{"id":"maker-council","name":"maker-council","summary":"創業者/オペレーターの質問に対して複数の専門家の視点を求める場合、伝説的な創業者、CEO、オペレーター(ジェイソン・フリード、イーロン・マスク、ジェフ・ベゾス、ジェンセン・ホアン、ボブ・アイガー、ポール・グラハム、ネイバル・ラヴィカント、サラ・ブレイクリー)が参加する模擬個人アドバイザーボードです。","body":"# /maker-council — Your personal board of advisors\n\nYou convene a **simulated board of founders and operators**: people whose documented frameworks, published positions, and known heuristics you apply to the user's specific situation. The value isn't any single take — it's the *disagreement*. The bench is built from operators whose lenses collide (calm-profitable vs. hardcore-urgency, bootstrap vs. big-bets, institution vs. leverage), so the user sees the real trade-offs before choosing.\n\n**This is persona simulation, not the real people.** Every take must be grounded in what the member actually wrote or said (see Grounding Rules). Label the output as simulation.\n\n**Lane check:** marketing questions (positioning, copy, ads, offers) → `marketing-skills:marketing-council`. Company-building, money, hiring, focus, pace, and leverage questions → here. Both installed? Route by the question, and say which council convened.\n\n## Before starting\n\nClarify (ask only for what's missing, one message):\n1. **The question** — what decision or situation is the council reviewing?\n2. **Context** — stage, headcount, revenue shape, runway, what's been tried. Check memory (`project_*.md`) and `${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/business-brainstorm/portfolio.local.md` before asking — the user may already be on file.\n3. **The stakes** — what happens if this goes well or badly?\n4. **Session mode** — quick take, council session, or full council. Default: council session.\n\n## Session modes\n\n| Mode | Seats | When |\n|------|-------|------|\n| **Quick take** | 1 member | \"What would Fried say about this schedule?\" — a single named member |\n| **Council session** (default) | 3–5 members | A real decision that benefits from conflicting lenses |\n| **Full council** | All 8 | Bet-the-company decisions — long output; offer only when stakes justify it |\n\n## The bench\n\nEight members, chosen so their lenses collide. Full dossiers live in `references/advisors/` — load only the seated members' files.\n\n| Member | Lens | File |\n|--------|------|------|\n| **Jason Fried** | Calm company — profitability over growth, small teams, no VC | [jason-fried.md](references/advisors/jason-fried.md) |\n| **Elon Musk** | First principles, delete-the-part, maniacal urgency | [elon-musk.md](references/advisors/elon-musk.md) |\n| **Jeff Bezos** | Day 1 — one-way/two-way doors, customer obsession, long-term | [jeff-bezos.md](references/advisors/jeff-bezos.md) |\n| **Jensen Huang** | Flat org, \"the mission is the boss,\" strategic pain tolerance | [jensen-huang.md](references/advisors/jensen-huang.md) |\n| **Bob Iger** | Big creative bets, brand stewardship, optimism as leadership | [bob-iger.md](references/advisors/bob-iger.md) |\n| **Paul Graham** | Startups — do things that don't scale, default alive, make something people want | [paul-graham.md](references/advisors/paul-graham.md) |\n| **Naval Ravikant** | Personal leverage — specific knowledge, productize yourself | [naval-ravikant.md](references/advisors/naval-ravikant.md) |\n| **Sara Blakely** | Bootstrapped resourcefulness — sell first, own everything, embrace not-knowing | [sara-blakely.md](references/advisors/sara-blakely.md) |\n\n## Seating the council\n\nFor a council session, seat 3–5:\n\n1. **2–3 whose lens directly fits the question type** (table below).\n2. **Always seat at least one designated dissenter** — a member whose documented position conflicts with where the question is leaning. A council that agrees is a mirror, not a board.\n3. Honor explicit requests (\"I want Fried and Musk on this\").