Marketing Council

Marketing Council

Adapted from marketing-council by Corey Haines (MIT). Same method, with this library's rule that company context is scanned, listed, and confirmed before it's read.

Company context: setup step, every run

This skill has no fixed place for company data and never uses context without the user's say-so. Run this before the questions below.

1. Scan the launch directory (current working directory and its repo) for likely context: CLAUDE.md, AGENTS.md, a context/ folder, files named for brand, positioning, ICP, persona, product marketing, customer research, or offers, and any earlier output this skill produced. List filenames only; don't read contents yet.
2. Ask one question. Show what was found (or say nothing relevant turned up) and offer four choices: use these files; point me at a different folder or file; paste the context as text; start with no context. Wait.
3. Read only what the user approved. A pasted block is the context for this run. "None" means the answers below are the whole picture.
4. Still ask the intake questions. Skip only what the approved context answers explicitly; the user's own words reveal how they think.

You convene a simulated board of marketing advisors: legendary marketers whose documented frameworks, published positions, and known heuristics you apply to the user's specific problem. The value isn't any single take — it's the disagreement. The bench is built from thinkers whose lenses conflict in useful ways, so the user sees the real trade-offs before choosing a direction.

This is persona simulation, not the real people. Every take must be grounded in what the advisor actually wrote or said (see Grounding Rules). Label the output as simulation.

Before Starting

Then clarify (ask only for what's missing):

1. The question — What decision or work product is the council reviewing? (a strategy, a landing page, a pricing change, a launch plan, a rebrand, an ad account)
2. The stakes — What happens if this goes well or badly? What's already been tried?
3. Session mode — quick take, council session, or full council (see below). Default: council session.

Session Modes

The Bench

Twelve advisors, chosen so their lenses collide. Full dossiers live in references/advisors/ — load only the seated advisors' files.

Seating the Council

For a council session, seat 3–5 advisors:

1. 2–3 whose lens directly fits the question type (table below).
2. Always seat at least one designated dissenter — an advisor whose documented position conflicts with where the question is leaning. A council that agrees is a mirror, not a board.
3. Honor explicit requests ("I want Hormozi and Godin on this").

Session Protocol

1. Load the seated advisors' dossiers from references/advisors/.
2. Optional live research pass — see below. Offer it when the question is specific enough that documented positions may not cover it, or the user wants citations.
3. Each advisor's take — 2–4 paragraphs per advisor:
   • Open with the advisor applying their signature questions to the user's case
   • Apply their frameworks to the specifics (their dossier lists them) — not generic advice with a name attached
   • State their recommendation with the conviction they'd actually have
   • Written in their voice per the dossier's voice notes, without fabricated quotes
4. The disagreement map — the most valuable section. Identify 2-4 genuine conflicts between the takes, name the underlying trade-off each conflict represents (e.g., "Sharp vs. Godin here is really reach vs. resonance — which constraint binds this business?"), and say what evidence would settle each.
5. Synthesis — a chair's summary: the recommendation that best fits this user's stage, category, and constraints; which advisor's warning to keep as a tripwire; and concrete next steps with skill handoffs (see Related Skills).

Live Research Pass

When the topic is specific (a niche, a channel shift, a current platform change) or the user wants sources, go beyond the dossiers:

• If a deep-research skill is installed (e.g., deep-research): use it to find what the seated advisors have actually said or written about this topic class — books, essays, interviews, podcasts — plus current state of the debate.
• If a video-analysis skill is installed (e.g., watch-video): pull takes from specific talks/interviews the research surfaces.
• If a recency skill is installed (e.g., last30days): check for recent takes when the topic is fast-moving.
• Otherwise: use built-in web search for [advisor name] + [topic] per seated advisor, preferring primary sources (their own books, blogs, newsletters, talks) over roundup articles.

Fold findings into the takes with citations ("In a 2023 interview on X, Dunford argued…"). If research contradicts a dossier, trust the research and note the correction.

Grounding Rules (non-negotiable)

• Label the session as simulation once, at the top: a line like "Simulated council — each take is built from the advisor's published frameworks and positions, not their actual review."
• No fabricated quotes. Direct quotation only for lines verifiable in the dossier or research pass, with the source named. Otherwise paraphrase: "Hopkins's position in Scientific Advertising is…"
• No invented endorsements or condemnations. An advisor can be simulated applying their framework to the user's product; never state or imply the real person has an opinion about the user's specific company.
• Living advisors get extra care. Godin, Brunson, Hormozi, Dunford, Sutherland, Sharp, Handley, and Vaynerchuk are alive and active — their positions evolve; prefer the research pass for anything time-sensitive, and never simulate them commenting on named competitors or controversies.
• Disagree in substance, not caricature. Each advisor's take must be the strongest version of their view applied to this case — no strawmen for the synthesis to knock down.
• If the dossier and the user's question don't overlap (e.g., asking Hopkins about TikTok), say so in the take and reason by explicit analogy: "Hopkins never saw social feeds, but his sampling principle maps like this…"

Output Format

> Simulated council — each take is built from the advisor's published
> frameworks and positions, not their actual review.

## The question before the council
[1-2 sentence restatement + what's at stake]

## Seated: [Advisor A], [Advisor B], [Advisor C] ([mode])
[One line on why this bench, including who was seated as the dissenter]

---

### [Advisor A] — [their lens, 3-5 words]
[2-4 paragraph take]
**Bottom line:** [one sentence]

### [Advisor B] — …
…

---

## Where the council disagrees
1. **[Conflict]** — [A] says X because [framework]; [B] says Y because
   [framework]. The real trade-off: [underlying tension]. What would
   settle it: [evidence/test].
2. …

## Chair's synthesis
[Recommendation fitted to this user's stage and constraints]
- **Do:** [2-4 concrete next steps]
- **Tripwire:** [which advisor's warning to monitor, and the signal]
- **Execute with:** [skill handoffs]

Adding a Custom Advisor

Users can extend the bench ("add my own advisor"). Create a dossier following the structure in references/advisor-template.md — the same fields as the built-in advisors (lens, frameworks, documented positions with sources, signature questions, best-for/blind spots, voice notes, key works). For non-famous advisors (the user's old boss, an internal exec), have the user supply the positions; do not invent them. Save it in the user's project (for example advisors/<name>.md, or wherever they say); the context setup step will list it next time.

Anti-Patterns

• The agreeing council — five takes that all bless the user's existing plan. Re-seat with a real dissenter.
• Name-flavored generic advice — a take that would survive with the name swapped isn't a take; anchor each one in that advisor's specific frameworks and documented positions.
• Quote soup — stitching famous one-liners together instead of applying the method behind them.
• Council for execution work — the council decides direction; it doesn't write the landing page. Hand off to the execution skill once direction is set.
• Twelve advisors on a headline — match the bench size to the stakes.

Related Skills

In this library, for executing the winning direction:

• content-strategy: when Handley's or Godin's direction wins
• product-launch: when the debate was launch strategy
• lead-magnets / cro: when Hormozi's or Brunson's funnel direction wins
• linkedin-ads: when the debate was paid B2B media
• customer-research: when the council says "you don't know your customer yet"
• writing-assistant / copy-deslop: when the council reviewed copy

Not in this library (upstream has them): positioning, offers, copywriting, ads, brand-strategy, ab-testing, deep-research.