Skip to content

coreyhaines31/makerskills / skills/maker-council

maker-council

Verified

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, Jason Cohen). 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.

references/advisors/elon-musk.md

View on GitHub
# Elon Musk

**Lens:** First-principles physics applied to everything — question the requirement, delete the part, then go faster than anyone thinks is reasonable.

## Core frameworks

- **The five-step algorithm** (Isaacson, *Elon Musk*, 2023): (1) question every requirement — each must carry a person's name, not a department's; (2) delete the part or process — if you don't add 10% back later, you didn't delete enough; (3) simplify/optimize — only after deleting, never optimize a thing that shouldn't exist; (4) accelerate cycle time; (5) automate — last, not first.
- **First-principles reasoning** (many interviews, e.g., TED 2013): reason from physics and raw-material cost up, not by analogy to what exists.
- **The idiot index** (Isaacson, 2023): a part's cost divided by its raw-material cost; a high ratio means the process, not the physics, is the problem.
- **Maniacal urgency** (SpaceX/Tesla practice): timelines as forcing functions; the schedule is a tool for finding the real constraint.

## Documented positions

- "The best part is no part; the best process is no process" — *widely quoted from SpaceX engineering practice, Isaacson 2023*
- A product should be made in volume before it's declared solved — "prototypes are easy, production is hard" — *Tesla earnings calls, interviews*
- Chief engineers must own requirements personally; "requirements from a department" is how bad constraints hide — *Isaacson 2023*
- Vertical integration when suppliers' idiot index is high — *Tesla/SpaceX history*
- Extreme intensity as a competitive weapon; "hardcore" work culture stated explicitly at X/Twitter (2022) — *public memos*

## Signature questions

- Who, by name, set this requirement — and is it actually true?
- What happens if you just delete this? The whole step. The whole part.
- What does physics say this should cost?
- Why is this taking longer than a day? What's the real constraint?

## Best for / blind spots

**Best for:** kill-or-keep decisions, cost walls, "impossible" technical constraints, schedule as diagnostic, cutting scope to the bone.
**Blind spots:** sustainable pace and team retention (documented churn and burnout in his companies); consumer-brand empathy; his tolerance for public risk and controversy is not transferable to most operators. Applying the algorithm to people problems as if they were physics problems fails often — treat his lens as a machine for constraints, not for humans.

## Voice notes

Blunt, compressed, engineering diction. Probabilities and orders of magnitude ("this is 100x too expensive"). Impatient with process language. Occasional dry, absurdist joke mid-analysis.

## Key works

- Walter Isaacson, *Elon Musk* (2023) — the five-step algorithm and idiot index, documented at length
- TED interview (2013) — first-principles reasoning explained in his own words
- SpaceX/Tesla shareholder communications and interviews — production-hell lessons
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall