roelven

Voice Profile Extraction Prompt

Instructions for the LLM

You are a voice analyst and writing coach. Your task is to analyze a collection of texts written by a single author and extract a comprehensive, generalizable voice profile that can be used to instruct other LLMs to write in that author's authentic voice.

---

Input Requirements

roelven

Claude Code Blood Lab PDF Parser

Parse blood lab PDFs into structured JSON. You can use this as a command in Claude Code, or run the python script if Claude Code is not installed. The python script will call the Anthropic API directly.

Setup

# Install dependencies
pip install anthropic

roelven

#!/usr/bin/env python3
"""
Download all images from markdown files and update references for Hugo migration.
"""

import os
import re
import sys
from pathlib import Path
from urllib.parse import urlparse, unquote

roelven

#!/usr/bin/env bash
# Simple CLI for OpenAI Sora 2 video generation.
# Requirements: bash, curl, jq
# Usage examples at bottom.

set -euo pipefail

# Load environment variables from .env file if it exists
if [[ -f "$(dirname "$0")/.env" ]]; then
  set -a

roelven

Claude Code Obsidian Summary Command

A UserPromptSubmit hook for Claude Code that generates concise project summaries in your Obsidian vault when you type obsidian-summary.

What It Does

When you type obsidian-summary during a Claude Code session, Claude will:

• Analyze the session to extract project details
• Determine the project/tool name
• Summarize what was built in bullet points

roelven

FROM node:18-bullseye

# Install tooling
RUN apt-get update && \
    DEBIAN_FRONTEND=noninteractive apt-get install -y \
      git \
      ca-certificates \
      bash && \
    rm -rf /var/lib/apt/lists/*

roelven

yt-migrate

A pragmatic, script-based migration tool to move personal YouTube data between two Google accounts using the official YouTube Data API v3.

This exists because Google does not provide a first-class way to migrate user-level YouTube data (subscriptions, playlists, likes) between accounts, especially when Brand Accounts are not an option.

The script is designed to be:

• Explicit about what is and is not possible
• Safe to re-run (resume-friendly)
• API- and ToS-compliant (no scraping)

roelven

Receive a Signal notification when your scan is ready

Powered by Paperlessg-ngx

Great for Paperless users that have printer that scan to a network folder. Quickly scanning a document and getting the link to its PDF is now super fast and low effort!

Paperless

Mount the local /scripts directory as a volume in your docker-compose.yml for the webserver container:

roelven

Set up your Samsung Frame TV with correct status tracking in Home Assistant

1. Set up your TV + connect it to your LAN
2. Install the HA Samsung Smartthings integration
   • Make sure to connect it to your Samsung account, so that the integration will automatically provide the auth token in the next step.
   • Read more here
3. Install ha-samsungtv-smart using HACS
4. Configure the integration, make sure to turn your TV on as you'll need to approve this on your Frame.
5. Add the following snippet to your HA configuration.yaml:

roelven

#!/usr/bin/env bash
# Simple CLI for OpenAI Sora 2 video generation.
# Requirements: bash, curl, jq
# Usage examples at bottom.

set -euo pipefail

API_BASE="${OPENAI_API_BASE:-https://api.openai.com}"
API_KEY="YOUR_API_KEY"
MODEL="${MODEL:-sora-2}"          # or "sora-2-pro"