Agent skill

Maker Council

by coreyhaines31 in coreyhaines31/makerskills

When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant…

MITAuto-check passedResearch & Science

Install Maker Council

skills CLI
$ npx skills add coreyhaines31/makerskills --skill maker-council -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install coreyhaines31/makerskills maker-council --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/coreyhaines31/makerskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/maker-council .claude/skills/maker-council && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
maker-council
GitHub stars
851
Token cost
~2.9k tokens
SKILL.md length
1,234 words
Files
10 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant…

  • Works in 4 steps: The question — what decision or… → Context — stage, headcount, revenue… → The stakes — what happens if this goes… → …
  • Board of advisors
  • SKILL.md covers Before starting, Session modes, The bench and Seating the council, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Maker Council is an agent skill from coreyhaines31/makerskills. When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant, Sara Blakely). Bring a real decision — "should I raise prices?", "hire my first employee?", "raise or bootstrap?", "kill this project?" — and the council weighs in through documented frameworks, surfaces disagreements, and synthesizes a recommendation. Also use for 'maker council,' 'board of advisors,' 'what would Bezos…

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `references/advisor-template.md`, `references/advisors/bob-iger.md` and `references/advisors/elon-musk.md`).

It sits in Research & Science, covering Deep research. The repository describes itself as: AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude… The licence is MIT.

When your agent uses it

  • Board of advisors
  • What would Bezos do
  • What would Jason Fried say
  • Ask the council

Example prompts

  • “should I raise prices?”
  • “hire my first employee?”
  • “raise or bootstrap?”
  • “/maker-council”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. The question — what decision or situation is the council reviewing?
  2. Context — stage, headcount, revenue shape, runway, what's been tried. Check memory (project_*.md) and…
  3. The stakes — what happens if this goes well or badly?
  4. Session mode — quick take, council session, or full council. Default: council session.

What it can do on your machine

Read from SKILL.md and the folder at commit cc31579. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maker Council loads about 2.9k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 223 tokens; SKILL.md has 1,234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~223
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from coreyhaines31/makerskills at commit cc31579, republished under its MIT licence (© coreyhaines31). 1,234 words, ~2,908 tokens.

Download SKILL.mdSave it as .claude/skills/maker-council/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
maker-council
description
When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant, Sara Blakely). Bring a real decision — "should I raise prices?", "hire my first employee?", "raise or bootstrap?", "kill this project?" — and the council weighs in through documented frameworks, surfaces disagreements, and synthesizes a recommendation. Also use for 'maker council,' 'board of advisors,' 'what would Bezos do,' 'what would Jason Fried say,' 'channel Naval,' 'ask the council,' or how a famous founder would approach a problem. Optional live-research pass via deep-research / watch-video / last30days. Marketing questions go to marketing-skills' marketing-council. Archives to ~/.config/makerskills/maker-council/archive/. To commit to a direction, hand off to decide.
metadata.version
0.1.1

/maker-council — Your personal board of advisors

You 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.

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.

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.

Before starting

Clarify (ask only for what's missing, one message):

  1. The question — what decision or situation is the council reviewing?
  2. 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.
  3. The stakes — what happens if this goes well or badly?
  4. Session mode — quick take, council session, or full council. Default: council session.

Session modes

ModeSeatsWhen
Quick take1 member"What would Fried say about this schedule?" — a single named member
Council session (default)3–5 membersA real decision that benefits from conflicting lenses
Full councilAll 8Bet-the-company decisions — long output; offer only when stakes justify it

The bench

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

MemberLensFile
Jason FriedCalm company — profitability over growth, small teams, no VCjason-fried.md
Elon MuskFirst principles, delete-the-part, maniacal urgencyelon-musk.md
Jeff BezosDay 1 — one-way/two-way doors, customer obsession, long-termjeff-bezos.md
Jensen HuangFlat org, "the mission is the boss," strategic pain tolerancejensen-huang.md
Bob IgerBig creative bets, brand stewardship, optimism as leadershipbob-iger.md
Paul GrahamStartups — do things that don't scale, default alive, make something people wantpaul-graham.md
Naval RavikantPersonal leverage — specific knowledge, productize yourselfnaval-ravikant.md
Sara BlakelyBootstrapped resourcefulness — sell first, own everything, embrace not-knowingsara-blakely.md

