a11y-pass
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.
$ npx -y skills add Archive228/loopkit --skill kill-dead-code --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/kill-dead-codeContext preview
The summary Claude sees to decide when to auto-load this skill.
Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.
name: kill-dead-code description: Find and remove unreachable/unused code safely. Use during cleanup or before a refactor. when_to_use: cleanup, "remove unused", before refactoring, dead branches
1. **Prove it's dead** — no references (grep the symbol across the repo, including dynamic/string usage and tests). Unused export ≠ dead if it's a public API. 2. Check it's not feature-flagged off (dead today, alive when the flag flips). 3. Delete it AND its now-orphaned tests, imports, and config. 4. Run the full suite + a build. Dead code removal should change behavior in exactly zero ways. Bias to delete: every line someone has to read is a cost. But never delete what you can't prove is unreachable — say "I think X is unused, confirm?" instead of guessing.
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…