When the user wants multiple expert perspectives on a marketing question — a simulated board of advisors staffed by legendary marketers (Seth Godin, David Ogilvy, Eugene Schwartz, April Dunford, Rory Sutherland, Alex Hormozi, Byron Sharp, and more). Also use when the user mentions 'marketing council,' 'board of advisors,' 'advisory board,' 'what would Seth Godin say,' 'what would Ogilvy think,' 'c
8586When the topic is specific (a niche, a channel shift, a current platform change) or the user wants sources, go beyond the dossiers:8788- **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.89- **If a video-analysis skill is installed** (e.g., `watch-video`): pull takes from specific talks/interviews the research surfaces.90- **If a recency skill is installed** (e.g., `last30days`): check for recent takes when the topic is fast-moving.91- **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.92
8788- **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.89- **If a video-analysis skill is installed** (e.g., `watch-video`): pull takes from specific talks/interviews the research surfaces.90- **If a recency skill is installed** (e.g., `last30days`): check for recent takes when the topic is fast-moving.91- **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.92
141142Users can extend the bench ("add my own advisor"). Create a dossier following the structure in [references/advisor-template.md](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 to `.agents/advisors/<name>.md` in the user's project so it persists and never collides with repo updates.143
23Copy this structure to add an advisor to the bench. Save custom advisors to `.agents/advisors/<kebab-name>.md` in your project (not inside the skill folder) so they survive skill updates.45Two kinds of custom advisors, two grounding standards:67- **Public figures** (a famous marketer not on the bench): every framework and position must trace to something they published or said — research before writing, cite sources, follow the same grounding rules as the built-in dossiers.8- **Private advisors** (your former boss, your best customer, your CFO): the *user* supplies the positions and heuristics. The agent must not invent views for a real private person — interview the user to fill the template.9
3233## Best for / blind spots3435**Best for:** [problem types their lens genuinely illuminates]36**Blind spots:** [documented criticisms or acknowledged limits — this is37what makes their dissent honest rather than decorative]3839## Voice notes4041[2-3 sentences: sentence rhythm, favorite metaphors, tone, tics. Enough42to write in their register without fabricating quotes.]43
35**Best for:** [problem types their lens genuinely illuminates]36**Blind spots:** [documented criticisms or acknowledged limits — this is37what makes their dissent honest rather than decorative]3839## Voice notes4041[2-3 sentences: sentence rhythm, favorite metaphors, tone, tics. Enough42to write in their register without fabricating quotes.]43
67- **Public figures** (a famous marketer not on the bench): every framework and position must trace to something they published or said — research before writing, cite sources, follow the same grounding rules as the built-in dossiers.8- **Private advisors** (your former boss, your best customer, your CFO): the *user* supplies the positions and heuristics. The agent must not invent views for a real private person — interview the user to fill the template.9
会不会绕过安全保护？检查是否跳过网站安全验证、开放过多文件权限，或取消操作前的确认。未发现风险
会不会误导 AI 或隐藏内容？检查工作说明是否要求 AI 忽略你的指令、干扰检查结果，或夹带看不见的文字。发现 2 项风险
1516**Check for product marketing context first:**17If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md`), read it before asking questions.18
141142Users can extend the bench ("add my own advisor"). Create a dossier following the structure in [references/advisor-template.md](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 to `.agents/advisors/<name>.md` in the user's project so it persists and never collides with repo updates.143
5051**Seating a custom advisor:** mention them by name when convening ("seat my advisor Maria on this council"). The agent loads the file from `.agents/advisors/` and treats it like any bench dossier, including the grounding rules — no fabricated quotes, no invented endorsements.52
8788- **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.89- **If a video-analysis skill is installed** (e.g., `watch-video`): pull takes from specific talks/interviews the research surfaces.90- **If a recency skill is installed** (e.g., `last30days`): check for recent takes when the topic is fast-moving.91- **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.9293Fold 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.94
90- **If a recency skill is installed** (e.g., `last30days`): check for recent takes when the topic is fast-moving.91- **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.92
9293Fold 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.94
97- **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."*98- **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…"99- **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.100- **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.
741. **Load the seated advisors' dossiers** from `references/advisors/`.752. **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.763. **Each advisor's take** — 2–4 paragraphs per advisor:77 - Open with the advisor applying their *signature questions* to the user's case78 - Apply their frameworks to the specifics (their dossier lists them) — not generic advice with a name attached79 - State their recommendation with the conviction they'd actually have80 - Written in their voice per the dossier's voice notes, without fabricated quotes814. **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.825. **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).83
9697- **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."*98- **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…"99- **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.100- **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.101- **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.
34**Best for:** Offer construction, pricing, unit-economics discipline, lead gen for high-LTV services/info/SaaS, breaking analysis paralysis with volume quotas.35**Blind spots (documented):** Critics document engineered scarcity/FOMO in his own launches (e.g., the 2025 Money Models launch critique) and note the playbook oversimplifies outside high-ticket, pain-driven categories. Offer-maximalism (bonus stacks, urgency, guarantees) reads infomercial-coded in brand-sensitive, enterprise, and luxury contexts. Little on long-horizon brand, creative craft, or buyers not in acute pain. *His launch/revenue figures are self-reported — don't state as verified fact.*36
34**Best for:** Offer-market fit before copy polish, audience/list selection, direct-response email and mail, injecting urgency and personality into sterile copy, ruthless founder prioritization.35**Blind spots:** No framework for brand, product, retention, or reputation. His career included an 18-month federal prison term for mail fraud (the Boron Letters were written from that camp) — the documented shadow side of the style; his tactics transfer poorly to trust-sensitive, regulated, or enterprise contexts. *Legend-figures like the coat-of-arms letter's "most mailed in history" claims are unverifiable — treat as lore, not statistics.*36
1112**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.13
78 - Apply their frameworks to the specifics (their dossier lists them) — not generic advice with a name attached79 - State their recommendation with the conviction they'd actually have80 - Written in their voice per the dossier's voice notes, without fabricated quotes814. **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.
80 - Written in their voice per the dossier's voice notes, without fabricated quotes814. **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.825. **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).83
910You 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.1112**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.13
5253For a council session, seat 3–5 advisors:54551. **2–3 whose lens directly fits the question type** (table below).562. **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.573. Honor explicit requests ("I want Hormozi and Godin on this").58
1516**Check for product marketing context first:**17If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md`), read it before asking questions.18
73741. **Load the seated advisors' dossiers** from `references/advisors/`.752. **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.
8586When the topic is specific (a niche, a channel shift, a current platform change) or the user wants sources, go beyond the dossiers:8788- **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.89- **If a video-analysis skill is installed** (e.g., `watch-video`): pull takes from specific talks/interviews the research surfaces.90- **If a recency skill is installed** (e.g., `last30days`): check for recent takes when the topic is fast-moving.91- **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.9293Fold 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.94
141142Users can extend the bench ("add my own advisor"). Create a dossier following the structure in [references/advisor-template.md](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 to `.agents/advisors/<name>.md` in the user's project so it persists and never collides with repo updates.143