01 Claude skill

Brand Context Folder creator for Claude

Architecture transfer, not content copying. The Marcus-Aurelius reference structure — concentric layers, evidence-based voice profile, dual-theme HTML brand books — applied to a fresh client.

Claude skill bundle · ~12 files advanced Free · No upsell
1 folder, 4 surfaces
Same brand system powers Claude Projects, Claude Code, n8n automations, and downstream skills — no prompt drift.
Free download · Claude skill bundle

Get the bundle

Two fields. We send the files and a setup note — that's it.

No spamUnsubscribe anytimeGDPR-friendly
02 The leak

If this sounds familiar, the claude skill is for you.

01

Your brand guide lives in a Figma file or locked PDF, and no AI session can actually read it at runtime.

02

Voice drifts across every automation because each workflow ends up writing its own ad-hoc prompt.

03

Proposals and emails surface hallucinated case studies and broken offer pricing — the LLM has no authoritative file to query.

04

Your single-file brand doc has crossed 500 lines and nobody reads it. Important rules get skipped on every draft.

03 What's inside

A working system, not a prompt.

Each piece extracted from a live engine — same prompts, same scaffolding, same rules.

  • 01
    SKILL.md — the canonical brand system every Claude session loads first: colours, typography, logo rules, voice shortcuts, decision matrix
  • 02
    CLAUDE.md — one-page index for humans and fresh sessions, so a new Claude run knows what to read and in what order
  • 03
    Seven structured reference files: target audience, brand voice (YAML), style rules, brand assets, offers and pricing, sales process, pillar landing briefs
  • 04
    Two rendered HTML brand books — dark and light — sharing one CSS foundation, nine sections each, machine-queryable
  • 05
    Five-phase workflow: discovery interview → voice extraction → scaffold and populate → render brand books → handoff summary
  • 06
    Nine-dimension voice profile (directness, warmth, confidence, formality, wit, precision, authority, vulnerability, contrarianism) with every score cited against a real evidence snippet
Field-tested · Marcus-Aurelius brand system

This is the exact architecture running my own brand — and the same one I scaffold for every new client whose work has to flow across Claude, n8n, and downstream skills without rewriting prompts.

3 layers
Concentric architecture — each layer solves a specific failure mode of single-file brand guides
9 dimensions
Voice profile with every trait cited against a real evidence snippet — falsifiable, not vibes
4 surfaces
Claude Projects, Claude Code, n8n automations, downstream skills — one folder, no drift
04 Audience

Built for a specific operator. Not for everyone.

Who it's for
  • Operators onboarding a new client whose work will run across multiple AI surfaces and need a single source of truth
  • Founders setting up their own brand as a reusable system, not a one-off landing page or Figma file
  • Anyone migrating a brand guide from Figma, Notion, or a locked PDF into something an AI session can read at runtime
Probably not for you if
  • Anyone who needs one piece of on-brand work — write the email, post, or page directly without spinning up a full system
  • Operators editing an existing brand folder — read it first, then edit in place
  • Anyone wanting a single output file (just the voice profile, just the offers doc) — that's a sub-skill's job
05 · Get it

The same claude skill I run for paying clients. Yours, free.

Two fields. The bundle and a short setup note land in your inbox.

No spamUnsubscribe anytimeGDPR-friendly

06 · FAQ

Common questions

Do I need a Claude paid plan to run this?

Yes — the skill assumes Claude.ai with skills enabled, or Claude Code. The skill itself is free.

Can I use this for clients in any industry?

Yes. The architecture is industry-agnostic — what changes is the input (client interview, voice samples, offers). The output structure stays the same across luxury hospitality, B2B services, agencies, or product brands.

How is this different from a normal brand-guide generator?

Most generators output a single file or a slide deck. This produces a queryable folder of plain text, structured YAML, and rendered HTML — the format AI sessions can actually load and obey at runtime, not just look at.

Can I edit the output after the skill runs?

Yes — the brand folder is plain text and YAML. Edit in place. Just don't re-run the skill on the same folder; that's a different workflow (and a sub-skill we'll publish separately).

Marc-Aurele Legoux, founder of Marcus-Aurelius Digital
Marc-Aurele Legoux · Founder

“I build AI growth engines for luxury villas, boutique hotels, and high-ticket service brands. The skills I give away are the ones I run for paying clients. If you build it yourself, great — if you’d rather have it built and run, talk to me.”