Skills

The agent skills behind this site's tooling — what each one does, how it composes with the others, and which ones you can try live.

• concept-family-explorer

  Gap-discovery layer above /dr — maps a subject's full conceptual family (parent, siblings, children, adjacent fields, frontier), scores what's missing, and researches every worthwhile gap to saturation.

• rabbithole

  The narrow inverse of concept-family-explorer — takes one named concept and exhausts it completely, drilling down through mechanism, edge cases, and primary sources until a pass finds nothing new.

• /dr — deep-research

  Multi-source deep research using firecrawl and exa, synthesizing findings into cited reports with inline attribution, confidence ratings, and explicit knowledge gaps.

• skill-tree-architect

  Whole-tree architect for a skill library's hub-and-spoke taxonomy — audits description-cap headroom, hub balance, and cross-hub placement, then rebalances for a new family.

• full-suite

  Exhaustively covers a subject end to end — maps the full concept family, researches every worthwhile gap to saturation, and compiles per-concept plus rollup llms-family files with keyword and semantic indexes.

• llms-concept-abstractor

  Abstracts ONE concept out of any docset or document — a medical textbook's 'heart', 'indexing' across every database docset — into a source-anchored, deduped llms-family concept pack.

• llms-deep-optimizer

  Audits and rewrites any llms.txt, llms-full.txt, llms-small.txt, or llms-facts.txt until it passes a measurable bar, inside a multi-pass convergence loop with live probes.

• notes-to-llms-txt

  Turns disorganized notes — a scratch file, a run of meeting notes, a mixed-topic dump — into a well-formed llms.txt family, by segmenting, clustering by topic, and drafting a source-anchored entry per topic.