InkOS Multi Agent Novel Writing Skill by [ara.so](https://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/book rules.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 book rules.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: Auditor always runs at temperature: 0 — eliminates 0–6 critical variance on same chapter Default revision mode is spot fix (only modify problem sentences) rewrite mode is available but measured to introduce 6× more AI markers polish mode is boundary locked: no paragraph add/delete, no name changes, no new plot Spinoff Canon Constraints When parent canon.md is detected, 4 additional audit dimensions activate automatically: Troubleshooting Validator fires on every chapter Check book rules.md fatigue word list — words listed there are enforced ≤1 per chapter. Remove infrequently used terms. Audit results wildly inconsistent between runs Confirm auditor temperature is locked to 0 in config. If using a proxy LLM API, ensure it respects temperature: 0 . Revision introduces more AI markers than original This is expected behavior — InkOS v0.4 automatically detects this and discards the revision. If it happens repeatedly, switch from rewrite to spot fix mode explicitly. Spinoff audit incorrectly flags events Verify parent canon.md has accurate divergence point timestamps. Events before the divergence point are canon locked; events after are fair game for the spinoff. Daemon stops a book after repeated failures Check daemon status for the suspended book. After fixing the underlying issue (usually outline ambiguity or book rules.md contradiction), run inkos daemon resume 书名 . Style guide not being applied by writer Run inkos style import again — if style guide.md is missing or empty, the writer skips style injection silently. Check that the reference text is ≥5000 characters for reliable fingerprinting.

inkos-multi-agent-novel-writing