Michael H mphinance

strangle-timer - Claude Desktop execution prompt

Copy everything in the box below into a Claude Desktop chat. It assumes you have a brokerage MCP connected in Claude Desktop (IBKR, Alpaca, Tradier, Tastytrade, ...). Replace the TICKER / strikes / contracts up top. It will analyze first, pick the FIRST side off the live 5-minute trend, and then flip you side-to-side as the trend reverses, reading the ticket back before every order. It never trades without your explicit "go". Despite the skill name this is NOT a held strangle: you hold ONE side at a time and rotate, you never sit long both wings.

Autonomous Claude coding loop for GitHub

A nightly GitHub Actions loop that reads a SPEC.md, plans its own backlog, and ships one feature per run as a pull request. Built on the official anthropics/claude-code-action.

Two roles, auto-selected: initializer (turns your spec into an ordered feature_list.json) and coder (builds the next pending feature, runs tests first, opens a PR). One long-lived branch, one PR, so you don't wake up to a thousand branches.

Substack Research Dossier — Intake Half Of The Creator Stack

A small public gist for Substack creators who want to research other Substacks systematically instead of doom-scrolling them.

Two files:

pull_substack_data.py — fetches the public archive + notes for any Substack handle. No auth required, just pip install requests.
research_substack_prompt.md — a Claude Code-style prompt that takes the JSON the script produces and writes a dossier in a clean reusable format: profile, last N posts, last N notes, followed-hyperlinks, lineage analysis, takeaways.

Why this exists

substack-toolkit

Full read-and-write Substack toolkit that works around the private-API gotchas Substack will not document for you.

substack-toolkit is a Claude Skill and a small standalone Python library for working with Substack from the outside. Post drafts from Markdown or a Python builder. Read your reader feed, the published archive of any publication, individual posts, profiles, and other users' Notes. Publish Substack Notes. Like and comment with explicit, side-effect-aware methods. Single file, two deps, MIT.

What it does

Write:

	#!/usr/bin/env python3
	"""
	fetch_my_afterhour_posts.py — grab your ENTIRE AfterHour post history in one go.

	No login. No API key. No app. Just your username.

	Turns out AfterHour's post feed is powered by a public API that anyone can call —
	you don't need to be logged in, and you don't need this script to be fancy. It just
	asks AfterHour for your posts, 100 at a time (that's the most it'll hand over in one
	request), and keeps asking for "the next 100" until it has everything. Then it saves

	#!/usr/bin/env python3
	"""
	🚀 Multi-Bagger DNA Screener — The "Find It Before The Analysts" Scanner

	Companion piece to Forefront Alpha's "How To Find a Multi-Bagger" series.
	He sells the framework: be EARLY, before the headlines, before the analysts,
	before the crowd. His named winners — IREN at $7, APLD at $6 — were all small,
	under-covered, fast-growing names BEFORE Wall Street showed up.

	This screener reverse-engineers that DNA into something you can actually run on

	"""
	pulse.py — Mine engagement signals from your Substack network.

	For each profile you follow:
	1. Pull recent posts (within WINDOW_DAYS)
	2. Compute the author's typical engagement baseline (median over the window)
	3. Flag posts that significantly outperformed their author's baseline
	4. Tag outliers by topic via Gemini
	5. Output a digest: which topics are over-performing in your network right now

	# ══════════════════════════════════════════════════════════════════════════════
	# MASTER MAP: underlying → list of 2x bull ETFs and 2x bear ETFs
	#
	# Sources:
	# [D] = Direxion
	# [G] = GraniteShares
	# [R] = REX Shares / T-REX / Tuttle Capital
	# [Df] = Defiance ETFs
	#
	# Only includes SINGLE-STOCK 2x ETFs, not index/sector/commodity products

	// This work is licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
	// https://creativecommons.org/licenses/by-nc-sa/4.0/
	// © BigBeluga

	//@version=6
	// 👨‍🏫 MPH NOTE: //@version=6 tells TradingView's servers which version of the Pine Script language to use. Different versions have different features and rules, so this line is essential for the script to run correctly.

	// This script is an implementation of a two-pole filter used as an oscillator.
	// Unlike a simple moving average, a two-pole filter provides a very smooth output
	// with minimal lag, which makes it ideal for creating responsive oscillators.