10 reviewed prompts.
Creates a page-by-page audit plan to find errors, broken formatting and thin content across a set of articles, with verified issues prioritized. Use it before a content cleanup or relaunch.
Reviews a drafted customer reply for tone, clarity and risky promises, then returns a cleaner version. Use when a support agent pastes a draft and wants it checked before it goes to the customer.
Scores a support conversation against your own quality standards, with evidence for each score, strengths and one improved wording. Use when reviewing tickets for coaching or quality checks, and keep it fair and specific.
Finds the weak spots in a prompt your team reuses, builds a small set of test inputs with pass checks, and proposes a minimal revision. Use when a saved prompt gives inconsistent results.
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.
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.
Designs how to test an AI-powered feature before and after launch: success metrics, a balanced test set, a 1-5 scoring rubric with examples, pass criteria and a failure log. Use when you need to know whether an AI feature is good enough to ship.
Use when generating or reviewing interface designs, mockups or front-end code: steers away from generic template looks toward restrained color, clear type hierarchy, complete states, realistic copy and smooth, accessible motion.
Use when you have just written or changed code and before presenting it: runs a focused second pass for the mistakes generated code commonly contains, fixes what it can, and reports what was fixed and what needs the author's attention.
Standing approach for reviewing code: rank findings by impact, explain why, and suggest a fix. Use when asked to review code, a change or a pull request.
