Let the business define the goals for the quarter “release product X”, “increase Y” and let the teams figure out how to achieve that but not 6 months in advance.
Plan, ideate, implement should take no longer than 2 weeks.
Allows teams to learn and pivot when appropriate.
We should be minimising the time between ideation and having something in front of the customer.
Planning in quarterly or halves contradicts this premise.
What matters is customer outcomes. Too much energy spent on how.
Sprint Planning, Retros, Cycle Time, velocity, number of weeks per sprints etc.
All bollocks.
The number of hours I’ve spent in quarterly/ halve planning for the plan to be derailed 2 weeks in is staggering.
It’s all busy work.
I can’t imagine using AI to write code without TDD.
Tests aren’t just safety nets anymore. They are the steering wheel on the race car.
Happy Pokemon day. 2026 Christmas Day will be my personal 30th Pokemon day.
I remember receiving the game from my grandad and having no idea what it was and spending weeks trying to defeat Brock because I only had Charmander on my team 😂
I caught Mewtwo with a standard Pokeball as a kid.
That kind of dedication has followed me into adulthood and everything I do 😏
pick 👏 the 👏 right 👏 tool 👏 for 👏 the 👏 right 👏 job.
Say it together now.
The human touch will be the thing that drives downloads on the AppStore.
I’ve seen a bunch of competitor apps appear recently and they all look the same.
What makes your app stand out amongst the vibe coded slop will be the difference between success and failure.
Hello Opus 4.6
I’ve been using AI for things I consider myself an expert at and using time saved to level up other skills using my brain like SEO, Graphic design and marketing.
0 to 1 is like stepping outside and running a 10k marathon after spending 10 years as a coach potato.
1 to 2 is like you’ve been training for a 10k marathon for 12 months, step outside and break your ankle.
When your TV remote has too many buttons, you can’t change the channel.
There’s a lesson in that.
Goodbye loyal customer 🫡
Agent Skill directories that let you install arbitrary skills and scripts, That's an attack vector waiting to be exploited surely?
MRR is a funny metric. I’ve been measuring my apps success in bills paid.
My energy bill is now paid by my apps every month 😆
Next goal: the mortgage.
I created a new Claude Code skill this evening for iOS App Store market research.
Previously this was a custom MCP server that I had to spin up locally on my machine.
SKILL.md files don't just have to be coding conventions and how-tos. They can allow your agents to call third parties.
Claude Long Term Memory
spec-kit, bmad, task-master, beads, beans.
It doesn't matter which one you pick. They all do the same thing
Just use one and get familiar with it - don't get stuck in that loop of switching tools every week because someone on Bluesky recommended it.
AI has turned my iPhone into a dev workstation.
A user reported a bug for an app I’ve built. I shared a screenshot + high-level architecture via Codex on iOS.
It found the issue, fixed it, and deployed - entirely from my phone.
12 months ago I was just doomscrolling and reading memes 😂
After watching a video Ali Abdaal created on the “GPS Method” I created a Claude skill to help me set my 2026 goals.
Works a treat 👌 and here is a top tip; you can zip skills up and upload them to Claude web.
github.com/mintuz/claud...
LLMs, autonomous agents, and “vibe coding” reward system thinkers.
Models think locally. Slop happens when humans do too. Your value is the bigger picture and to guide them along the path.
My 2026 Indie dev goals
- Reach £1000 MRR
- Release a new unannounced app I’ve been building for the last month.
- Start posting on TikTok behind the scenes of my indie app development process.
Have we not always been spec-driven development 🤔
You’re welcome.
My favourite 2025 app is “How We Feel” fantastic app for mental health, beautifully designed and completely free. No subscription required. A rarity in 2025
howwefeel.org/get
Web dev in 2015 was more enjoyable and easier than web dev in 2025.
This my 1000th post
Fun fact. codex has experimental skill support github.com/openai/codex...
Give Claude Code ago and research / install different skills/agents/workflows they really are a game changer.
The best way to learn though is experiment and “automate” the donkey work in your processes.
Here’s my Claude code plugins to get started github.com/mintuz/claud...
