📚 The Reusable Prompt Library
Wednesday, July 22, 2026 · 9:00 AM EST · 60 min
Join Zoom
The Reusable Prompt Library — Implementation Workbook
Edmund's Mastermind · Live Workbook
Building a Reusable Prompt Library

Building a Reusable Prompt Library

8 Categories Every Agent Should Own — Stop Retyping, Start Compounding

Your best prompts are scattered across a hundred dead chat threads. Tonight that ends: one library, 8 categories, 24 master templates — 15 seconds from "I need this" to a paste that works every time.

📐
The Architecture The master-prompt formula: Persona + Goal + Anti-Goal + [Variables] + Output Spec.
🗂
The Core 24 Three master templates per category — built from prompts that already worked.
♻️
The Compounding System Test, version, retire — 10 minutes a week and the library gets sharper forever.
Wednesday, July 22, 2026
9:00 AM EST · 60 Minutes
Meeting ID: 810 9036 1081 · Pass: 260722
Session Includes: 📐 Master-Prompt Formula | 🗂 8 Categories · 24 Templates | ♻️ Weekly Compounding Ritual | 💰 $0 in New Software
📚
Write It Once. Own It Forever. Build Your Prompt Library Live.
🎯

Your Money-Making Mission

The numbers that make today's session non-negotiable

Lost Re-Prompting
30 min
per day retyping context AI already heard last week
Master Templates
24
in your finished library — 3 per category, 8 categories
Need → Paste
15 sec
once the library exists, prompting becomes retrieval
Weekly Upkeep
10 min
the Friday ritual that makes the library compound

The 3 Systems You're Building Today

1
📐 The Library Architecture The master-prompt anatomy — Persona + Goal + Anti-Goal + [Variables] + Output Spec — and the one home where every template lives.
2
🗂 The Core 24 Eight categories, three master templates each — converted from the one-off prompts that already worked for you, not written from scratch.
3
♻️ The Compounding System Test, grade, version, retire. Ten minutes every Friday and your library gets sharper while everyone else's chat history gets longer.

My #1 Goal for This Session

My Current Prompt Chaos

📐

System 1 — The Library Architecture

The master-prompt formula and the one home your templates live in

1
System 1 of 3 · The Architecture · $0 in new software

Why This Works

A prompt that worked once is an asset. A prompt you have to find is a liability. The difference between agents drowning in chat history and agents running a machine is that the machine crowd made one decision: prompts are business documents — written once, stored in one place, improved on a schedule.

Every master template follows the same five-part anatomy: PERSONA (who the AI is), GOAL (the exact deliverable), ANTI-GOAL (what it must never do — clichés, fair-housing risk, "nestled"), [VARIABLES] (the bracketed slots you fill per use), and OUTPUT SPEC (format, length, versions). Five parts, every time — that's what makes a prompt reusable instead of lucky.

Where Your Library Lives

📄 Notion / Google Doc · $0
🧠 Claude Project / Custom GPT · $0*
✅ My Choice
💬

System 1 — AI Build Prompts

The AI builds your library structure — copy, paste, fill in [ ]

Run these live during the session. Prompt 2 is the engine of the whole night — it converts prompts that already worked into permanent templates.

Prompt 1 — Library Setup Generator

Build my prompt library structure for [NOTION / GOOGLE DOC]. Eight categories: Listing Marketing, Pricing & CMA, Buyer Comms, Negotiation, Paperwork & Compliance, Database & Referrals, Social Content, Voice & Phone. For each: a one-line description of what belongs there, the naming convention [PREFIX]-[name]-v[#], and an empty template card with the five sections (Persona / Goal / Anti-Goal / Variables / Output Spec) ready to duplicate. Output as a structure I can paste directly.

Prompt 2 — Prompt-to-Template Converter

Here's a prompt that produced a great result for me: [PASTE THE ONE-OFF PROMPT]. Convert it into a master template: 1) extract the reusable PERSONA, 2) state the GOAL precisely, 3) infer the ANTI-GOALS from what good output avoided, 4) replace every specific detail with [BRACKETED VARIABLES] and list them, 5) add an OUTPUT SPEC (format, length, versions). Then show me the finished template card plus one example of it filled in.

Prompt 3 — Persona Bank Builder

Write my persona bank: one reusable AI persona per library category (8 total). Each persona is 2–3 sentences: expertise, point of view, and how it writes — calibrated to my voice profile [PASTE OR REFERENCE] and my market [CITY/NICHE]. Example shape: "You are a luxury listing copywriter with 20 years in [MARKET] who writes vivid, specific, fair-housing-safe copy and never uses clichés." Make each distinct enough that swapping personas visibly changes the output.