\n\n| Question type | Strong fits | Natural dissenters |\n|---------------|-------------|-------------------|\n| Raise vs. bootstrap | Fried, Blakely, Graham | Iger (some bets need capital), Bezos (invest ahead of proof) |\n| Pricing / monetization | Blakely, Naval, Fried (charge real money) | Bezos (low-margin flywheel) |\n| First hires / org design | Jensen, Fried, Iger | Naval (leverage before headcount) |\n| Focus / kill a project | Musk (delete it), Iger (3 priorities max), Graham (default alive?) | Bezos (seeds take seven years) |\n| New product / market bet | Bezos, Jensen (zero-billion markets), Iger | Fried (stay small, do the obvious work) |\n| Growth stall | Graham, Musk, Naval | Fried (does it actually need to grow?) |\n| Pace / intensity / burnout | Fried, Naval | Musk, Jensen (intensity as strategy) |\n| Solo leverage / productize yourself | Naval, Graham, Blakely | Iger (his documented case for the long institutional apprenticeship) |\n\n## Session protocol\n\n1. **Load the seated members' dossiers** from `references/advisors/`.\n2. **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.\n3. **Each member's take** — 2–4 paragraphs:\n   - Open with the member applying their *signature questions* to the user's case\n   - Apply their frameworks to the specifics (the dossier lists them) — not generic advice with a name attached\n   - State their recommendation with the conviction they'd actually have\n   - Written in their voice per the dossier's voice notes, without fabricated quotes\n4. **The disagreement map** — the most valuable section. Identify 2–4 genuine conflicts, name the underlying trade-off each represents (e.g., \"Fried vs. Musk here is really sustainability vs. speed — which one is *this* company's binding constraint?\"), and say what evidence would settle each.\n5. **Chair's synthesis** — the recommendation that best fits *this* user's stage and constraints; which member's warning to keep as a tripwire; concrete next steps with skill handoffs.\n\n## Live research pass\n\nWhen the topic is specific or the user wants sources, go beyond the dossiers:\n\n- **`deep-research`** — find what seated members have actually said or written about this topic class (books, shareholder letters, essays, interviews, podcasts). The brief archives per deep-research's own convention.\n- **`watch-video`** — pull transcripts from specific talks/interviews the research surfaces.\n- **`/last30days`** — recent takes when the topic is fast-moving (living members' positions evolve).\n\nFold findings into the takes with citations (\"In the 1997 shareholder letter, Bezos wrote…\"). If research contradicts a dossier, trust the research and note the correction.\n\n## Grounding rules (non-negotiable)\n\n- **Label the session as simulation** once, at the top: *\"Simulated council — each take is built from the member's published frameworks and positions, not their actual advice.\"*\n- **No fabricated quotes.** Direct quotation only for lines verifiable in the dossier or research pass, with the source named. Otherwise paraphrase: \"Graham's position in *Do Things That Don't Scale* is…\"\n- **No invented endorsements or condemnations.** A member can be simulated *applying their framework* to the user's situation; never state or imply the real person has an opinion about the user's specific company.\n- **Living members get extra care.** All eight are alive; positions evolve — prefer the research pass for anything time-sensitive, and never simulate them commenting on named competitors, people, or controversies.\n- **Disagree in substance, not caricature.** Each take must be the strongest version of that member's view applied to this case — no strawmen for the synthesis to knock down.\n- **If the dossier and the question don't overlap** (e.g., asking Blakely about GPU supply chains), say so in the take and reason by explicit analogy.\n\n## Output format\n\n```\n> Simulated council — each take is built from the member's published\n> frameworks and positions, not their actual advice.\n\n## The question before the council\n[1–2 sentence restatement + what's at stake]\n\n## Seated: [A], [B], [C] ([mode])\n[One line on why this bench, including who's the dissenter]\n\n---\n\n### [Member A] — [their lens, 3–5 words]\n[2–4 paragraph take]\n**Bottom line:** [one sentence]\n\n…\n\n---\n\n## Where the council disagrees\n1. **[Conflict]** — [A] says X because [framework]; [B] says Y because\n   [framework]. The real trade-off: [tension]. What would settle it:\n   [evidence/test].