Seating the council

For a council session, seat 3–5:

  1. 2–3 whose lens directly fits the question type (table below).
  2. 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.
  3. Honor explicit requests ("I want Fried and Musk on this").
Question typeStrong fitsNatural dissenters
Raise vs. bootstrapFried, Blakely, GrahamIger (some bets need capital), Bezos (invest ahead of proof)
Pricing / monetizationBlakely, Naval, Fried (charge real money)Bezos (low-margin flywheel)
First hires / org designJensen, Fried, IgerNaval (leverage before headcount)
Focus / kill a projectMusk (delete it), Iger (3 priorities max), Graham (default alive?)Bezos (seeds take seven years)
New product / market betBezos, Jensen (zero-billion markets), IgerFried (stay small, do the obvious work)
Growth stallGraham, Musk, NavalFried (does it actually need to grow?)
Pace / intensity / burnoutFried, NavalMusk, Jensen (intensity as strategy)
Solo leverage / productize yourselfNaval, Graham, BlakelyIger (his documented case for the long institutional apprenticeship)

Session protocol

  1. Load the seated members' 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 member's take — 2–4 paragraphs:
    • Open with the member applying their signature questions to the user's case
    • Apply their frameworks to the specifics (the 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, 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.
  5. 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.

Live research pass

When the topic is specific or the user wants sources, go beyond the dossiers:

  • 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.
  • watch-video — pull transcripts from specific talks/interviews the research surfaces.
  • /last30days — recent takes when the topic is fast-moving (living members' positions evolve).

Fold 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.

Show full SKILL.md (450 more words)Show less

Grounding rules (non-negotiable)

  • 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."
  • 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…"
  • 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.
  • 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.
  • 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.
  • 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.

Output format

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

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

## Seated: [A], [B], [C] ([mode])
[One line on why this bench, including who's the dissenter]

---

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

…

---

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

## Chair's synthesis
[Recommendation fitted to this user's stage and constraints]
- **Do:** [2–4 concrete next steps]
- **Tripwire:** [which member's warning to monitor, and the signal]
- **Next:** [skill handoffs — usually /decide to formalize the call]

Archive

Sessions 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.

Write 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):

markdown
- 2026-07-15 — [<question>](./<filename>.md) — seated: <members> — **<synthesis in one line>**

Adding a custom member

Users can extend the bench ("add my own advisor"). Create a dossier following 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:

  • Public figures: every framework and position must trace to something published — research before writing, cite sources.
  • 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.

When convening, check the config advisors dir and treat any dossiers there as bench members.

Anti-patterns

  • The agreeing council — five takes that bless the existing plan. Re-seat with a real dissenter.
  • Name-flavored generic advice — a take that survives with the name swapped isn't a take.
  • Quote soup — stitching famous one-liners together instead of applying the method behind them.
  • Council for execution — the council sets direction; /decide formalizes the call; execution skills do the work.
  • Eight members on a small question — match bench size to stakes.

Composes with

  • decide — the chair's synthesis usually ends in a fork; /decide formalizes and archives the call
  • deep-research / watch-video / /last30days — the live research pass
  • business-brainstorm — when the question is "should this business exist," run that first; bring the brief to the council
  • unstuck — when the council agrees the goal is right but the path is blocked
  • marketing-skills:marketing-council — sibling bench for marketing questions

© coreyhaines31, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in skills/maker-council of coreyhaines31/makerskills.

  • SKILL.md
  • references/advisor-template.md
  • references/advisors/bob-iger.md
  • references/advisors/elon-musk.md
  • references/advisors/jason-fried.md
  • references/advisors/jeff-bezos.md
  • references/advisors/jensen-huang.md
  • references/advisors/naval-ravikant.md
  • references/advisors/paul-graham.md
  • references/advisors/sara-blakely.md

Open the folder on GitHubat commit cc31579

Compare with similar skills

Maker Council next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maker Council compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maker Council this skillcoreyhaines31/makerskills851—~2.9kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Deep Research WorkflowTokenRhythm/opensquilla7.1k—~1.3kAutomated safety check: PassApache-2.0
Deep Researchsanjay3290/ai-skills4329 repos~683Automated safety check: NotesApache-2.0
Horizontal-Vertical Deep ResearchKKKKhazix/khazix-skills21k—~2.1kAutomated safety check: PassMIT
Academic Research PipelineImbad0202/academic-research-skills51k—~15kAutomated safety check: PassCustom licence

Similar skills

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Deep Research Workflow

    TokenRhythm/opensquilla

    Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.

