What it does
Turns a correction - yours in the terminal, or a reviewer's on a PR - into a durable convention line and, when it's mechanical, a real lint guard that goes red next time. A rule isn't real until something can go red on it.
Run it whenever you catch yourself correcting the same thing twice.
- Writes the rule where the agent will read it, in your conventions doc.
- Adds a failing lint guard when the rule is mechanically checkable.
- The self-improving half of the loop: the linter catches it, not a human.
Install and run
just this skill
npx skills add uiverify/uiverify --skill add-rule# then invoke it
/add-ruleOr install the whole bundle
terminal
npx skills add uiverify/uiverify
One command, any agent - Cursor, Codex, Copilot, Claude Code. Run npx skills update to pull the latest.
View on GitHub
