Research Paper Metadata JSON
Extract a research paper's title, authors, abstract, and keywords into JSON.
AI prompts.
316 prompts · 221–240
Extract a research paper's title, authors, abstract, and keywords into JSON.
Extract citations, key quotes, and claim-evidence pairs from a research PDF paste.
This prompt rewrites a loose LLM prompt into a Markdown system prompt with set sections: identity and purpose, steps, output instructions, examples, and an input slot. It follows the layout used by Fabric patterns.
Craft a concise, achievement-focused professional summary for a target role.
This prompt reads the output of terraform plan and writes a Markdown summary. It looks at what infrastructure will change, security risks, likely cost effects, and compliance points, opening with a one-sentence summary.
This prompt rewrites text that reads as machine-written into short, plain, conversational paragraphs. It includes example pairs that show a phrasing to drop and what to write instead. The goal is everyday wording with simple sentences.
Rewrite an angry draft so it stays firm, clear, and professional.
Route a data question to processing, analysis, or visualization specialist agents.
Create a bulk regex replacement script with backups, preview mode, and an audit trail.
Draft a polite, evidence-based compensation counteroffer email from offer details and supporting evidence.
Find the strongest claims in a sales deck and list what to fact-check.
Build a sales playbook with stages, talk tracks, examples, and operating guidance.
This prompt rates a sales call from its transcript on a 1 to 10 scale across sales basics and how well the pitch fit the seller's business. You paste a short description of the selling company along with the transcript. It lists the main mistakes and ten coaching tips.
This prompt writes a TikTok script that runs less than a minute, split into four timed parts: hook, problem, demo, and call to action. Each part has visual directions, the words to say or show, and ideas for sounds and hashtags.
This prompt builds an Instagram Reel step by step: finding the idea, three possible openings, a timing plan for each second of the clip, and the full script with on-screen text. It adds a caption and hashtags, then reworks the Reel so it also fits TikTok and YouTube Shorts.
Design layered client and server validation with schemas, sanitization, error handling, and attack-vector notes.
This prompt writes a security review checklist for five kinds of ai agents: chat assistants, autonomous agents, text generation apps, chatflows, and workflows. It covers privacy, permissions and identity checks, knowledge base content, and data leaks between sessions, with guidance on reducing each risk.
Generate seed SQL inserts from a database schema.
Write a multi-phase seller conversion call script from diagnosis through close.
Score positive, negative, and neutral sentiment, then assign a label and rationale in JSON.
A prompt is the text you give a language model so it generates a useful response — instructions, examples, constraints, and your content. Prompt engineering is the craft of writing those instructions clearly. This directory hosts ready-to-copy prompts on the page.
Open a prompt, copy the text, paste it into Claude, ChatGPT, Grok, Gemini, or another chat, fill the placeholders, and send. No account is required on this site.
A prompt is copyable chat text. A skill is an agent pack, often a SKILL.md folder. A method is one way to solve a use case on Can AI? — it might be a prompt, skill, agent, tool, or stack. The same prompt can appear here and as a method on a use case.
Yes. The prompt text is on the page. If we show a source credit, keep that credit. There is no paywall in front of the text.
Someone submits a prompt, or it arrives as part of a method on a use case. An editor publishes it. There is no paid placement.
Standalone prompts for writing, research, coding, ops, and other outcomes, tagged with the same sitewide categories as the rest of the directory so you can browse by area.