game studios adapt the stateful pipeline to build branching or serialized game lore, character bibles, and chaptered story arcs. The taboo list and execution mode settings keep narrative within brand and rating constraints across many sessions.
Offer a monthly subscription to individual writers with limits on chapters per month, number of projects, and model access tiers. Higher tiers unlock multi-agent orchestration and premium model mapping for review and outlining roles.
Sell per-seat licenses to writing teams, studios, and publishers that need shared project state, role-based access, and multi-agent collaboration on long series. Include admin controls for role-to-model mapping policies and canon approval gates.
Charge clients a per-project or per-chapter fee to produce serialized fiction, including outlines, drafts, and consistency passes run by the novel-forge pipeline. Add rush tiers for accelerated chapter delivery or full manuscript recovery.
💬 Integration Tip
Require an explicit role-to-model mapping in project state before any canon work, and use an actual sessions_spawn probe rather than agents_list to confirm multi-agent availability. Keep the main session limited to routing and scaffold creation so the orchestrator never authors canon directly.
Scored Sep 27, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...