Use when (re)indexing a Sweet Search project. Runs the full-profile indexer with GPU model prewarming (CoreML cascade on M3+, candle Metal on M1/M2, ORT CPU elsewhere), kills ORT CPU models during indexing to avoid memory contention, and rewarms them for query readiness on completion. Incremental runs under 20 files stay on ORT CPU.
$npx -y skills add mrsladoje/sweet-search --skill sweet-indexInstalls into the current project.
Run `npx skills use "https://github.com/mrsladoje/sweet-search" --skill "mrsladoje/sweet-search/sweet-index"` 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/mrsladoje/sweet-search" that are relevant to the current task. Run `npx skills add "https://github.com/mrsladoje/sweet-search"` and select the relevant skills, then follow their instructions.