Code review, debugging, architecture, testing and docs. 100 reviewed prompts for engineering.
Designs a practical testing strategy for an application: risk map, test layers with targets, dependency handling, the first ten tests to write, CI gates and a four-week rollout. Use it when a suite is missing, slow or untrusted.
Walks the path a new developer takes from finding your product to a first working result, finds the friction at each step, and prioritizes fixes to the product and the docs. Use before a launch or when developer sign-ups are not turning into usage.
Builds a practical test plan for an AI assistant or automated workflow: realistic test cases, pass/fail rules, metrics and review triggers. Use before rolling a workflow out to a team.
Turns commit messages or change lists into user-facing release notes, a short engineering note, and a rollout and risk summary. Use when preparing a release announcement.
Reviews a web page or component's code for accessibility, loading speed, layout stability, missing states and mobile behavior, then gives prioritized fixes with code. Use before shipping a page or when users report it is slow or hard to use.
Reads a code diff and its commit message and produces a plain summary of what changed, why it matters, and what a reviewer should check. Use before opening a pull request or when reviewing someone else's change.
Produces a grounded plan for a code change: affected files, two or three options with trade-offs, a recommendation, ordered steps, tests and risks. Use it before anyone starts writing code.
Plans how to run an AI model on your own hardware: memory estimate, model size and compression level, runtime setup, expected speed, risks and a benchmark checklist. Use it when privacy or offline use rules out cloud services.
Explains how a codebase works in plain language for product managers, designers or new team members, with a guided tour, glossary and quiz questions. Use it for onboarding or before discussing changes with developers.
Reviews a list of dependencies and produces a prioritized plan to replace outdated or risky ones, with risks, testing and rollback. Use when planning dependency upgrades for a service.
Designs a pipeline strategy for building, testing and deploying multiple independent services from a single repository, with rollout and rollback rules. Use when starting or untangling a delivery pipeline.
Designs an internal cloud platform for your workloads: architecture, infrastructure-as-code module layout, reliability targets, cost model, security posture and runbook outline. Use it when setting up or reworking shared infrastructure.
