FluencyLoop safety net. Reconstruct journal entries for work that shipped without going through the loop — reads a merged diff, drafts a feature + session with decision blocks, renders a fluency briefing that maps each decision onto the design diagrams, then confirms them with the human one decision at a time. Marks every entry trust: ⚠ unverified until confirmed. Use post-merge, or when the user says "fluencyloop backfill", "document this PR after the fact", or "we skipped the loop on this one".
$npx -y skills add baokhang83/fluencyloop --skill backfillInstalls into the current project.
Run `npx skills use "https://github.com/baokhang83/fluencyloop" --skill "baokhang83/fluencyloop/backfill"` 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/baokhang83/fluencyloop" that are relevant to the current task. Run `npx skills add "https://github.com/baokhang83/fluencyloop"` and select the relevant skills, then follow their instructions.