Webhook Payload Normalizer JSON
Normalize an inbound webhook into canonical event JSON while preserving unmapped fields and timestamps.
AI prompts.
346 prompts · 321–340
Normalize an inbound webhook into canonical event JSON while preserving unmapped fields and timestamps.
Turn a messy notes dump into a realistic weekly plan.
Turn messy whiteboard notes into a grouped checklist of decisions, questions, and actions.
This prompt drafts a short cadence aimed at one person's role at a target company, with two emails, a LinkedIn note, a voicemail, and a last nudge. You add what your company does and what the buyer probably cares about. Each touch stays brief and low on hype.
This prompt writes eight pieces of Etsy content for one product. The set includes the description, a product story, 15 to 20 search keywords, an FAQ, customer reply templates, replies to bad reviews, thank-you notes, and posts for Instagram, Facebook, and Pinterest.
This prompt writes the headline line on a LinkedIn profile, up to 220 characters. It states your expertise and what you offer and works in keywords people search for.
This prompt turns a clinician's notes into a plain summary of the visit and discharge, written for a patient still learning English who reads at roughly a middle-school level. It explains the diagnosis and treatment simply and lists care steps at home, warning signs, and follow-up, closing on a supportive note. Patient data should only go into HIPAA-compliant tools.
This prompt reads the output of a git diff against the main branch and writes a PR description as Markdown. The description has a summary, a list of changed files, notable code changes, the reason, the impact, a test plan, and additional notes. The tone is plain and factual.
This prompt turns notes from a quarterly business review, along with a table of numbers, into a written summary. It covers results achieved, how the product was used, what is different from the prior quarter, risks, and three suggestions for the coming quarter, in a neutral tone.
This prompt writes a newsletter email of 150 to 300 words that fits a brand mention into a personal story. It includes a subject line and the preview snippet, a useful tip unrelated to the product, a gentle call to action, and a question that invites replies.
This prompt writes a reply to a customer using their message, the known facts, and your policy limits. The reply opens with empathy, gives the answer or next steps, explains any limits and offers other options, and closes by asking for one clear reply.
This prompt writes a technical user story for a new feature in a complex software system, in a form that product, development, operations, and QA can all read. Each story has a description in the As a, I want, So that pattern and a list of acceptance criteria. The style is plain, with no cliches, jargon, or filler openers and closers.
This prompt writes a full YouTube script from your subject, viewers, format, voice, and the action you want people to take. It starts with a hook in the first ten seconds, moves through three to five segments that keep questions open, adds a beat midway to pull attention back, and closes with the call to action.
This prompt writes twelve ads for the product and buyers you name, split evenly across emotional, practical, and curiosity angles. Each ad has a headline and body text kept under a character limit you set.
This prompt drafts an LOE (level of effort) estimate for work you describe. It covers scope and deliverables, business impact, roles and headcount, hours and cost, risks, dependencies, and assumptions.
This prompt builds an on-call runbook outline for a service in YAML. It includes severity tiers, alerts, triage steps, mitigation steps, rollback, message templates, escalation rules, and a checklist for after the incident.
This prompt writes a short note, under 200 words, explaining how actuals compare with plan and the prior period. It names the three biggest drivers, separates timing effects from lasting ones, and lists three items to confirm with owners.
This prompt first sketches who the buyers are, then writes three Facebook ads to test against each other. Each ad has a headline, body text, and a call to action.
This prompt writes a status update for a live incident from the timeline and current state. It gives two versions: one for the internal ops team with owners and next steps, and one for customers that sticks to known facts. Both include when the next update will come.
This prompt writes the short intro a host reads aloud before an episode of a podcast or show, based on what the episode covers. It names the guest, says who they are, and lists up to ten short topics covered.
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.