Mike D turlockmike

Optimization Playbook

Shared techniques for making Claude Code sessions and skills more effective, efficient, and adaptive. Consolidated from skills-optimizer, session-review, prompt-discovery, and extend-skill-builder.

1. The Viability Model

A system is viable when it sustains three properties simultaneously:

Bootstrap: Set Up Your AI Workspace

You are setting up a new AI workspace for a user at Extend. This file is your instruction set. Follow it step by step, interacting with the user as you go. Be conversational, not robotic.

Validate after every phase. Do not move to the next phase until the current one passes. If something fails, help the user fix it before continuing.

Success Criteria

X Research

Research topics on X (twitter) using a dedicated headed browser with saved auth cookies. Separate window from main Chrome.

When to use

Real-time AI/LLM discourse, announcements, and opinions from thought leaders
Breaking news or emerging topics not yet covered by blogs or docs
Checking what specific people are saying about a topic
Gathering community sentiment or reactions to launches, papers, or tools

name	agent-discovery
description	Discover AI agents and Claude Code skills across the helloextend GitHub org. Scans active repos via code search, analyzes with parallel haiku subagents, categorizes by purpose, outputs a structured catalog.

Agent Discovery

Discover all AI agents and Claude Code skills across the helloextend org by scanning active repositories, analyzing code with parallel subagents, and producing a categorized catalog.

Phase 1: Reconnaissance

Claude Code Usage Monitor

Query your Claude Code rate limit status from the terminal. Returns NDJSON with utilization percentages and reset countdowns for each rate window.

Prerequisites

Claude Code installed and authenticated (claude auth)
macOS (reads OAuth token from Keychain via security CLI)
python3 and curl on PATH

Extend CLI Agent Migration Plan - Detailed Command Mapping

🎯 Goal

Migrate all Extend CLI commands to agent-based interfaces. Complete command-by-command breakdown below.

📊 Coverage Summary

Original Commands: ~95 total
Removed/Deprecated: 31 commands
Migrating to Agents: 64 commands
Agent Coverage: 100% ✅

Starting Phase: Setup and Task Acquisition

Goal: To prepare your development environment, retrieve all necessary task details, and create a dedicated feature branch, ensuring you are ready to begin the Researching Phase.

Phase Starts: When a new Jira ticket is assigned, a new task is identified, or when a user suggests a large feature to build. Phase Ends: When you have a clean, up-to-date feature branch with all necessary ticket information loaded, and the ticket (if applicable) is moved to "In Progress" and assigned to you.

Expected Artifacts:

Local repository on the correct feature branch.
Feature branch correctly named and ideally pushed to the remote repository.

	---
	name: product-brief
	description: Create executive product briefs through collaborative discovery,
	artifact analysis, and web research. Use when asked to create, update, or
	review a product brief.
	---

	# Product Brief

	Create a 1-2 page executive product brief. You are a product-focused BA

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Eevee's Berry Farm 3D</title>
	<script src="https://cdnjs.cloudflare.com/ajax/libs/three.js/r128/three.min.js"></script>
	<style>
	@import url('https://fonts.googleapis.com/css2?family=Fredoka:wght@400;500;600;700&family=Patrick+Hand&display=swap');
	:root{--eevee:#c4956a;--card:rgba(255,255,255,0.92);--text:#3a2f28;--text-soft:#7a6e64;--border:#d0c8b8;--gold:#d4a020;--shadow:rgba(40,30,10,0.12);}

	#!/bin/bash
	set -e

	# EC Sandbox Setup Script
	# Downloaded at runtime by tiny UserData bootstrap
	#
	# Usage:
	# ./sandbox-setup.sh [options]
	#
	# Options: