Code review, debugging, architecture, testing and docs. 88 reviewed prompts for engineering.
Groups security scanner alerts and dependency warnings, finds shared root causes, and ranks fixes by severity and exposure. Use it when a long alert list needs a clear remediation order.
Compares virtualization platform options against your workloads, team skills and budget, and ends with a recommendation and a pilot plan. Use it before renewing or replacing a virtualization stack.
Turns a piece of code into a list of test cases plus runnable test code, with explanations a junior developer can learn from. Use it when you add or change a function and want solid coverage.
Designs a system from requirements to failure modes: clarifying questions, capacity estimates, components, data model and explicit trade-offs. Use it for real architecture decisions or to practise design interviews.
Checks a release against a readiness list, names the biggest risks, and plans staged rollout with stop thresholds and ordered rollback steps. Use before a production launch.
Turns a research paper's core method into a minimal, commented implementation, with every detail traced to the paper and every gap flagged as an assumption. Use it when reproducing or prototyping a published technique.
Compares an API before and after, classifies each change as breaking, safe or unclear, and drafts a consumer migration checklist and changelog note. Use it before releasing an API update.
Designs a clear, validated tool (function) definition that AI assistants can call reliably: naming, parameters, field order, output and error shapes, safety rules and example calls. Use it when connecting an assistant to your own APIs.
Rewrites a rough coding request into a structured brief with goal, context, constraints, out-of-scope items and a testable done condition, ready to hand to an AI coding assistant or a developer.
Diagnoses what makes working code hard to change and lays out small, low-risk refactoring steps with a safety net of tests and a before/after example. Use before cleaning up a messy module.
Reviews smart contract code for security flaws, risky admin powers and wasteful gas use, with exploit scenarios, fixes and tests to add. Use it before an external audit or any deployment that holds funds.
Critiques a product requirements draft or one-pager, ranking its weakest points, listing missing evidence and suggesting the questions to answer before building. Use before committing engineering time.
