The Marketing Foundation toolkit: the files your team installs

You finished the Foundation module with two documents: a messaging-framework.md and a brand-voice.md for your brand. This toolkit makes them infrastructure. A file you wrote once helps you once; a file your team installs — that Claude reads on every task — helps every job, forever.

Everything here is copy-able. Replace the Mizan placeholders (the GCC bookkeeping brand from the module) with your own, save the files in the folder your team works in, and open it in Claude Desktop. From then on, every content task in that folder starts from your real message and voice instead of each person’s guess.

The whole pack is three files and a handful of prompts. That’s the point — a foundation small enough to actually get installed beats a beautiful one that lives in a doc nobody opens.

The marketing CLAUDE.md

This is the standing context Claude reads automatically when it opens your project folder, so nobody has to re-explain the brand every chat. Keep it short and current — it points at the two foundation docs rather than repeating them.

# CLAUDE.md — [Brand] marketing

## Who we are
[Brand] is [one-line positioning — pull the core promise from
messaging-framework.md]. We sell to [audience] in [markets, e.g. the GCC],
in [English and Arabic].

## The two source-of-truth files — read these first
- messaging-framework.md  → WHAT we say (positioning, pillars, proof, objections)
- brand-voice.md          → HOW we say it (tone, words we use/avoid, examples)
- brand-voice-ar.md       → the Arabic voice (authored, not translated)
Always read the relevant ones before drafting. If a draft conflicts with
them, the files win — flag the conflict, don't quietly override it.

## How we work with you
- You draft; a person decides. Fact-check every claim, stat, price, and
  named customer — state nothing as fact you can't source.
- On brand and message, follow the two files above, not your own taste.
- Bilingual work is adapted, not translated. Ask which language leads.

## What's safe in this folder
- Safe: drafts, briefs, published copy, our brand/messaging docs, aggregate
  metrics, public competitor material.
- Never here: customer lists, PII, lead-level data, unreleased financials,
  anything under NDA or embargo. Tell me if a file looks like it contains them.

## House rules
- Words we avoid: [paste the lexicon from brand-voice.md].
- Every published claim has a named human owner before it ships.

On Desktop you create and edit this in the file pane — no commands. Anthropic’s docs call the “Ask permissions” mode the one recommended for new users; leave it on, and the first time Claude reads this file you’ll approve it in the prompt.

The brand-voice.md template

Voice is the document teams get wrong by writing adjectives. This template forces the specific, exampled version Claude can actually act on. Fill it from copy you’re proud of.

# brand-voice.md — [Brand]

## Who we sound like
One or two sentences: the person your brand talks like. Concrete, not
"professional yet approachable." e.g. "A sharp colleague who respects your
time and never shows off."

## Tone rules (do / don't pairs)
- Do: [plain verbs]            Don't: [leverage, utilize, empower]
- Do: [contractions]           Don't: [exclamation marks]
- Do: [you/your, one reader]   Don't: [we/our as the subject of every line]
- Do: [short, one idea]        Don't: [stacked clauses]
- Do: [name the benefit]       Don't: [lead with the feature]

## Before / after (the rules, shown)
✗ [a real off-voice sentence you've actually shipped or rejected]
✓ [the same sentence, on voice]
(two or three pairs — these examples ARE the document)

## Words we use / words we avoid
Use:   [5–10 words that sound like you]
Avoid: [5–10 words that don't — jargon, hype, competitor clichés]

## Arabic voice note
Register: where you sit between MSA and a Gulf-natural tone, and why
(tie it to the audience). Formality, rhythm, how you address the reader.
Authored from Arabic copy you're proud of — see brand-voice-ar.md.

The messaging-framework.md template

The messaging house — what you say, kept separate from how you say it. The proof column is the discipline: a pillar without it doesn’t ship.

# messaging-framework.md — [Brand]

## Positioning
For [target persona] who [need], [Brand] is the [category] that
[core value] — unlike [main alternative], we [key differentiator].

## Core promise
[One plain sentence. A stranger could repeat it.]

## Value pillars (benefit · capability · PROOF)
1. [Benefit in the customer's words] · [the capability that delivers it]
   · Proof: [the single hardest real proof point — metric/outcome/cert]
2. ...
3. ...
(Flag any pillar whose proof is thin or missing — fix or cut. No wishes.)

## Per-persona angles
[Persona A]: leads on [pillar]; fears [x]; top objection: [...]
[Persona B]: leads on [pillar]; fears [y]; top objection: [...]

## Objection handling (the 6 that stall deals)
| Objection            | Honest, proof-backed answer            |
| price                | ...                                    |
| switching cost       | ...                                    |
| trust / security     | ...                                    |
| "why now"            | ...                                    |
| build vs buy         | ...                                    |
| [the one specific to us] | ...                                |

## Words we use / words we avoid
Use: [...]   Avoid: [...]

The saved-prompt library (Foundation)

The recurring foundation jobs, as prompts you reuse. Paste them in the chat with the right files open; on the Terminal & Automation track these become slash commands so they’re one keystroke, but you need none of that to use them today.

Pressure-test the proof
  "Read messaging-framework.md. For each value pillar, name the single
   strongest proof point and rate it: solid / thin / missing. For anything
   thin or missing, tell me exactly what evidence would fix it. Don't soften."

Build the per-persona angles
  "Using messaging-framework.md, rewrite the core promise and the two pillars
   that matter most for [persona], in their language and priorities, and name
   the one objection they're most likely to raise."

QA a draft against voice AND message
  "Read brand-voice.md and messaging-framework.md, then review this draft.
   Flag every line that's off-voice or off-message, quote it, and rewrite it.
   List any claim that needs a fact-check before it ships."

Localize, don't translate
  "Read brand-voice-ar.md and messaging-framework.md. Adapt this English copy
   into Arabic for a Gulf audience — match the Arabic voice doc's register,
   localize the examples and objections, and flag anything that shouldn't
   carry over directly. This is an adaptation, not a translation."

Refresh the foundation
  "The product/market changed: [what changed]. Read messaging-framework.md and
   tell me which pillars, angles, or objections are now stale, what to update,
   and what proof I need to re-confirm. Propose a versioned diff, don't rewrite
   silently."

Installing it (Desktop, no setup)

1. Save the three files — CLAUDE.md, brand-voice.md, messaging-framework.md (plus brand-voice-ar.md for bilingual teams) — in the folder your marketing team works in.
2. Open that folder in Claude Desktop and approve the read in the “Ask permissions” prompt.
3. Start any task by opening the relevant docs; the prompts above do the rest.

That’s the whole install. The foundation you built in the module is now shared infrastructure — and Module 2 of the track extends this same pack with the content-engine templates that build on it. If you’re standing this up across a team rather than for yourself, read the operating guide for the data, sign-off, and rollout layer that belongs underneath.