Claude Prompts

Scaffold a production App Router page: Server Component data fetching, Suspense streaming for instant TTFB, correct cache strategy (fetch cache vs unstable_cache vs revalidatePath), loading/error boundaries, and generateMetadata — with the non-obvious patterns most tutorials skip.

Production-grade dashboard layout: KPI cards with counting animations and trend sparklines, a chart area, activity table — all with dark mode, skeleton loading states, and responsive breakpoints defined to the pixel.

Generate correct, non-recursive RLS policies so anyone reads published rows and only owners edit their own.

Production-ready Stripe webhook route that verifies the signature and processes events exactly once.

A retrieval-augmented system prompt that answers only from context and returns inline citations or 'I don't know'.

Turn any assistant into a decisive, no-padding expert. Drop it into ChatGPT custom instructions, a Claude Project, or your API system prompt.

Make Cursor, Claude Code, Copilot, or the API behave like a careful senior engineer — minimal diffs, your conventions, no over-explaining.

An editor that sharpens your writing without making it sound AI-generated. Works as ChatGPT custom instructions or a Claude system prompt.

Turns any assistant into a tutor that actually teaches — questions, hints, and understanding checks instead of answer dumps.

For developers: forces schema-exact, parseable output every call — for apps, agents, and data pipelines built on the API.

Generate 10 hero headlines matched to buyer awareness stages using PAS, 4U, and 'So What?' frameworks — with A/B test picks ranked by expected lift.

Write three-tier pricing copy engineered with the decoy effect, anchoring bias, and loss aversion — including plan names that don't make buyers feel cheap and FAQs that kill the 5 objections that actually prevent SaaS purchases.

Extract stateful logic from a bloated component into typed, testable custom hooks.

Paste a slow query and get a root-cause diagnosis, targeted index/rewrite fixes, and a before/after query plan — with specific pattern detection for N+1s, implicit casts, and composite index gaps.

Design a production JWT auth flow with access/refresh rotation, token family revocation, and a concrete threat model — including the 6 common JWT mistakes that lead to breaches and how to avoid each one.

Produce a reproducible Pandas cleaning pipeline: types, missing values, dedupe, outliers.

Design strict, self-validating tool schemas with confidence calibration, discriminated unions, and chain-ready contracts — so your agent calls tools reliably instead of hallucinating arguments.

Turn a goal into a coordinated planner→worker→critic agent workflow with clear handoffs and a stop condition.

Turn a feature description into a normalized Prisma schema with relations, indexes, and migration-safe defaults.

Expand a one-line startup idea into a 10-slide narrative arc with stage-specific VC objection prep, a precise ask slide, and the proof each claim must show.

Turn raw interview notes into ranked insight themes, supporting quotes, and concrete product decisions.

Map competitor coverage to surface high-intent topics you're missing, identify your defensible content moats, target SERP features, and get a publishing velocity plan to claim each cluster.

Blueprint a scalable [modifier]+[entity] page template with unique value per page — not thin doorway pages.

A prompt that makes any AI lead you through a focused 5-minute morning reflection — one question at a time — and ends with a clear intention for the day.