Knowledge distillation methodology: candidate extraction, confidence scoring, tier routing, conversation-scoped mode. TRIGGER when: running /learn or /distill, deciding if an insight is memory-worthy, or scoring a knowledge candidate. SKIP: ad-hoc memory reads/writes (use agent-memory); vector storage (use semantic-memory-store).
$npx -y skills add komluk/scaffolding --skill distillInstalls into the current project.
Run `npx skills use "https://github.com/komluk/scaffolding" --skill "komluk/scaffolding/distill"` 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/komluk/scaffolding" that are relevant to the current task. Run `npx skills add "https://github.com/komluk/scaffolding"` and select the relevant skills, then follow their instructions.