    7.1k GitHub stars~1.3k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Deep Research

    sanjay3290/ai-skills

    Execute autonomous multi-step research using Google Gemini Deep Research Agent.

    432 GitHub starsUsed in 9 repos~683 tokens
    Research & ScienceAuto-check: notes
  • Horizontal-Vertical Deep Research

    KKKKhazix/khazix-skills

    Runs a two-axis deep research method on a product, company, concept or person: its full history over time, compared with peers today, delivered as a typeset PDF report.

    21k GitHub stars~2.1k tokensUpdated 10 days ago
    Research & ScienceAuto-check passed
  • Academic Research Pipeline

    Imbad0202/academic-research-skills

    Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.

    51k GitHub stars~15k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Academic Research Suite for Codex

    Imbad0202/academic-research-skills-codex

    A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.

    12k GitHub stars~12k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed

More from coreyhaines31/makerskills

All 21 skills in this repo
  • Business Brainstorm

    coreyhaines31/makerskills

    When you want to pressure-test a potential new business, product, or side project against the serial-founder filter.

    851 GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed
  • Company Brain

    coreyhaines31/makerskills

    Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf.

    851 GitHub stars~4.9k tokensUpdated 2 days ago
    Auto-check passed
  • Company Cfo

    coreyhaines31/makerskills

    Monthly CFO workflow for a company or agency — pull raw data from bank + payment processor + payroll + expense management, categorize and reconcile, compute end-of-month cash via transaction-sum…

    851 GitHub stars~4k tokensUpdated 2 days ago
    Auto-check: notes
  • Decide

    coreyhaines31/makerskills

    When you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them, reaches a call (or "wait"), and archives the rationale for future reference.

    851 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed
  • Ingest

    coreyhaines31/makerskills

    When you paste raw human input — a call transcript (Grain, Zoom, Granola, Fathom), a text or email from a client/partner/friend, a voice-memo dump, or meeting notes — and want it converted into…

    851 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Paste

    coreyhaines31/makerskills

    When you want to clean and reformat content (usually from your terminal) for pasting into Slack, Notion, Twitter/X, LinkedIn, email, GitHub, or plain text.

    851 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check: notes

Questions about Maker Council

What does Maker Council do?

When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant…. Maker Council is an agent skill from coreyhaines31/makerskills. When you want multiple expert perspectives on a founder/operator question — a simulated board of advisors (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham, Naval Ravikant, Sara Blakely).

When should I use Maker Council?

Maker Council fits situations like: board of advisors; what would Bezos do; what would Jason Fried say; ask the council.

How do I install Maker Council in Claude Code?

Run `npx skills add coreyhaines31/makerskills --skill maker-council -a claude-code`. Or copy the skill folder (skills/maker-council in coreyhaines31/makerskills) into .claude/skills/maker-council in your project. Claude Code loads it when a task matches its description.

How do I install Maker Council in Codex?

Run `npx skills add coreyhaines31/makerskills --skill maker-council -a codex`. Or copy the skill folder (skills/maker-council in coreyhaines31/makerskills) into .agents/skills/maker-council in your project. Codex loads it when a task matches its description.

Can I use Maker Council in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add coreyhaines31/makerskills --skill maker-council -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maker-council, .gemini/skills/maker-council, .github/skills/maker-council and .opencode/skills/maker-council in your project.

What does Maker Council need to run?

SKILL.md names no scripts, command-line tools or credentials: Maker Council is instructions for the agent only.

Does Maker Council access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Maker Council safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maker Council use?

Maker Council is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maker Council use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7k tokens, read only when the agent opens those files.

What are the alternatives to Maker Council?

Skills that share tags, products or a category with Maker Council: GitHub Deep Research (bytedance/deer-flow, 84k stars), Deep Research Workflow (TokenRhythm/opensquilla, 7.1k stars), Deep Research (sanjay3290/ai-skills, 432 stars) and Horizontal-Vertical Deep Research (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maker Council?

coreyhaines31 (a GitHub user) maintains it in coreyhaines31/makerskills, which has 851 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.

Source: coreyhaines31/makerskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.