a11y-pass
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.
$ npx -y skills add Archive228/loopkit --skill revert-surgical --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/revert-surgicalContext preview
The summary Claude sees to decide when to auto-load this skill.
Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.
name: revert-surgical description: Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something. when_to_use: "revert this", a bad deploy, one commit broke prod, undo without losing other work
Don't `git reset --hard` away three good commits to undo one bad one.
On a shared branch, always revert (forward), never rewrite history. Reproduce the breakage first so you revert the RIGHT thing, then verify the revert actually fixes it.
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt…
Review a diff against the goal spec assuming the code is BROKEN. The reviewer
Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything…