Total Skills
10
Skills published by craft-man with real stars/downloads and source-aware metadata.
Total Skills
10
Total Stars
10
Total Downloads
0
Comparison chart based on real stars and downloads signals from source data.
init
1
onboard
1
graphify
1
ingest
1
lint
1
mine
1
query
1
save
1
Bootstrap a new mnemo knowledge base with taxonomy directory structure and a starter SCHEMA.md. Use when starting a new wiki, setting up a second brain, initializing a personal knowledge base, or when the user says "set up my wiki", "create a knowledge base", "initialize mnemo", or "start my second brain". Run once per project before the first ingest. After init, optionally wires the wiki into CLAUDE.md for future session memory.
Initialize or update the global user profile in ~/.mnemo/. Use when the user runs /mnemo:init for the first time, when no person-user.md exists in the global memory tier, or when the user says "update my profile", "change my preferences", "who am I in mnemo", or "my role has changed".
Map the current project codebase into a queryable mnemo knowledge graph using graphify. Converts graphify's structured output (graph.json) directly into mnemo wiki pages — entities, concepts, and a synthesis report — so agents can answer questions about the project without re-reading source files on every session. Use when the user says "map my codebase", "build a knowledge graph", "index my project", "graphify this", or invokes /mnemo:graphify explicitly.
Process raw files in raw/ into synthesized, categorized wiki pages via LLM analysis. Extracts entities and concepts, creates bidirectional wikilinks, and enforces source citations. Use when the user says "ingest this", "add this to my wiki", "process my notes", "compile this paper into the knowledge base", "add to second brain", or drops new files into raw/ and asks to process them.
Audit the mnemo knowledge base for structural issues: orphaned pages, broken index links, missing YAML frontmatter, missing source citations, oversized pages, pages with no inbound wikilinks, stale temporal claims, superseded pages missing a History section, and unprocessed raw files. Presents each finding as a proposed edit awaiting user approval. Use when the user says "check my wiki", "audit the knowledge base", "lint my notes", "find broken links", or "health check". Run periodically and after any batch ingest.
Extract knowledge from the current conversation session worth persisting to the mnemo knowledge base. Scans for decisions, new entities, insights, and conclusions. Invoke explicitly (/mnemo:mine) or when the user expresses intent to save something ("remember this", "note that", "important") or when the agent detects high-value signals ("we decided", "in conclusion", "key insight") — in any language.
Search the mnemo wiki knowledge base. Uses qmd (hybrid BM25 + vector semantic search) if configured at init, otherwise falls back to BM25 ranked retrieval. Supports tag:, since:, category:, backlinks:, and top-linked modifiers. Use when the user asks "what does my wiki say about X", "search my notes for Y", "find pages about Z", "query the knowledge base", "what do I know about X", or "look up X in my second brain". Falls back to global knowledge base if local returns no results.
Save AI-generated content — summaries, comparisons, analyses, insights — as a permanent, categorized wiki page with YAML frontmatter. Routes to sources, entities, concepts, or synthesis based on content type. Use when the user says "save this", "add this to my wiki", "store this analysis", "keep this insight", "create a wiki page for this", or "persist this summary". Asks for a title and category before writing.
Interactively create or revise .mnemo/SCHEMA.md — the domain taxonomy that guides ingest categorization. If raw/ files are present, infers entity types and concept categories from their content before asking questions. Use when the user says "define my schema", "set up my taxonomy", "what entity types should I use", "update my schema", "my domain has changed", or right after /mnemo:init.
Display size metrics and scaling health for the mnemo wiki: page counts per category, total line count, top 5 largest pages, and scaling threshold status (flat index, approaching 150-page shard threshold, or sharded). Use when the user says "stats", "how big is my wiki", "show me wiki metrics", "how many pages do I have", "is my knowledge base getting large", or "check scaling status".