AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Webnovel Write

skill-zhao73-xiaoshuo-studio-webnovel-write · by Zhao73

Use when drafting a chapter in the local Codex studio from an approved plan and a selected style profile.

↗ Repository
— No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-zhao73-xiaoshuo-studio-webnovel-write

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Webnovel Write? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

webnovel-write

Purpose

Draft prose from the studio plan while staying grounded in technique-derived voice guidance.

Requirements

  • Local Codex CLI available
  • Active project context
  • Plan summary
  • Style profile with anti-AI focus items

Reference: docs/local-codex-studio.md

Workflow

  1. Confirm the plan is specific enough to write from.
  2. Restate the active anti-AI focus list before drafting.
  3. Write the draft as a local Codex execution task, not as a generic chat answer.
  4. Keep the prose aligned to:
  • project premise
  • scene goal
  • hook target
  • anti-AI focus list
  1. Queue webnovel-humanize or webnovel-review immediately after drafting.

Guardrails

  • Use reference-derived techniques, not named-author mimicry.
  • Prefer scene-level concreteness over abstract explanation.

Output

  • A draft suitable for the Draft Queue and Review Center.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Agent Skills