Elonize
Armor for coding agents: a playbook of Claude Code skills that make an agent prove its work, not describe it.
npx -y skills add yiyaw-lab/agent-armor --skill elonizeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Alias for /raze — apply Elon's principles (Musk's Algorithm: question requirements → delete → simplify → accelerate → automate; idiot index; the best part is no part). The razor (delete to the simplest sufficient form) is the core move; this is the growing basket of those first-principles rules. Modes: <target> (scan+propose) | audit | apply.
SKILL.md
1.2 KB, as published. Nobody here has run it
Alias for /raze. Follow ~/.claude/commands/raze.md exactly — same modes (<target> | audit | apply), same propose-on-approval + ≥80-unused-confidence gate + per-cut tests-green + hard refuse-list safety, same two-sided add-back-rate metric.
Why two names: raze is the verb — apply the razor, raze the unnecessary to the simplest sufficient form (self-documenting: a cold reader infers the method). elonize is the basket — the razor is ONE of Elon's principles; as more get encoded (idiot index, best-part-is-no-part, first-principles requirement teardown, the accelerate/automate ordering), they accrue under this name. Use whichever reads truer in the moment; they run the identical procedure today.