Prompt 4 — Anti-Goal Extractor

Here are 3 AI outputs I rejected or heavily edited: [PASTE THEM]. Diagnose exactly what made them fail — clichés, generic claims, wrong tone, invented facts, fair-housing risks. Turn the diagnosis into a reusable ANTI-GOAL block I can paste into every template: "Never: [the list]." Then rewrite one of the rejected outputs with the anti-goals applied so I can see the difference.

🗂

System 2 — The Core 24

Eight categories × three master templates — the working library

2
System 2 of 3 · The Core 24 · Built from prompts that already worked

Why This Works

You don't need 200 prompts. You need 24 that you trust — three per category, covering create / analyze / communicate. Every category follows the same pattern: one template that makes something (a listing launch, a social batch), one that reads something (comps, a contract, your database), and one that says something (the follow-up, the ask, the hard conversation).

And you don't write them from scratch. Tonight's move is conversion: mine your chat history for the prompts that already produced wins, run each through the Template Converter, and file it. An hour of conversion beats a month of invention.

The 8 Categories (Your Library's Shelves)

A
1–4 · Revenue Front 🏠 Listing Marketing · 💲 Pricing & CMA · 🤝 Buyer Comms · ⚔️ Negotiation
B
5–6 · Operations 📋 Paperwork & Compliance · 🗃 Database & Referrals
C
7–8 · Visibility 📣 Social Content · 📞 Voice & Phone
💬

System 2 — Master Template Starters

Four of the Core 24, ready to customize — the full grid of 24 is in the workbook

Each of these IS a master template — persona, goal, anti-goal, variables, output spec. Run them tonight, then convert your own.

LM-listing-launch-v1 (Category 1)

PERSONA: You are a luxury listing copywriter in [MARKET] who writes vivid, specific, fair-housing-safe copy. GOAL: A complete launch for [ADDRESS] — features [DETAILS], likely buyer [PROFILE]. ANTI-GOAL: Never use "nestled," "boasts," "stunning," or any reference to who should live there — property and location only. VARIABLES: address, details, profile, open-house date. OUTPUT: 1) MLS max 250 words, 2) Instagram caption with hook, 3) 60-sec video script — each clearly labeled.

CMA-narrative-v1 (Category 2)

PERSONA: You are a pricing strategist who turns comp data into stories sellers accept. GOAL: The living-room pricing narrative for [ADDRESS]; seller believes [THEIR NUMBER]; my comps [PASTE]; my range [RANGE]. ANTI-GOAL: Never invent data, never bash the seller's number, never promise a sale price. VARIABLES: address, seller's number, comps, range. OUTPUT: the narrative (under 400 words), 3 questions to ask before revealing my number, and the "but Zillow says" response.

NEG-counter-strategist-v1 (Category 4)

PERSONA: You are a real estate negotiation strategist who prioritizes my client's actual interests over "winning." GOAL: I represent the [SIDE] at [ADDRESS]; offer on the table [TERMS]; other side's position [KNOWN]; client's priorities [PRICE/TIMING/CERTAINTY]. ANTI-GOAL: No bluffs I can't back, nothing that risks the relationship with the co-op agent, no legal advice. VARIABLES: side, address, terms, known, priorities. OUTPUT: 3 counters ranked by acceptance odds with exact language, plus the pre-agreed walk-away line.

DB-reengage-miner-v1 (Category 6)

PERSONA: You are a database strategist who believes every quiet contact is a future closing. GOAL: Segment these 6+ month dormant contacts [PASTE: name / last interaction / source / notes] into likely-seller, likely-buyer, referral source, archive. ANTI-GOAL: No guilt-trip openers, no "just checking in," nothing that sounds mail-merged. VARIABLES: the export, my value offer [FORM/MARKET UPDATE]. OUTPUT: the four segments as lists, plus one re-engagement message per active segment in my voice.

♻️

System 3 — The Compounding System

Test, grade, version, retire — the 10-minute ritual that keeps the library alive

3
System 3 of 3 · The Compounding System · 10 min/week

Why This Works

Libraries die the same way CRMs die: built in a burst of enthusiasm, never touched again. The fix isn't discipline — it's a tiny ritual with a trigger. Every Friday, 10 minutes: which template did I use most? Which output did I edit hardest? That edit becomes a version bump. Which template did I not touch in a month? It gets retired or merged.

This is where the compounding happens. A template used 40 times and refined 6 times is an asset no competitor can copy — it encodes your market, your voice, and every lesson from every use. Your chat history disappears; your library appreciates.

The Version Discipline

🧪 TEST
🔁 VERSION
🗑 RETIRE
💬

System 3 — AI Build Prompts

The AI maintains the library too — grading, refining, and auditing on your behalf

These are the librarian's tools. Prompt 3 is the compounding engine — run it every time an output needed heavy edits.

Prompt 1 — A/B Prompt Tester

Run both of these templates on the same real input and produce both outputs side by side: TEMPLATE A: [PASTE v1]. TEMPLATE B: [PASTE v2]. INPUT: [REAL CASE]. Then compare them on: specificity, my-voice match, anti-goal compliance, and readiness to ship without edits. Declare a winner and tell me exactly which lines made the difference.

