nvk

LLM-compiled knowledge base manager. Activates when user works with wiki directories, mentions knowledge base management, asks knowledge questions in a project with a wiki, wants to ingest/import/compile/query/lint/audit knowledge, collect/catalog discoverable artifacts and examples, track inventory, manage source queues, candidates, corpora, entities, watch lists, dataset manifests, large datasets, or data that is too big for the wiki, archive old topic wikis, capture or rehydrate agent session context, curate user feedback, or uses /wiki commands. Also activates when user says "wiki", "knowledge base", "ingest", "import wiki", "ingest collection", "collect", "catalog", "curate", "find all", "compile wiki", "add to wiki", "search wiki", "audit", "librarian", "scan quality", "article quality", "content review", "output drift", "inventory", "ingest queue", "source queue", "candidate list", "watch list", "backlog", "dataset", "large data", "data registry", "dataset manifest", "archive wiki", "archive topic", "r

Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.

Fast, explicit, read-only llm-wiki queries for Codex. Use for factual lookups, evidence checks, lists, and inventory status without wiki writes.

LLM-compiled knowledge base manager for Codex. Use it to initialize, ingest, import source collections, collect catalogs, track inventory, index datasets, archive old topics, compile, query, lint, audit, research, plan, capture or rehydrate agent session context, and generate outputs from topic-scoped wikis. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, collection ingestion, import wiki, collect, catalog, curate, find all, inventory, source queue, candidate list, watch list, backlog, dataset, large data, data registry, dataset manifest, compilation, querying, linting, audit, research, librarian, scan quality, article quality, content review, output drift, provenance, archive wiki, archive topic, restore wiki, session capture, capture context, rehydrate, resume from session, implementation plan, or uses /wiki-style shorthand in a repo with .wiki/, ~/wiki/, or a configured hub path.

Fast, read-only, index-first queries over an llm-wiki with bounded file reads, exact citations, and honest evidence gaps.

LLM-compiled knowledge base manager for OpenCode. Use it to initialize, ingest, import source collections, collect catalogs, track inventory, index datasets, archive old topics, compile, query, lint, audit, research, plan, capture or rehydrate agent session context, and generate outputs from topic-scoped wikis. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, collection ingestion, import wiki, collect, catalog, curate, find all, inventory, source queue, candidate list, watch list, backlog, dataset, large data, data registry, dataset manifest, compilation, querying, linting, audit, research, librarian, scan quality, article quality, content review, output drift, provenance, archive wiki, archive topic, restore wiki, session capture, capture context, rehydrate, resume from session, lessons learned, implementation plan, or uses wiki-related shorthand in a repo with .wiki/, ~/wiki/, or a configured hub path.

Local-first health intelligence manager for Claude Code. Use it when the user says /health, @health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

Local-first health intelligence manager for OpenCode and Pi. Use it when the user says @health, /health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

Local-first health intelligence manager for Codex. Use it when the user says @health, /health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

Convert the current session's research, summary, plan, or partially completed work into an interactive one-step-at-a-time instruction mode. Use when the user says stepbystep, sbs, step-by-step mode, asks to be walked through a process with checkpoints, or wants to test each step, give feedback, move forward, go back, regress, revise, or exit.

Convert the current session's research, summary, plan, or partially completed work into an interactive one-step-at-a-time instruction mode. Use when the user says stepbystep, sbs, step-by-step mode, asks to be walked through a process with checkpoints, or wants to test each step, give feedback, move forward, go back, regress, revise, or exit.

Check domain and social namespace availability for candidate names and handles. Use when someone needs fast triage on whether a brand, product, or handle appears to be available across domains and common social platforms. Prefer the bundled checkname script and report uncertain cases honestly.

Check domain and social namespace availability for candidate names and handles. Use when someone needs fast triage on whether a brand, product, or handle appears to be available across domains and common social platforms. Prefer the bundled checkname script and report uncertain cases honestly.