Christopher Carroll Smith chriscarrollsmith

name	editing-video
description	Use for turning raw video footage into more polished and publishable content.

Editing video

Pipeline order (steps in brackets are optional and cost money):

name	analyzing-sec-filings
description	Retrieves and parses SEC EDGAR filings (10-K, 10-Q, 8-K, DEF 14A) into markdown or structured financial data using the edgartools Python library. Use when working with SEC filings, EDGAR data, XBRL financials, or company fundamental analysis.

Analyzing SEC Filings

Use edgartools for all SEC filing work. Do not use curl, manual HTML parsing, or filing.full_text_submission().

Setup

Embedding your downloaded Twitter archive data for semantic search and RAG with `llm`

Getting your tweets

Twitter allows you to download your archive of tweets. You can do this by going to your account settings and requesting your archive. Once you receive the email with the download link, you can download the zip file.

Exploring the data

Top-level keys of twitter_archive.json (via jq 'keys' twitter_archive.json):

Projects

Runner-Up: Doctor of Credit

Creator: Evan Mullen
Description: Extract structured data about bank deposit bonuses from the Doctor of Credit website.

Prerequisites

Google Chrome CLI entrypoint

Let's hack on `llm`!

If you have uv installed (and you should!), you can install llm globally in a uv-managed tool environment with:

uv tool install llm

If you want to use models other than OpenAI models, you'll need some extensions:

	#!/usr/bin/env python3
	"""Build an interactive workflow graph from GitHub issues across one or more repos.

	Fetches open issues, groups them by label hierarchy, draws blocking dependencies,
	and renders either a Graphviz DOT file or a Cytoscape preset page for browsing.

	Why: The graph helps teams coordinate—see what blocks what, pick work that
	unblocks others, and focus on different areas of the codebase in parallel without
	overlap.

	"""
	Run repo commands in Modal with streamed logs and optional synthetic timeout.

	Usage:
	uv run modal run runner.py --cmd '<bash command>'

	Examples:
	# Run the main export command remotely
	uv run modal run runner.py --cmd \
	'uv run -m src.compute_heavy_entrypoint'

	import os
	import sys
	from typing import Any, Dict, List

	from openai import OpenAI


	def ensure_api_key() -> None:
	if not os.getenv("OPENAI_API_KEY"):
	print("ERROR: Please set OPENAI_API_KEY in your environment.")

	#!/usr/bin/env bun
	// @bun-dependencies: puppeteer@latest puppeteer-extra@latest puppeteer-extra-plugin-stealth@latest

	import puppeteer from 'puppeteer';

	async function scrapeXTweet(url, metadata) {
	// Launch browser with stealth options
	const browser = await puppeteer.launch({
	headless: true, // or 'new' for new headless mode
	executablePath: '/usr/bin/google-chrome',

	#!/bin/bash

	# create-nl-tool.sh - Programmatically create natural language interfaces
	# for CLI tools
	# Usage: ./create-nl-tool.sh <tool-name>
	# Example: ./create-nl-tool.sh repomix

	set -e

	if [ $# -eq 0 ]; then