AI Blocks › Build and ship software
Find where your launch will break, and plan how it recovers
Describe your launch or release. Get the weak joints, what wins when things pile up, and a recovery plan.
Check a launch for weak joints and plan its recovery is a free AI workflow for the job "Build and ship software". It guides your AI through several skills in order, passing each step's output to the next.
Free · No account · Made by AI Blocks · Level: advanced · Thinking: high
What it does
Most launches fail where two parts meet, not inside one part. Two teams each did their job, but the data, the timing or the order did not match at the join. Then an alarm goes off that nobody can read, and people scramble. This workflow checks the joins first. It lists the parts, marks what passes between them, gives every job a priority and plans what the system keeps and drops under load. Then it takes those findings and designs the alarms, the go or no-go decision and a safe point to restart from. The order comes from Margaret Hamilton's paper "What the Errors Tell Us", which draws on her work on software for the Apollo missions.
You give it
- What is launching, the date and what success looks like
- The parts, teams and suppliers involved, as far as you know them
- Change records, plans or earlier problems (optional)
- The mistakes people on your team say can't happen (optional)
You get
- A list of parts and every join between them, with what crosses each
- A readiness score out of 100 with how it was worked out
- A priority plan for when the system is overloaded, and what it must never drop
- A run-through plan for the whole launch
- Alarm text for each mistake, the go or no-go decision it asks for and a safe restart point
Use it when
- A release or migration is coming and you want to know where it could fail before it does.
- Your last launch went wrong at a handoff between teams or tools, and you want to stop that happening again.
- You are adding a new system to a busy one and need to know what happens when everything runs at once.
Steps
- Launch integration checklist: Describe a launch, migration or release. Get a readiness score, the joins between parts and a run-through plan.
- Error and recovery message writer: Describe a system and its operators. Get what the alarm says, what the person decides and how it recovers.
How to use it
- Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
- Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
- Describe the launch and list the parts you know about. It works step by step and saves each result.
- Do the run-through with a person in the loop before the real launch, and fix what it finds.