From armor
Reviews diffs and PRs for cleverness, fashion-driven choices, premature abstraction, and author-serving indirection. Asks whether each choice serves the reader or the author's ego.
How this skill is triggered — by the user, by Claude, or both
Slash command
/armor:ego-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ego-driven design never produces something humane. The
Ego-driven design never produces something humane. The designer who builds to look good builds for himself, not the user. The same trap sits in code. Code is not where you prove you are clever. It is where you serve the next person who has to read it.
This lens reads a diff with one question: who does this serve?
For each non-obvious choice in the diff, ask who it serves — the next maintainer, the caller, the on-call engineer — or the author's self-image.
Flags:
For each flag, ask: would this survive the author explaining it to the person who maintains it next year?
"I did it because it is elegant" is not a reason. "I did it because the old way broke here, and here is the bug" is a reason.
Not "is this good code." Ask "is this kind to the next person." Kind code is boring on purpose. It does the obvious thing in the obvious place.
| Location | What | Who it serves | Simpler alternative |
|---|
Keep it specific. Point at lines. Offer the simpler version, do not just name the sin.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub markacianfrani/armor --plugin armor