Library · the universal hub

ONE REPOSITORY
FOR THE ENTIRE PROMPT STACK.

Prompts, skills, reads, tips, and peer-reviewed research — all searchable, all free to browse.

Grounded in Sweller (1988, updated 2019) · cognitive load theory
⌘ K
Showing 60 of 2750 promptsSort · Most copied ▾
Advanced
★ FLAGSHIPEngineeringClaude
Staff-Engineer Code Review

Reviews a PR like a senior who optimizes for the next reader, not style nits.

Advanced
★ FLAGSHIPEngineeringClaude
Architecture Decision Record (ADR)

Write an ADR that future-you will still understand in 18 months.

Advanced
★ FLAGSHIPEngineeringClaude
Blameless Postmortem

Outage report that reduces fear of speaking up and produces real action items.

Advanced
★ FLAGSHIPGTMClaude
Cold Outbound — Peer-to-Peer

Reach a busy founder without AI-slop tone. Four lines, one ask, no hedging.

Advanced
★ FLAGSHIPFounder VoiceClaude
Calm + Concrete Investor Update

Monthly update that earns trust by being honest about misses.

Advanced
★ FLAGSHIPGTMClaude
Press Release — YC Tone

Announce a B2B SaaS launch in the YC style. Sharp lede, two metrics, one founder quote.

Advanced
★ FLAGSHIPSalesClaude
Sales Discovery — 7 Questions That Surface Pain

Ask the questions that surface pain, not features. Seven questions, no leading the witness.

Advanced
★ FLAGSHIPGTMClaude
SaaS Pricing — First Principles

Set pricing for a new B2B SaaS. Three tiers, unit economics, anchor + decoy logic.

Advanced
★ FLAGSHIPGTMClaude
Positioning — April Dunford Method

Five-step positioning canvas: competitive alternatives, unique attributes, value, ICP, market.

Advanced
★ FLAGSHIPResearchClaude
Customer Interview Synthesis

Distill 12 customer calls into themes, frequencies, and a top-3 list that survives committee.

Advanced
★ FLAGSHIPWritingClaude
Newsletter Issue — Specific Subject Line

Hook earns the open. 3 curated items, one personal note, soft CTA.

Advanced
★ FLAGSHIPContentClaude
YouTube Script — Built for Retention

Hook → reframe → 3 acts → payoff. Designed to hold 60%+ retention.

Advanced
★ FLAGSHIPWritingClaude
Product Changelog — User-Facing

Announce a feature ship. Lead with the job it does, not the feature name.

Advanced
★ FLAGSHIPWritingClaude
Conference Talk Abstract

Submit a talk that reviewers can't skip. Hook, claim, 3 takeaways, audience.

Advanced
★ FLAGSHIPResearchClaude
Research Paper TL;DR

Compress a 30-page paper into 5 lines + 4 structured takeaways.

Advanced
★ FLAGSHIPDesignClaude
Design Critique — Typography Pass

Critique a screen's type hierarchy: sizes, weights, leading, optical alignment.

Advanced
★ FLAGSHIPDesignClaude
Empty State — Designed for Activation

An empty state that teaches the user what to do next. Not just a blank screen.

Advanced
★ FLAGSHIPDesignClaude
Form Validation Microcopy

Error messages that respect the user. Specific, actionable, never condescending.

Advanced
★ FLAGSHIPCustomer SupportClaude
Angry Customer Reply — De-escalate

Acknowledge, explain, propose, follow up. Don't roll over.

Advanced
★ FLAGSHIPLegalClaude
SOC 2 Questionnaire — Vendor Reply

Reply to a SIG Lite questionnaire using your SOC 2 report. Cite controls.

Advanced
★ FLAGSHIPOpsClaude
OKR Refactor — From Wishful to Falsifiable

Take wishful OKRs and turn them into bets you can actually grade.

Advanced
★ FLAGSHIPHealthcareClaude
Patient Intake — SOAP Note

Compress a 20-min intake call into a structured clinical note a physician can scan in 60s.

Advanced
★ FLAGSHIPLegalClaude
NDA Red-line — Vendor-Sent

Flag the clauses that matter: mutuality, term, IP carveouts, governing law.

Advanced
★ FLAGSHIPEducationClaude
Socratic Lesson Plan

Teach a concept by asking, not telling. Five questions ordered by difficulty.

Advanced
★ FLAGSHIPEducationClaude
Rubric Design — Creative Work

Design a rubric for grading creative work that doesn't kill the creativity.

Advanced
★ FLAGSHIPLegalClaude
Policy Doc — From First Principles

Write a policy doc (e.g., remote work, AI usage) that's clear, lived, and won't gather dust.

Advanced
★ FLAGSHIPE-commerceClaude
Product Description — Job-to-Be-Done

Sell without lying. Lead with the JTBD. Three specs. Risk reversal.

Advanced
★ FLAGSHIPReal EstateClaude
Real Estate Listing — Sell the Lifestyle

Sell the moment, not the square footage. 3 paragraphs.

Advanced
★ FLAGSHIPE-commerceClaude
Amazon Listing — Algorithm + Buyer

Write a listing that wins the algorithm AND the buyer. Keywords, bullets, A+ copy.

Advanced
★ FLAGSHIPFounder VoiceClaude
Strategy Memo — Two-Pager

Decision memo that earns the meeting. Context, options, recommendation, risks.

Advanced
★ FLAGSHIPFounder VoiceClaude
Board Deck — Narrative First

Build a board deck that tells one story. Not 40 slides of metrics.

Advanced
★ FLAGSHIPFounder VoiceClaude
Hiring Loop Design — Senior IC

Design a 5-stage interview loop that surfaces real signal, not theater.

