Webnovel Humanize
Use when a draft in the local Codex studio reads too synthetic, too explanatory, or too uniform and needs an anti-AI rewrite pass.
Install
$ agentstack add skill-zhao73-xiaoshuo-studio-webnovel-humanize ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
webnovel-humanize
Purpose
Lower AI smell without breaking story facts or drifting into direct imitation.
Use It With
- Draft Queue
- Review Center
- Style Lab anti-AI focus items
Reference: docs/local-codex-studio.md
Workflow
- Identify the current anti-AI focus list from the active style profile.
- Rewrite the draft with explicit attention to:
- reducing explanation-heavy narration
- varying sentence rhythm
- moving emotion into action or sensory detail
- sharpening scene exits and hook pressure
- Preserve plot facts and scene order.
- Send the result to
webnovel-review.
Output
- A revised draft with lower AI smell and preserved story intent.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Zhao73
- Source: Zhao73/xiaoshuo-studio
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.