Devices, not reminders
Mistake-proof your code, your pipeline, and your agents. Audits code for mistakes that are possible, designs APIs where misuse cannot be expressed, installs guardrails, and turns incidents into devices that prevent recurrence.
Skills 11 in the ChatGPT listing
Agent guardrails Stop an AI agent damaging your repo: PreToolUse hooks, permission deny rules, protected paths, verification gates. audit Find footguns in code that already exists: swappable arguments, silent fallbacks, unguarded deletes, signatures that are easy to misuse. authz Multi-tenant isolation, IDOR and row-level security. data Pipelines, warehouses, dbt models and metrics, where failure is silently wrong numbers rather than a crash. design Design APIs, schemas, types and state machines so misuse cannot be expressed. guardrails Pre-commit hooks, CI gates, lint rules, database constraints and branch protection. llm AI features you ship to users: structured output, tool schemas, prompt injection, evals. ops Deploys, schema migrations, rollback and infrastructure. Poka yoke Mistake-proofing for anything: code, config, a schema, a process, a runbook, a form. retro Turn a bug, outage or repeated mistake into a device that makes the whole class impossible. ux Forms, destructive actions and flows users get wrong. 
