Prompt catalog
Browse reusable AI prompts by topic, then open any prompt to copy and adapt it for your workflow.
375 prompts · page 30 of 42
Paste a draft agent skill or reusable prompt along with your project context, the target task, available tools, and known risks, and get back a structured audit covering purpose, required inputs, output format, safety boundaries, and failure modes. The review also flags missing checks and repeatability gaps, then returns an improved version ready to test — useful before wiring a skill into an autonomous coding agent or handing it to a team.
Submit a proposal along with your project context, stack, constraints, and team's skill level to get a skeptical second opinion before committing engineering weeks to it. The review separates what's genuinely strong from what's over-engineered, surfaces hidden coupling that will resurface later as maintenance cost, and ends with a clear verdict plus a minimal implementation path instead of just a list of concerns.
Paste a diff along with your public API surface, schema context, and configuration context to get a structured audit of breaking changes before you ship a release. It checks renamed methods, changed signatures, request or response field changes, unmigrated schema changes, environment variable renames, and altered defaults, then returns a severity-ranked table with affected users, migration paths, and a deprecation strategy where one is needed.
Feed in a target keyword, the top 10 current SERP results (titles, descriptions, URLs, formats), and optional context on your brand or audience, and it reverse-engineers exactly what Google is rewarding for that query right now. Returns primary and secondary search intent with justification, the page elements and content format required to compete, opportunities to win SERP features like featured snippets or PAA boxes, and E-E-A-T differentiators — especially valuable on YMYL topics.
Maps out where CTAs should sit across a landing page's user journey based on just a conversion goal — sign-ups, purchases, demo requests — and the page's topic, replacing scattered guesswork with a placement rationale tied to how a visitor actually moves through the page. A follow-up step then suggests the text and design elements that make each placed CTA more effective, and it pairs well with a CTA copy or form-friction prompt once positions are locked in.
Builds a full year of content planning from an industry, target audience, business goals, and known seasonal trends, mapping each of the 12 months to a theme, three content pillars, five key topics, seasonal tie-ins, relevant industry events, and recommended content types. Meant to be revisited quarterly, swapping in real performance data as each quarter closes so the calendar stays grounded instead of becoming a one-time planning exercise.
Feed in an aging article's full body text and, optionally, its live URL, and a model with web-browsing verifies every time-sensitive claim against current sources while checking today's SERP intent and format against what the page currently delivers. It returns one clear decision — update, new page, merge, or no action — with a before/after list of outdated facts and citations, a 0-10 cannibalization risk score with subscores, an implementation plan, and top risks, so it requires live browsing access to work as designed.
Walks through building an XML sitemap that reflects real page hierarchy and priority rather than a flat list of URLs. - Inputs: business/site description, website link, and list of pages - Explains how hierarchy and priority should be structured - Follow-up generates an embeddable XML sitemap for WordPress - For large sites, paste pages in batches by category instead of all at once
Generates a structured batch of email subject lines for testing, grouped by psychological angle rather than random variation. - Inputs: email topic, audience, main message, desired action, brand voice, and words to avoid - Produces: 20 subject lines grouped by angle, preview text for the 5 strongest, and a testing hypothesis per group - Flags: spam-risk wording and recommends one A/B test pair to run first - Built for email marketers who want a defensible reason behind every subject line, not just volume