Mock modepayments, email are simulated. No real payments, emails or production data.
Library
Everything is searchable and filterable. Free items open immediately, course items unlock with the course, and AI Club releases unlock with a membership.
A focused review of the things that actually leak: keys, access rules, inputs and the endpoints you forgot were public.
The commands you actually type, what each one is for, and how to get back when something goes wrong.
Twelve reusable prompts built on role, goal, constraints and format — with the variable you are meant to change marked in each.
Architecture, prompts, approval flow and cost model for an enquiry-response agent.
The counter-prompt to "done!" — makes the agent prove its own work against reality.
Gets a working local project onto a real URL, with the environment set up properly and the deploy actually checked.
The Connect Anything prompt: picks the integration method, handles secrets correctly, proves the connection with one real call.
Read-only by default, with permissions designed in.
Turns a stack trace into a diagnosis, a fix and a check that the fix holds.
The general-purpose build prompt: hand an agent an outcome and get a working, tested feature back.
Pressure-tests an agent design before you build it.
The skeleton these projects start from, and the decisions behind it.
A starter architecture for documentation-grounded support with clean escalation.
A process that produces Arabic that reads natively instead of translated.
The checks that keep payment and event webhooks from double-granting or being spoofed.
Turns a vague service into a named, scoped, priced offer.
Five levers that reliably cut spend without hurting output quality.
What to check before and immediately after a deploy.
Turns what a prospect actually said into responses you can use.
Where to put a human in the loop, and how to make the gate fast enough to survive.
A focused check on the things that actually get exploited.
Analyses a competitor’s positioning using only what they publish.
Retries, timeouts, validation and error handling from the start.
Explains a topic at your level, then tests whether you understood it.
67 resources