Copy, remix, and improve AI prompts that solve real tasks

Prompt directory

Open a public prompt page to read and copy its full text.

• Pre-Mortem Risk Scan

  Gary Klein's pre-mortem as a prompt: imagine the launch already failed, work backward through 8-10 failure modes, mitigate the cheap-now ones.

• Decision Doc (RFC) Writer

  Amazon/Stripe-style decision doc with genuinely comparable options, a 'do nothing' baseline, and one-way vs two-way door reversibility analysis.

• Pre-Commit Risk Scanner

  Reviews uncommitted changes for security risks, performance issues, and breaking changes before commit. Trending as AI-powered code review gate on GitHub discussions.

• Archetype-Driven UI Prompt

  Forces selection of specific design archetype, palette, and typography before generating UI. Prevents generic output by requiring self-audit and iteration. Popular in design communities.

• Vercel v0 Competitor Killer

  Generates production-ready React components with Tailwind and Shadcn that rival v0.dev output. Going viral as open-source alternative to paid tools.

• Hermetic Unit Test Generator

  Creates AAA-pattern unit tests with zero ambient mocks, ensuring isolated, reproducible tests. Trending in Cursor community for production-ready testing workflows.

• Studio Product Shot

  E-commerce-grade product photography prompts: three-point lighting, macro lens specs, true-to-life color — with a lifestyle-context variant.

• Refactor Without Breaking

  Contract-first refactoring: baseline the observable behavior, flag risky spots, write missing tests first — so 'improved' never means 'silently changed'.

• DSPy Program Compiler

  Converts natural language task descriptions into executable DSPy programs with optimized prompts and metrics. Trending in AI engineering communities after DSPy 2.5 release.

• Context-Specialized Code Review

  Runs targeted code reviews across security, performance, accessibility, and quality dimensions using OWASP, WCAG, and CWE standards. Trending in developer communities.

• Background Agent Brief

  Gives AI complete context from issue trackers and existing code to implement features autonomously. Trending for async development workflows.

• Negative Prompt Cleanup

  Generates the matching artifact-exclusion list for any image prompt, correctly formatted for Midjourney --no, Stable Diffusion, or DALL-E.

• Find My Lost Item in Photo

  Practical visual search prompt that went viral after a user found their shoe among 1,000 pairs. Template for locating specific items in crowded photos.

• Knowledge Graph Discussion Extractor

  Extracts entities, relationships, tensions, and community insights from discussion threads to map who talks to whom and identify unresolved topics.

• Anthropic Prompt Caching Optimizer

  Restructures your prompts to maximize Claude's prompt caching, reducing costs by up to 90% for repetitive tasks. Viral after Anthropic's pricing update.

• Resume ATS Optimizer

  Rewrites resumes to pass applicant tracking systems with keyword density, achievement quantification, and format compliance. Trending on PromptPrepare. — spotted on PromptPrepare trending prompts list

• Kill the AI Slop

  Forces a real design spec — palette, fonts, layout risk, micro-interactions — before any code, so your UI stops looking like every other AI build.

• Lovable/Bolt Build Spec Generator

  Converts rough website ideas into complete art-directed build prompts for Lovable, Bolt, v0, or Cursor with exact typefaces, colors, layout, motion, and asset URLs.

• Dark Mode Retrofit

  Adds a proper dark mode — parallel token set, adjusted shadows, WCAG-checked accents, prefers-color-scheme — instead of naively inverted colors.

• WCAG Accessibility Audit

  Audits a component against WCAG 2.1 AA — contrast, keyboard nav, ARIA, focus states, heading order — prioritized by what blocks screen-reader users.

• Headline Sprint (10 Angles)

  10 hero headlines across 5 deliberate angles — benefit, pain, proof, plain, bold — then the model ranks which 2 to A/B test first.

• Mega-Prompt Structure Template

  Universal format for combining system rules, project context, and tasks that works across Cursor, Claude, ChatGPT. Viral for consistent AI behavior.

• Steelman Both Sides

  Debiases the model before a big decision: strongest case for each side, the crux underneath, then a clearly-labeled opinion with confidence level.

• Adversarial Bug Hunter

  Acts as hostile QA to find breaking edge cases, then writes tests to catch them. Going viral for finding production bugs before deployment.