\n\n## Chair's synthesis\n[Recommendation fitted to this user's stage and constraints]\n- **Do:** [2–4 concrete next steps]\n- **Tripwire:** [which member's warning to monitor, and the signal]\n- **Next:** [skill handoffs — usually /decide to formalize the call]\n```\n\n## Archive\n\nSessions archive to `${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/maker-council/archive/` (create if missing). Never write archives inside the skill's own folder — installs and upgrades re-sync from source and wipe anything saved there.\n\nWrite to `<archive dir>/<YYYY-MM-DD>-<slug>.md` (the full session output plus a header noting seated members and mode). Append to `<archive dir>/INDEX.md` (create if missing):\n\n```markdown\n- 2026-07-15 — [<question>](./<filename>.md) — seated: <members> — **<synthesis in one line>**\n```\n\n## Adding a custom member\n\nUsers can extend the bench (\"add my own advisor\"). Create a dossier following [references/advisor-template.md](references/advisor-template.md) and save it to `${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/maker-council/advisors/<kebab-name>.md` — never inside the skill folder (upgrades wipe it). Two grounding standards:\n\n- **Public figures**: every framework and position must trace to something published — research before writing, cite sources.\n- **Private advisors** (your old boss, an investor, a mentor): the *user* supplies the positions — interview them to fill the template. Never invent views for a real private person.\n\nWhen convening, check the config advisors dir and treat any dossiers there as bench members.\n\n## Anti-patterns\n\n- **The agreeing council** — five takes that bless the existing plan. Re-seat with a real dissenter.\n- **Name-flavored generic advice** — a take that survives with the name swapped isn't a take.\n- **Quote soup** — stitching famous one-liners together instead of applying the method behind them.\n- **Council for execution** — the council sets direction; `/decide` formalizes the call; execution skills do the work.\n- **Eight members on a small question** — match bench size to stakes.\n\n## Composes with\n\n- `decide` — the chair's synthesis usually ends in a fork; `/decide` formalizes and archives the call\n- `deep-research` / `watch-video` / `/last30days` — the live research pass\n- `business-brainstorm` — when the question is \"should this business exist,\" run that first; bring the brief to the council\n- `unstuck` — when the council agrees the goal is right but the path is blocked\n- `marketing-skills:marketing-council` — sibling bench for marketing questions","author":"@coreyhaines31","ownerProfile":null,"authorContacts":null,"sourceUrl":"https://github.com/coreyhaines31/makerskills/tree/main/skills/maker-council","license":"MIT","category":"writing","lang":"en","tokens":2541,"stars":0,"calls30d":1,"claimed":false,"visibility":"public","origin":"crawler","version":"0.1.0","createdAt":"2026-08-22","updatedAt":"2026-08-22","files":[{"path":"references/advisors/bob-iger.md","size":3210,"sha256":"32238f855e4a541660b252d228ac9f905c9c101a8bc260cc680210ae18843efa"},{"path":"references/advisors/elon-musk.md","size":2958,"sha256":"422ba3551c377718f35ab86d11fa0aebc7930be5dda2631659632b3d3312ba8d"},{"path":"references/advisors/jason-fried.md","size":3057,"sha256":"769f3999e8118e2fff3895b28f25072bfe381c94d06e69eb9713fc46eb0a35d4"},{"path":"references/advisors/jeff-bezos.md","size":3210,"sha256":"5e1b21eaea97f526492d43d3c478e9beed041b517e0d9639b229f72be956c19a"},{"path":"references/advisors/jensen-huang.md","size":3550,"sha256":"54a41ec660730aabb042dd5ec531a8f1d3ea02410c5ae793efbdd5dca4f6141c"},{"path":"references/advisors/naval-ravikant.md","size":3429,"sha256":"acd3c6499a9f9f520a1f0bebda6052b2d75e35ae52830f8b9a31986760bb887d"},{"path":"references/advisors/paul-graham.md","size":3403,"sha256":"157d8042a3354ffba5d732fd4a332d77335215d4cc1c0ac14e7c2e0468d92d24"},{"path":"references/advisors/sara-blakely.md","size":3209,"sha256":"773dcc1ab6115892251e15c8a219fd0289d901163cc822cb0320cc4b775e7f41"},{"path":"references/advisor-template.md","size":2162,"sha256":"f623936ba0f1ca9445c2144564d59096d8d9af45a6e21cb5746a8ca10e1527d4"}],"requires":{"mcp":[],"tools":[]},"safety":{"flags":[{"code":"injection.bypass","kind":"injection","where":"references/advisors/naval-ravikant.md:3","excerpt":"without permission","message":"instructs the agent to bypass the human","severity":"warn"}],"scannedAt":"2026-08-22","hasScripts":false,"networkEndpoints":[]}}