Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.
$npx -y skills add archive228/loopkit --skill active-memory-reminderInstalls into the current project.
Run `npx skills use "https://github.com/archive228/loopkit" --skill "archive228/loopkit/active-memory-reminder"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/archive228/loopkit" that are relevant to the current task. Run `npx skills add "https://github.com/archive228/loopkit"` and select the relevant skills, then follow their instructions.