Webnovel Write
CheckedGenerates creative webnovel chapters in various genres based on prompts, outlines, or existing story elements.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add lingfengqaq/webnovel-writer --skill webnovel-write -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
lingfengqaq
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned lingfengqaq/webnovel-writer at 54513e3e1a.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 54513e3e1a
- Scanned
- 13 files, 1,399 lines
About this skill
What it does
The Webnovel Write skill generates creative webnovel chapters in various genres. It follows a structured workflow to produce publishable chapters, aiming for a default length of 2000-2500 words (unless otherwise specified). The process includes review, polishing, and data feedback loops to ensure quality and maintain context throughout the writing process. The skill outputs structured data including chapter content, review metrics, summaries, and chapter metadata.
When to use it
- Generating chapters for a webnovel project based on prompts or outlines.
- Creating new chapters that build upon existing story elements.
- Producing chapters in specific genres like esports, livestreaming, or cosmic horror.
- When you need a consistent and structured approach to writing webnovel content.
- To ensure quality through automated review and data feedback.
Key capabilities
- Generates webnovel chapters based on prompts or existing story elements.
- Follows a defined workflow with distinct steps (e.g., writing, style adaptation, review, polishing).
- Supports different modes:
/webnovel-write(full process),/webnovel-write --fast(skips style adaptation), and/webnovel-write --minimal(basic review only). - Produces structured data including chapter content (
.mdfiles), review metrics (index.db.review_metrics), summaries (.mdfiles), and metadata (.webnovel/state.json). - Includes automated review and quality control steps using a Task sub-agent.
Example prompts
- "/webnovel-write Generate chapter 5 of my fantasy novel, focusing on the protagonist's training."
- "/webnovel-write --fast Continue chapter 12 based on this outline: [outline content]"
- "/webnovel-write Create a new chapter for my esports webnovel, incorporating these key events: [event details]"
Tips & gotchas
- The skill requires complete input to start the writing process; missing information will halt execution.
- Review and data feedback are mandatory steps that cannot be skipped entirely.
- The skill relies on a structured workflow with specific steps, and attempting to combine or skip these steps is prohibited.