Agent skill · creative production · aradotso
inkos-multi-agent-novel-writing
Multi-agent CLI system for autonomous novel writing, auditing, and revision with human review gates
Why this skill is useful
Adds a multi-agent CLI system with executable commands for autonomous novel writing and auditing that significantly extends the AI's creative capabilities.
What it needs
Requires npm installed locally. Requires openai account access. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
InkOS Multi-Agent Novel Writing Skill by ara.so — Daily 2026 Skills collection InkOS is a multi-agent CLI system that autonomously writes, audits, and revises novels. Agents handle the full pipeline: Writer → Validator → Auditor → Reviser, with human review gates at configurable checkpoints. Installation Requirements: Node.js ≥ 20.0.0 Quick Start Project Structure After inkos book create, the project directory contains: Core Commands Book Management Writing Pipeline Genre System Style Matching Spinoff (Prequel/Sequel/IF-branch) AIGC Detection Daemon (Continuous Production) Configuration Global Config (~/.inkos/config.json) Per-Book Rules (story/bookrules.md) Agent Architecture InkOS runs five specialized agents in sequence: Post-Write Validator Rules (Deterministic, No LLM) Rule Condition ------ ----------- Forbidden patterns 不是……而是…… constructs Em-dash ban —— character Transition word density 仿佛/忽然/竟然≤1 per 3000 chars High-fatigue words Per-book list, ≤1 per chapter Meta-narrative Screenwriter-style narration Report terminology Analytical framework terms in prose Author moralizing 显然/不言而喻 etc. Collective reaction 「全场震惊」clichés Consecutive 了 ≥4 consecutive sentences with 了 Paragraph length ≥2 paragraphs over 300 chars Book-specific bans bookrules.md forbidden list Audit Dimensions (33 total, LLM-evaluated) Key dimensions include: Dims 1–23: Core narrative quality (plot, character, pacing, foreshadowing) Dim 24–26: Subplot stagnation, arc flatness, rhythm monotony (all 5 genres) Dim 27: Sensitive content Dim 28–31: Spinoff-specific (canon conflicts, future info leakage, world rule consistency, foreshadowing isolation) Dim 32: Reader expectation management Dim 33: Outline deviation detection Code Integration Examples Programmatic Usage (TypeScript) Webhook Handler (Express) Custom Genre Definition Style Import Pipeline Audit Revision Loop The v0.4 hardened audit-revision loop prevents revision from introducing more AI markers: Key settings for audit consistency: Audit …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/inkos-multi-agent-novel-writing