Prompt directory
A prompt library for work, code, research, photos, and more. Every prompt shows what you need to provide, what it produces, and which AI models it was tested with.
Need reusable instructions with versions and install commands? Browse Claude Code skills, Cursor skills, or the full agent skills registry—and see how an AI package manager differs from copy-paste.
Browse by model: Gemini prompts, Claude prompts, and Nano Banana photo prompts. Or start with a use case: LinkedIn headshot prompts or product photography prompts.
Browse by series
Explore
10 prompts
Won't agree just to be nice. Every big claim needs evidence. Why it matters: agreement without proof feels good and changes nothing.
Build a promotion packet narrative with evidence and leveled impact. Why it matters: a ready draft saves you from a blank page.
Critique an essay outline for thesis, evidence, and structure (no ghostwriting). Why it matters: nice answers don't fix the real problem.
Rewrite LinkedIn headline, About, and experience bullets for target roles using plain voice, searchable keywords, and only evidence you. Why it matters: a ready draft saves you from a blank page.
Detects missing audience insight, unclear positioning, weak evidence, channel conflicts, and measurement gaps. Why it matters: clear words get more clicks than fluff.
Explains a paper’s research design, evidence quality, limitations, and what its results do not establish. Why it matters: simple explanations stick better.
Organizes projects, metrics, feedback, scope, and lessons into a concise evidence-based self-review. Why it matters: nice answers don't fix the real problem.
Converts a meeting or message thread into the decision, evidence, alternatives, disagreements, owners, and follow-ups. Why it matters: a ready draft saves you from a blank page.
Creates a playful, evidence-based roast with adjustable intensity and clear personal boundaries. Why it matters: a fun format makes the idea stick.
Groups customer feedback into themes, contradictions, opportunities, and research gaps without inventing evidence. Why it matters: nice answers don't fix the real problem.
