svngoku

YouTube Transcript SKILL

Use this skill to fetch the transcript of a YouTube video, with or without timestamps.

Use this skill with Claude (by extracting it to .claude/skills/) or with any other agent using Skillz.

Note: This skill is unlikely to run successfully on the Claude web app, since access to YouTube is blocked. Use it with Claude Code or other local agents.

Claude Code Hooks for working with `uv`

by Glenn Matlin / glennmatlin on all socials

Installation

Download and copy all files in this gist to ~/.claude/
Move the .py files to ~/.claude/hooks
Restart Claude Code.

Architecture

Website: Expo Router website with Tailwind.
Native app: Expo Router app with CNG.
Backend: Expo API routes WinterTC-compliant. Routes are in src/app/api/ directory. API routes use +api.ts suffix (chat+api.ts).
Secrets: Use .env files and API routes for secret management. Never use EXPO_PUBLIC_ prefix for sensitive data.

Code Style

Use TypeScript whenever possible.

Based on this blogpost.

Install with Homebrew:

$ brew install postgresql@14

(The version number 14 needs to be explicitly stated. The @ mark designates a version number is specified. If you need an older version of postgres, use postgresql@13, for example.)

	# /// script
	# requires-python = ">=3.11,<3.12"
	# dependencies = [
	# "distilabel[hf-transformers, hf-inference-endpoints]",
	# ]
	# ///
	from distilabel.models import InferenceEndpointsLLM
	from distilabel.pipeline import InstructionResponsePipeline

	repo_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"

	# /// script
	# requires-python = ">=3.11,<3.12"
	# dependencies = [
	# "duckdb", sentence-transformers, huggingface_hub
	# ]
	# ///
	from sentence_transformers import SentenceTransformer
	import duckdb
	from huggingface_hub import get_token

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

	import os

	from llama_parse import LlamaParse # pip install llama-parse
	from llama_index.core import SimpleDirectoryReader # pip install llama-index
	source_directory = r'\data'
	target_directory = r'\tables'

	parser = LlamaParse(
	api_key="...", # can also be set in your env as LLAMA_CLOUD_API_KEY
	result_type="markdown", # "markdown" and "text" are available

	# Based on younesbelkada/finetune_llama_v2.py
	# Install the following libraries:
	# pip install accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7 scipy

	from dataclasses import dataclass, field
	from typing import Optional

	import torch
	from datasets import load_dataset
	from transformers import (

	// if code snippet is inside input or textarea tags
	function copy() {
	var codeSnippet = document.querySelector("#code-snippet");
	codeSnippet.select();
	document.execCommand("copy");
	}
	document.querySelector("#copy").addEventListener("click", copy);

	// if code snippet is inside pre or code tags
	function copy() {