275 tagged knowledge base, measured the same way as everything else here.
Browse within: karpathy 54obsidian 47llm-wiki 40markdown 40local-first 36fact-checking 29finance 29healthcare 29law 29swiss 29agent-memory 24knowledge-graph 24workflow 17wiki 14
Command
Brain Console — RuvNet Brain Console (same console as /rvbc, /brain-console, and /ruvnet-brain:configure — every spelling works). Opens the live console page: your whole RuvNet stack on one page. Read-only until you click.
Command
Open the RuvNet Brain Onboarding Console — a local web page that mirrors YOUR machine's RuvNet setup, explains it in plain English, and lets you safely configure and fix it. Read-only until you click; every machine change is explained first and is reversible.
Command
What's new in RuvNet Brain — the big things in the current MAJOR release (4.0), in plain English. Not the point-release churn — the headline changes since 3.x. Ends by offering to open the Console so you can see it live.
Command
Build a bespoke, art-directed explainer site (+ downloadable AI knowledge pack) for any GitHub repo.
Command Claude Code
Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…
Command Claude Code
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
Command Claude Code
Checks the integrity of the abapwiki knowledge base: parseable YAML frontmatter, no broken wikilinks, resolvable [VERIFIED: path:N-M] citations, non-nested confidence tags, drift between wiki and DB, synchronization between canonical agent contracts and the .claude/agents/ copies. Use this skill periodically or after…
Command
3-round autonomous research loop with intermediate notes and synthesis.
Command
Push vault notes to NotebookLM, ask cited questions, generate reports (experimental).
Command
10-principle structured thinking framework saved to vault.
Command
Ask a question against the compiled wiki.
Command
Compile raw sources into the wiki (incremental by default).
Command
Generate a long-form article from the compiled wiki.
Command
Compact the hot tier into the warm tier. Two modes.
Command
Use the bundled Codex research skill to recall, refresh, or store project-scoped research.
Command
Save a source (URL, file path, or the current session) into the LLM Wiki. Claude auto-routes to the global or local wiki unless you pass --global / --local.
Command
Ask the LLM Wiki a question. Reads the most relevant pages and answers in this chat; optionally saves the answer back into the wiki.
Command Claude Code
Archive multiple completed changes at once.
Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
Command Claude Code
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
Command Claude Code
Fetch web content or documentation into the raw/ directory.
Command Claude Code
Show all available memex knowledge base commands.
Command Claude Code
Append a log entry to the vault activity log.
Command Claude Code
Run the full end-to-end verifier across every recipe + flagship, then have the cookbook-junior-dev agent triage the report. Accepts optional args like "--flagships-only", "--only icd10coder,creditmemodrafter", "--no-verify", "--limit 5".