When any quantitative claim changes (f_NL number, σ, anomaly count, MCMC sample count, redshift, etc), grep every .tex AND every HTML/TSX page in the repo for the old value, replace with new in one atomic commit. Zero stale instances allowed. Claims-table on…
Mirror a compiled paper PDF to every hosting path: public/papers/ (legacy static site) and site/public/ (Next.js site). Both must serve the same PDF. If only one is updated, one of the two site surfaces shows the stale PDF.
Bigbounce-specific specialization of /revision-tracker-update. Binds the schema to project-context/peer-reviews/REVISION_TRACKER.md and to the 6-paper layout (P1A, P1B, P2, P3, P4, P5). Same workflow as the global skill but tied to this repo's file paths.
Dual sync of bigbounce HTML pages (index.html, paper.html, activity.html, data-explorer.html, explained.html, glossary.html, figures.html, etc.) AND the Next.js site/ subdirectory. Both must update in same commit as SSOT — never as follow-up. Site staleness…
Bump paper version atomically: \paperVersion + \paperTimestamp + \date{} in the .tex + version.json at repo root. Semver rules: patch=minor edits, minor=substantive section adds, major=restructure. All 4 items in same commit. pypdf-verify page 1 reflects new…