Plugin
loopkit
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
53 skills755
@archive22833 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
@archive228Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
@archive228Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt…
@archive228Review a diff against the goal spec assuming the code is BROKEN. The reviewer
@archive228Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
@archive228Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
@archive228Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything…
@archive228Reviews a diff against the goal spec assuming the code is broken. Invoke after every code change.
@archive228Draft suggested next features into feature_list.suggestions.json (separate from feature_list.json)
@archive228Run the batch quality pass over the current diff — simplify → reduce-nesting → kill-dead-code → a11y-pass →…
@archive228Write the goal spec (PROMPT.md) before implementing. Loads the loopkit spec-first skill.
@archive228Run adversarial verification on the current diff before claiming done. Loads the loopkit adversarial-verify skill and dispatches…
@archive228© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic