Writing / Kit
The kit. What I actually use, ready to copy.
Templates, checklists and prompts from the way I scope, build and ship products with AI agent teams. Neutral versions of the real thing: copy them, adapt them, break them. Each one links to the article that explains why it looks the way it does, and keeps a changelog of what changed and what incident changed it.
CLAUDE.md template
The seven sections every agent session inherits, in the order an agent reads them, with nine neutral hard rules to start from.
v1.0 / CLAUDE.mdTemplate / BuildTicket template for agents
Frontmatter a script can validate, plus the three fields that stop agents inventing requirements. Blank and filled versions.
v1.0 / ticket.mdFormat / BuildEscalation and decision format
How an agent stops at a real decision: an id, three options, a recommendation. You answer with a letter.
v1.0 / escalation.mdTemplate / BuildNotion board for an agent team
Tasks, decisions and meetings as Notion databases, plus the card the orchestrator drafts and a person owns.
v1.0 / notion-board.mdChecklist / BuildRelease gate checklist
The merge gate and the release gate, as checkboxes. Written for the day a skipped check reports green.
v1.0 / release-gate.mdTemplate / LeadMVP scope one pager
Thesis, one workflow, invariants and what is not built. The page that stops a fast build from sprawling.
v1.0 / mvp-scope.mdChecklist / OptimizeCheckout audit checklist
Rebuild the funnel per user, find the re-entry gap, instrument it, then test with a written hypothesis. SQL included.
v1.0 / checkout-audit.mdFree to use, no sign up. Every block has a copy button and a download. If something here stops working for you, tell me and it goes in the changelog.