Curated AI prompts you can run right now.

Turns a quarter's focus area into 3 Objectives, each with 3-4 measurable Key Results.

KRs are leading indicators with numbers — not vague aspirations.

A polite, value-first follow-up email after a no-reply — not "bumping this up".

Brings new value with each touch instead of nagging.

10 high-value vocabulary words for a topic — definitions, examples, mnemonics.

Curated, not random. Each word is one a native uses but a learner often misses.

10 quiz questions (mix of MCQ + short answer) from a piece of text — for self-study or class.

Includes answer key with brief explanations.

Translates code comments + docstrings to a target language, preserving code style.

For internationalising open source / sharing repos with multilingual teams.

A complete CI pipeline YAML — lint, test, build, scan, deploy — for a Node/Python/Go service.

Caching, matrix builds, secrets handling, deploy gates.

Day-by-day study plan from now to exam date, balancing review and new material.

Realistic schedule that includes breaks, retrieval practice, and sleep.

Reviews a form for length, field order, error handling, mobile readiness.

The single biggest conversion lever on most pages.

10 tagline variants in 4 styles for one product.

Each ≤ 8 words. Tested for memorability, not "creativity".

3 ad variations (hook + body + CTA) tested for thumb-stop and conversion.

Built for the Meta auction — short, specific, scroll-stopping.

Audits an existing UI for design-system gaps — inconsistent colors, spacing, typography, components.

Output is a prioritised checklist of "fix this before adding new pages".

Generates 12-15 open-ended interview questions for a research goal, organised by interview phase.

Avoids leading questions and survey-style "rate 1-5" — gets to the actual story.

Rewrites a weak "In conclusion…" into a punchy closing that drives the next action.

Most blog conclusions are throwaway. This makes them earn their place.

A mood-board brief — adjectives, references, colors, do's and don'ts — ready for a designer.

Saves the back-and-forth of "make it more modern".

A 60-second cold call script that gets to the point without sounding salesy.

Permission-based opener, specific reason for the call, single ask.

Outline for a stakeholder-facing roadmap deck — themes, bets, sequencing, what we're not doing.

Theme-based, not feature-list. Avoids "when ships X?" follow-ups.

Detailed outline for a 2000-3500 word whitepaper, with abstract + each section's key ideas.

Avoids the "research is thin" trap — every section gets actual claims to defend.

15 adversarial test cases for an LLM feature — jailbreaks, prompt injection, harmful asks.

For red-teaming an AI tool before launch.

Reviews button, tooltip, and form labels — flags vague or jargon-y copy and rewrites.

For the small text in an interface that adds up to the user experience.

Generates Anki-style flashcards from a topic — front, back, hint, tags.

Atomic cards (one fact each), with cloze deletions where useful.

Designs an empty state — illustration, headline, sub, primary action — for any screen.

Empty states are first impressions for new users. They deserve more than a sad cloud.

Builds a 30-min demo agenda customised to the prospect's use case.

Stops generic feature-tours that lose deals.

Reorganises a product's navigation — top-level, sub-nav, footer — based on user tasks.

Card-sort thinking — by task, not by team org chart.

Identifies cognitive load hotspots on a screen — what the user has to hold in working memory.

Stops "feature stuffing" before it ships.

Speech celebrating a retiree's career — specific achievements, personality, wish for next chapter.

For colleagues or family. Lands somewhere between roast and tribute.

Rewrites stack-trace / generic errors into helpful "here's what to do" messages.

Error copy is product copy. It matters more than landing pages for retention.

Takes a vague stakeholder question and turns it into a precise, answerable analytical query.

"How are we doing?" → 3 specific questions with metrics.

Reads cohort data + surfaces retention shape, decay rate, and "is this curve flat enough?".

For PMF tests, retention reviews, churn analysis.

A "Start / Stop / Continue / More of / Less of" retro template tailored to a release.

For end-of-release or end-of-cycle reviews.

Maps the first 5 minutes — what the user sees, does, and learns to reach first value.

Skips welcome tours nobody reads. Focuses on time-to-first-value.

Builds a customer case study from raw notes — Problem, Solution, Results, Quote.

PSR format with concrete numbers + 1 strong pull quote.

