ScalarView
Think at the right altitude.
We are living in fast times with slow minds. Most failures of understanding are failures of scale: people work hard at the wrong order of magnitude, polishing sentences while the thesis collapses, executing daily tasks severed from the reason the work exists, attaching civilizational stakes to a single anecdote.
A scale-literacy protocol
ScalarView treats scale as an epistemic dimension, not a visual metaphor. Every idea belongs at one of seven discrete levels, from concrete evidence at the bottom to universal stakes at the top. Moving down demands specificity. Moving up demands implication. Jumping levels without support gets flagged.
- +3Universal or civilizational stakes
- +2Whole-project thesis
- +1Current phase
- 0Present working focus
- -1Structural components
- -2Claims, mechanisms, causes
- -3Evidence: quote, data, source
It is free, open, and written in plain markdown. It runs anywhere instructions run.
Five behaviors
Installed as an agent skill, ScalarView does the opposite of most skills. It makes the agent withhold premature answers and run disciplined protocol on your thinking, one rung at a time.
- SCALAR LADDER
Place any idea at its level. Do not collapse scales.
- 5 WHYS DOWN
Root-cause descent with Toyota's discipline: no blame, no vague causes, every link tested backward with "therefore."
- 5 SO-WHATS UP
Implication ascent, introduced here. Ask "So what?" five times, rejecting money, metrics, and vanity as stopping points, until the stakes are proportionate, grounded, or exposed as fake.
- SCALE AUDIT
Feed it a draft, memo, pitch, or plan. Get back a ladder map flagging every unmarked jump: anecdote to civilization, feature to destiny, metric to meaning.
- PROPORTIONALITY CHECK
Two questions, always: are the stakes too big for the evidence? Is the action too small for the ambition?
Run it now
Works with any agent that supports the open SKILL.md format: Claude, Claude Code, Codex, Cursor, Gemini CLI, and others.
mkdir -p ~/.claude/skills/scalarview curl -o ~/.claude/skills/scalarview/SKILL.md \ https://raw.githubusercontent.com/justinneuman-coder/scalarview/main/SKILL.md
On Claude.ai: Settings > Capabilities > Skills > upload the skill folder. On anything else: paste SKILL.md into your custom instructions. Then just talk: "Run 5 So-Whats on this." "Scale-audit my draft." "Does this even matter?"
The instrument: FractalView
The protocol pairs with a free app built on the same ladder. Local-first and deliberately without AI: your work stays on your device, and nothing is mined, ranked, or trained on. It is the version of this practice that belongs in classrooms and other places where AI doesn't.
Where this comes from
The 5 Whys belongs to Taiichi Ohno and the Toyota Production System. The 5 So-Whats is its upward counterpart, introduced by this protocol. The Sierpinski mark honors David Foster Wallace, who described structuring Infinite Jest as a Sierpinski gasket: the same pattern of meaning recurring at every scale.
Cite it
Neuman, Justin. "ScalarView: A Scale-Literacy Protocol," v1.0 (2026). fractalview.app
Licensed CC BY 4.0. Use it, fork it, teach it, ship it inside your own tools. Keep the attribution. Attribution is the whole ask.