Prompt 2 — Output Grader

Grade this output against its template's spec. TEMPLATE: [PASTE]. OUTPUT: [PASTE]. Score 1–10 on: goal delivered, anti-goals respected, voice match, factual discipline (nothing invented), output spec followed. For anything under 8, quote the offending line and say whether the fix belongs in the OUTPUT (one-off) or the TEMPLATE (systemic).

Prompt 3 — Template Refiner

I used this template: [PASTE]. It produced: [PASTE OUTPUT]. Here's what I actually sent after editing: [PASTE FINAL]. Diff my edits, infer the rule behind each one, and produce the next version of the template with those rules baked in — so next time the first draft IS the final. Show the changelog: v[N] → v[N+1], what changed, why.

Prompt 4 — Friday Library Review

Run my 10-minute Friday library review. This week I used: [LIST TEMPLATES + ROUGH COUNTS]. Heavy edits happened on: [WHICH]. Untouched for 30+ days: [WHICH]. Tell me: 1) which single template earns a version bump this week and what the bump should be, 2) what to retire or merge, 3) one gap — a task I did manually this week that deserves a new template, 4) my library health score out of 10. Keep the whole review under 200 words.

🗺

The Full Library Map — The Core 24

Eight categories, three templates each: create / analyze / communicate

CategoryCreateAnalyzeCommunicate
🏠 Listing MarketingListing LaunchListing Audit (vs. comps' copy)Open-House Promo
💲 Pricing & CMACMA NarrativeAVM RebuttalPrice-Reduction Story
🤝 Buyer CommsNew-Buyer WelcomeShowing Recap + SignalsOffer-Strategy Brief
⚔️ NegotiationCounter StrategistMultiple-Offer AnalyzerWalk-Away Framing
📋 Paperwork & ComplianceRepair-Request DraftContract SummarizerInspection Translator
🗃 Database & ReferralsAnniversary TouchRe-Engagement MinerReferral Ask
📣 Social Content7-Day BatchPost-Performance ReviewMarket-Stat Explainer
📞 Voice & PhoneReceptionist ScriptCall-Notes SummarizerVoicemail Scripts (5 scenarios)

The Conversion Rule

Don't write these from scratch. Mine your chat history for the version that already worked, run it through the Prompt-to-Template Converter, and file it under the naming convention. Target pace: 8 templates tonight (one per category), 24 by day 30.

📅

The 30-Day Library Plan

From scattered chats to a compounding asset in four weeks

Week 1 — Foundation
  • Library home built (Notion/Doc + naming convention)
  • Persona bank: 8 personas written
  • Anti-goal block extracted from rejected outputs
  • First 8 templates converted (one per category)
  • Library loaded into my Claude Project / Custom GPT
Week 2 — The Build-Out
  • Mine chat history: 10 more winners identified
  • Convert 8 more templates (16 total)
  • Every template used at least once on real work
  • First Friday review done (10 min)
  • First version bump shipped (v1 → v2 somewhere)
Week 3 — Completion
  • Final 8 converted — Core 24 complete
  • A/B test: 2 templates vs. old freestyle prompting
  • Output Grader run on my 3 most-used templates
  • Team/partner access granted + walkthrough
  • Friday review #2
Week 4 — Compounding
  • Retire/merge anything untouched since Week 1
  • Version log shows 4+ bumps
  • Time audit: minutes from need → shipped output
  • One new template from a gap the reviews exposed
  • Friday ritual locked as a recurring calendar block
📈

Your Library ROI Calculator

The library costs $0 and 10 minutes a week. Here's what that buys.

Time Math

The Asset Math

✍️

My Library Commitment Contract

Signed today. First 8 templates before I sleep.

I commit to:

The Category I'm Building First

🏠 Listing Marketing 💲 Pricing & CMA 🤝 Buyer Comms ⚔️ Negotiation 📋 Paperwork 🗃 Database 📣 Social 📞 Voice & Phone

My Biggest Obstacle — and How I'll Handle It

The Library Manifesto

I don't write prompts.
I own them.

Every agent using AI today is doing one of two things: renting intelligence one chat at a time, or building an asset that compounds. The renters start every conversation from zero — same context, same instructions, same corrections, typed again and again into a history no one will ever read.

The owners write it once. Persona, goal, anti-goal, variables, spec — filed, named, versioned. Their twentieth listing launch is better than their first, because every use taught the template something. Their library is a business document, as real as their CRM and more personal than their brand.

Twenty-four templates. Eight categories. Ten minutes a week. That's not a productivity hack — that's intellectual property. And a year from now, when every agent has the same AI tools, the only difference left will be what you taught yours.

"Because Starting From a Blank Prompt is NOT an Option!"

— Edmund Bogen · Edmund's Mastermind · Bogen.ai