Given an unexpected metric change, lists 5 most-likely causes + the order to investigate.

Saves the "let me check every dashboard" rabbit hole.

Designs a 6-tile dashboard layout for a stakeholder, with each tile's metric + viz type.

Stops the "let's just add another widget" creep.

Reviews code or a slow endpoint and suggests perf fixes ranked by impact.

Big-O analysis + N+1 detection + indexing hints.

Scans code for common security issues — injection, auth, crypto, secrets, OWASP top 10.

Not a substitute for a pen-test, but catches the obvious holes.

Plans how a desktop layout adapts at tablet + mobile — what stacks, what hides, what changes.

Not just "mobile-first" — actual decisions per breakpoint.

Brief for motion designers — easing, duration, choreography, performance notes.

For Lottie / Framer Motion / CSS animations — keeps brand motion coherent.

A dinner-party theme + 4-course menu + drink pairings + playlist vibe.

For hosts who want to do more than "everyone bring something".

Maps a step-by-step user flow (screens, decisions, edge cases) for a specified user goal.

Output is structured so you can sketch it in Whimsical/FigJam without re-thinking the logic.

3 push notification variants — high open + low unsubscribe.

Mobile reality: title ≤ 50 chars, body ≤ 100 chars, drives a specific action.

Designs a fallback strategy when the LLM doesn't know the answer — refuse, deflect, escalate.

Prevents hallucination + makes the AI predictable.

Senior-engineer code review: bugs, security, style, missed cases — ranked by severity.

Paste a git diff or a code block. Get the kind of review a thoughtful staff engineer would write: real bugs first, nitpicks last.

Analyses current subscription pricing vs benchmarks + suggests pricing experiments.

Specifically for SaaS / membership businesses considering a pricing change.

Question set for a JTBD interview that uncovers the real "switch" moment.

Classic Bob Moesta / Switch interview format — anatomy of a purchase.

Writes a log query (Datadog / Splunk / Loki / CloudWatch) to surface what you need.

For incident investigation, post-mortem evidence, or alerting setup.

Plan for metrics, logs, traces, and alerts for a new service — what to instrument from day 1.

Stops "we don't know what broke" incidents.

Turns a cryptic stack trace into a plain-English explanation of what went wrong and where to look.

Cuts the time from "stack trace appeared" to "you know where to look" by 80%.

Scores a list of feature ideas using RICE (Reach × Impact × Confidence / Effort) and ranks them.

Forces honest numbers. Tells you which 2-3 things to ship next and which to drop.

Translates an internal system prompt into clear user-facing help copy for the same tool.

So users understand what the AI is good at + bad at.

Designs an A/B test — hypothesis, variants, primary metric, MDE, sample size, duration.

Stops "let's just see if it converts" experiments that yield nothing.

Generates a personalised tax document checklist for a person's situation + country.

For freelancers, salaried, business owners — knows what each needs.

Writes 3 caption variants (storytelling, list, contrarian) for one post topic.

Optimised for the dwell-time + comment patterns Instagram's 2026 algo rewards.

Decodes any cron schedule string into when it actually runs.

Paste a cron expression. Get back a plain-English description plus the next 5 fire times.

Sales proposal email summarising scope, price, timeline — clear yes/no path forward.

For service businesses sending a written proposal.

Generates a structured component specification (states, variants, props) ready to hand to a designer.

For when you need someone to build a Button or Card or Modal that doesn't end up reinvented every Sprint.

A 2-3 week recovery plan for a common minor injury — rest, mobility, return-to-activity.

Mild ankle sprain, runner's knee, lower-back tweaks. NOT for serious injuries.

3-5 daily prompts — morning + evening — for clarity, not therapy.

For focus, decision quality, end-of-day decompression.

Writes Bloom's Taxonomy-aligned learning objectives for a lesson / module / course.

Observable, measurable. Stops "students will understand X" non-objectives.

Generates 12 open-ended discovery questions tailored to a buyer persona.

Built on MEDDPICC / SPIN — uncovers pain, budget, decision process without sounding scripted.

Drafts a 2-page board pre-read from raw metrics + a quarter's notes.

TLDR + traffic-light metrics + key decisions needed.