elon-musk
@rules/execution.md @references/frameworks.md
Elon Musk
Rebuild decisions from first principles instead of inheriting analogy-driven defaults. Organize results as a multi-file folder for future reference.
<when_to_use>
Use this skill when:
- the current options all look like slight variations of the same idea
- cost, structure, or strategy feels constrained by habit
- you need to separate real constraints from inherited assumptions
Do not use this skill when:
- the job is mostly factual research with no redesign
- the request is standard implementation planning
- the user needs startup validation scoring rather than assumption teardown
Boundary:
- if the main job is startup scoring and readiness assessment, use
startup-validator - if the main job is broad idea generation, use
genius-thinking
Examples:
/elon-musk SaaS pricing is crowded and undifferentiated
/elon-musk infrastructure cost is 40% of revenue
/elon-musk churn is high and retention playbooks are failing
</when_to_use>
<input_check>
If $ARGUMENTS is missing, ask:
Which problem should we deconstruct using first principles?
</input_check>
<owned_job>
For each run:
- Restate the problem and desired outcome.
- Gather facts only where the answer depends on current evidence.
- Classify assumptions using the A/B/C model from references/frameworks.md.
- Rebuild options from the surviving fundamentals.
- Stress-test the best path with inversion and pre-mortem.
</owned_job>
<document_shape>
Output Structure
.hypercore/elon-musk/[topic-slug]/
├── flow.json # phase tracking
├── research.md # domain research (conventions + facts + innovation cases)
├── assumptions.md # A/B/C matrix with Socratic questioning
├── redesign.md # rebuilt options from fundamentals + comparison table
└── execution.md # inversion + pre-mortem + action plan
- Use ASCII kebab-case for
[topic-slug](e.g.,saas-infra-cost). - Each phase produces its own file for organized reference.
flow.jsontracks progress through phases. Seereferences/flow-schema.mdfor the schema.- If the folder exists from a prior run, read existing files before updating.
</document_shape>
<flow_tracking>
Flow Tracking
Write flow.json at the start and update as each phase completes.
Phase progression
| Phase | Output file | Next |
|---|---|---|
research |
research.md — industry conventions, actual facts, innovation cases |
deconstruct |
deconstruct |
assumptions.md — A/B/C matrix with Socratic questioning |
redesign |
redesign |
redesign.md — rebuilt options + current vs first-principles comparison |
execute |
execute |
execution.md — inversion, pre-mortem, action sequence |
done |
Resume support
If flow.json already exists, read it and continue from the last incomplete phase. Do not restart completed phases.
</flow_tracking>
Workflow
| Phase | Task | Output file |
|---|---|---|
| 1 | Clarify the decision, gather domain research | research.md |
| 2 | Identify constraints, conventions, unknowns (A/B/C matrix) | assumptions.md |
| 3 | Rebuild alternatives from fundamentals | redesign.md |
| 4 | Stress-test the best path, recommend next actions | execution.md |
Research rule:
- if the problem depends on current facts, gather and cite them
- if the problem is conceptual, do not force web or team workflows
<output_contract>
Each output file should include:
research.md: industry conventions, actual data/benchmarks, innovation cases (with source URLs)assumptions.md: A/B/C matrix (A=physical constraints, B=conventions to eliminate, C=needs verification), Socratic questioning appliedredesign.md: current vs first-principles comparison table, 3-5 alternative paths with feasibility/impact scoresexecution.md: inversion failure scenarios (5-7), pre-mortem analysis, prioritized action sequence
</output_contract>
Before finishing, check:
- conventions are separated from true constraints
- unknowns that need evidence are labeled explicitly
- the recommendation does not depend on obsolete tool or model names
- inversion or pre-mortem was used to challenge the preferred path
- all output files are saved under
.hypercore/elon-musk/[topic-slug]/ flow.jsonstatus is set tocompleted
More from alpoxdev/hypercore
bug-fix
[Hyper] Analyze bugs, present repair options, then implement and verify the user-selected fix path. Routes simple bugs directly; tracks complex multi-phase investigations via .hypercore/bug-fix/ JSON flow.
47tanstack-start-architecture
[Hyper] Enforce TanStack Start architecture in existing Start projects, especially route structure, server functions, loader/client-server boundaries, importProtection, hooks, SSR/hydration, and hypercore conventions. Use before structural code changes, route work, server function work, or architecture audits in TanStack Start codebases.
45gemini
[Hyper] Use when the user wants to invoke Google Gemini CLI (`gemini`) for reasoning, research, or AI assistance. Trigger phrases: \"use gemini\", \"ask gemini\", \"run gemini\", \"call gemini\", \"gemini cli\", \"Google AI\", \"Gemini reasoning\", or when users request Google's Gemini models, research with web search, plan-mode review, or want to resume a previous Gemini session. Do not use for generic writing, runbook cleanup, or local edits that do not require the Gemini CLI.
45crawler
[Hyper] Investigate websites with Playwriter plus CDP to choose a crawl strategy, capture API/auth evidence, document findings under `.hypercore/crawler/[site]/`, and generate crawler code only after discovery is grounded.
45research
[Hyper] Produce a multi-source, source-backed markdown research report for fact-finding, comparisons, market/trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources. Use when synthesis and citations are needed, not for one-source lookups.
45genius-thinking
[Hyper] Generate and prioritize differentiated ideas for stuck product, strategy, or innovation problems when ordinary brainstorming is too shallow. Saves structured multi-file analysis under .hypercore/genius-thinking/[topic-slug]/ with phase tracking.
44