AGENT SKILL

voice-novel

Local machine skill for VoiceNovel — handles story export to disk.

License 许可
MIT
最近更新
2026-09-04
Stars
★ 0
Forks
0

01 前言 Front Matter

name
voice-novel
author
rabbit-r1-skillz
version
1.0.0
commands
[ "export-story" ]
description
Local machine skill for VoiceNovel — handles story export to disk.

02 资源文件 3

03 SKILL.md 正文

VoiceNovel — OpenClaw Skill

This skill bridges the VoiceNovel R1 Creation to your local machine. It handles one responsibility:

  1. Story export — saves your collaborative novel as a .txt file on your machine when you long-press PTT from the chapter list.

Setup

1. Install OpenClaw

Follow the main clawhound skill documentation to install and run the OpenClaw polling daemon on your machine. The daemon watches openclaw:cmd in the R1's shared storage and dispatches commands to registered skills.

2. Register this skill

Place this directory (or a symlink to it) in your OpenClaw skills folder, typically:

~/.openclaw/skills/voice-novel/

Or register via the OpenClaw config file:

{
  "skills": [
    { "name": "voice-novel", "path": "/absolute/path/to/voice-novel/skill/" }
  ]
}

3. Create the skill handler

Create a file at ~/.openclaw/skills/voice-novel/handler.js (or .py if you prefer Python — see below):

// handler.js — Node.js OpenClaw skill handler for voice-novel
const fs = require("fs");
const path = require("path");
const os = require("os");

const EXPORT_DIR = path.join(os.homedir(), "Documents", "VoiceNovel");

module.exports = async function voiceNovelHandler(command, params) {
  if (command === "export-story") {
    const { filename, content } = params;
    if (!filename || !content) {
      return { error: "Missing filename or content" };
    }

    // Sanitize filename
    const safeName = filename.replace(/[^a-zA-Z0-9\-_.]/g, "_");
    const dir = EXPORT_DIR;

    if (!fs.existsSync(dir)) {
      fs.mkdirSync(dir, { recursive: true });
    }

    const filePath = path.join(dir, safeName);
    fs.writeFileSync(filePath, content, "utf8");

    return { path: filePath };
  }

  return { error: `Unknown command: ${command}` };
};

Python alternative (handler.py):

import os
import re
from pathlib import Path

EXPORT_DIR = Path.home() / "Documents" / "VoiceNovel"

def handle(command, params):
    if command == "export-story":
        filename = params.get("filename", "")
        content = params.get("content", "")
        if not filename or not content:
            return {"error": "Missing filename or content"}

        safe_name = re.sub(r"[^a-zA-Z0-9\-_.]", "_", filename)
        EXPORT_DIR.mkdir(parents=True, exist_ok=True)
        file_path = EXPORT_DIR / safe_name
        file_path.write_text(content, encoding="utf-8")
        return {"path": str(file_path)}

    return {"error": f"Unknown command: {command}"}

Story export location

By default, stories are saved to:

  • macOS / Linux: ~/Documents/VoiceNovel/
  • Windows: %USERPROFILE%\Documents\VoiceNovel\

Filenames follow the pattern: voice-novel-{genre}-{timestamp}.txt


Security notes

  • This skill only writes files to the configured export directory.
  • It does not read arbitrary files, execute shell commands from story content, or make network requests.
  • The content field passed from the R1 is plain story text — it is written verbatim with no code execution.
  • Filenames are sanitized before use: only alphanumerics, hyphens, underscores, and dots are preserved.

04 同仓库更多 Skills

ajohnsonnow
ajohnsonnow/r1-warren

whisper-quiz

WhisperQuiz — voice-answered trivia game for Rabbit R1. Generates questions via the R1's built-in LLM, captures spoken answers via STT, and evaluates correctness with flexible LLM-based matching.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

walk-cast

Walking podcast production skill. Receives raw audio metadata and transcript from the R1, removes long pauses, applies noise reduction and normalization, generates AI chapter titles and episode metadata via LLM, and uploads the final episode to your configured podcast RSS host (Spotify for Podcasters / Anchor, Podbean, Buzzsprout, RSS.com, or any FTP-accessible feed).

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-guide

Environment description and navigation assistant for blind and low-vision users. Analyzes camera frames via a vision LLM, reads visible text, identifies scene categories (people/vehicles/food/hazards/exits), performs 360° scans, retrieves GPS position, and sends emergency SMS alerts — all via audio feedback with zero screen dependency.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-draft

Voice-driven document drafting for the Rabbit R1. Dictate stream-of-consciousness speech; the R1 formats it into Email, Blog Post, Report, Proposal, Meeting Notes, Creative Writing, Code Comments, Cover Letter, or Tweet Thread — then saves the result to a configured folder on your local machine via OpenClaw.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-commit

Hands-free git and CI workflow voice controller for the Rabbit R1. Speak git/CI commands and hear results — commit, push, status, PR management, test runs, and deploy, all voice-driven via OpenClaw.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

vet-vault

VA benefits assistant with DD214 OCR, eligibility analysis, and benefit summary export. Handles camera capture → OCR extraction → eligibility computation, VA deadline fetching, and PDF export for veteran appointments.

★ 0