Advanced
★ FLAGSHIPFounder VoiceClaude
Performance Conversation — Hard Truth

Have a hard performance conversation that respects both people. Script + recovery plan.

Advanced
★ FLAGSHIPFounder VoiceClaude
Pitch Deck — The Narrative

Build a 10-slide deck investors don't skim. Inevitability, wedge, traction, ask.

Advanced
★ FLAGSHIPStrategyClaude
Pre-Mortem — Imagine We Failed

Run a pre-mortem on a decision. Imagine it's failed; trace back the most likely cause.

Advanced
★ FLAGSHIPAIClaude
System Prompt — Architect

Build a system prompt for a custom agent that doesn't drift. Role, constraints, format.

Advanced
★ FLAGSHIPManagementClaude
Feedback — Radical Candor

Deliver feedback that the recipient can hear AND act on. Specific, kind, future-focused.

Advanced
★ FLAGSHIPDataClaude
Experiment Design — A/B Test

Design an A/B test that's powered, falsifiable, and shippable. Hypothesis to readout.

Advanced
★ FLAGSHIPWritingClaude
Thought Leadership — Contrarian Take

Argue a contrarian position credibly. Steelman opposition, then dismantle.

Advanced
★ FLAGSHIPMarketingClaude
Onboarding Email Sequence

5-email onboarding that gets users to first value, not just first login.

Advanced
★ FLAGSHIPProductClaude
Product Spec — Shippable v0.1

Write a spec that fits on one page and ships in one sprint.

Advanced
★ FLAGSHIPAIClaude
Prompt Debugging — Systematic

Diagnose why a prompt is producing poor output and fix it.

Advanced
AI StartupsAI EngineeringClaude
RAG vs Fine-tune Decision Memo

**Role:** You are a senior AI engineer who has shipped both RAG-based and fine-tuned LLM products at production scale. You believe most team…

Advanced
AI StartupsAI EngineeringClaude
Evals Harness Design for [Domain]

**Role:** AI engineer who has built evals suites that have caught 30+ production regressions before they shipped. You believe vibes-based "t…

Advanced
AI StartupsAI EngineeringClaude
System Prompt Audit

**Role:** Senior prompt engineer who has audited 100+ production system prompts. You read prompts the way an editor reads prose — for the me…

Advanced
AI StartupsAI EngineeringClaude
Agent Loop Halt-Condition Design

**Role:** Applied AI engineer who has shipped agents that completed millions of tool-calling iterations in production. You believe most agen…

Advanced
AI StartupsAI EngineeringClaude
Vector DB Schema Migration Plan

**Role:** Database architect specializing in vector stores at production scale. **Context:** Team is migrating from [SOURCE: e.g., pgvector…

Advanced
AI StartupsAI EngineeringClaude
Token Budget Audit

**Role:** AI engineer focused on cost optimization. You've cut LLM bills 50-70% at multiple companies by identifying token waste. **Context…

Advanced
AI StartupsAI EngineeringClaude
Synthetic Test Set Generator

**Role:** AI engineer specialized in evals. You generate synthetic test sets for products with no ground-truth labels yet. **Context:** A t…

Advanced
AI StartupsAI EngineeringClaude
Regression Suite Design

**Role:** AI engineer who has watched 5+ companies regress quality silently when model versions rotated. You build the suite that catches it…

Advanced
AI StartupsAI EngineeringClaude
LangSmith Trace Analyzer

**Role:** Applied AI engineer who reads LangSmith traces for a living. You've debugged 200+ production agent runs. **Context:** A specific …

Advanced
AI StartupsAI EngineeringClaude
LangGraph State Design

**Role:** AI engineer specialized in LangGraph / state-machine agent architectures. **Context:** Building an agent for [TASK] in LangGraph.…

Advanced
AI StartupsAI EngineeringClaude
Multi-tenant Prompt Isolation

**Role:** AI infrastructure engineer. You've built multi-tenant LLM systems serving 1000+ customers without cross-tenant leakage. **Context…

Advanced
AI StartupsAI EngineeringClaude
Per-Customer Fine-tune ROI Analysis

**Role:** AI ops lead. You've fine-tuned 20+ customer-specific models and learned that 60% of them weren't worth it. **Context:** Customer …

Advanced
AI StartupsAI EngineeringClaude
Model Upgrade Migration Plan

**Role:** AI ops engineer. You've migrated production traffic across model versions 6 times. **Context:** A model upgrade is incoming (e.g.…

Advanced
AI StartupsAI EngineeringClaude
Prompt Template Versioning System

**Role:** Senior AI engineer focused on prompt operations. **Context:** Team has [N] production prompts. Currently they're hardcoded string…

Advanced
AI StartupsAI EngineeringClaude
A/B Harness for Prompts

**Role:** Experimentation engineer applied to LLM products. **Context:** Team wants to A/B test prompt variants on production traffic. Curr…

Advanced
AI StartupsAI EngineeringClaude
LLM Failure-Mode Taxonomy

**Role:** AI safety researcher building the team's shared vocabulary for LLM bugs. **Context:** Team is shipping LLM features fast and prod…

Advanced
AI StartupsAI EngineeringClaude
Streaming UX Patterns

**Role:** Senior product engineer for AI products. You've shipped streaming UIs at 4+ companies. **Context:** A team is building a streamin…

Advanced
AI StartupsAI EngineeringClaude
LLM Cost Dashboard Spec

**Role:** Engineering manager who has built 3 LLM cost dashboards across companies. **Context:** A team has no visibility into LLM costs by…

"

Working memory is the bottleneck of all complex cognition.

John Sweller