Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From llm-wiki
Compiles, lints, or queries the wiki's typed graph layer from markdown pages. Supports extract, lint, and query subcommands like neighbors, edges, path, facts.
npx claudepluginhub praneybehl/llm-wiki-plugin --plugin llm-wikiHow this command is triggered — by the user, by Claude, or both
Slash command
/llm-wiki:graph extract | lint | neighbors --node <id> | edges --subject <id> | path --from <id> --to <id> | facts --about <id>wiki/The summary Claude sees in its command listing — used to decide when to auto-load this command
Run a graph-layer operation against the wiki using the `llm-wiki` skill's graph workflow. Arguments: $ARGUMENTS 1. Confirm `wiki/graph/ontology.yaml` exists. If not, the wiki is pre-graph — offer to seed `wiki/graph/` (copy the templates from `skills/llm-wiki/assets/`) before doing anything else. Do not fabricate ontology entries. 2. Dispatch on the first argument: - `extract` → `python skills/llm-wiki/scripts/wiki_graph_extract.py wiki/` - `lint` → `python skills/llm-wiki/scripts/wiki_graph_lint.py wiki/` - `neighbors --node <id>` → `python skills/llm-wiki/scripts/wiki_graph_que...
/pith-graphGenerates an interactive force-directed graph from [[wikilinks]] in ./wiki/ .md files and opens wiki-graph.html in the browser.
/graphifyBuilds, queries, and inspects a project knowledge graph stored in .planning/graphs/. Supports build, query, status, and diff subcommands.
/wikiManages LLM Wiki knowledge bases: init new wiki, ingest paths/URLs, compile index, query questions, lint, or remove. Uses subcommands via arguments.
/queryQueries compiled wiki for answers using quick (indexes), standard (articles), or deep (full+raw+sibling) depths, citing sources only from wiki content.
/wiki-bfsPerforms breadth-first web research on a given topic, optionally ingesting results into an LLM wiki. Supports configurable depth (--layers) and custom wiki path (--wiki).
Share bugs, ideas, or general feedback.
Run a graph-layer operation against the wiki using the llm-wiki skill's graph workflow.
Arguments: $ARGUMENTS
wiki/graph/ontology.yaml exists. If not, the wiki is pre-graph — offer to seed wiki/graph/ (copy the templates from skills/llm-wiki/assets/) before doing anything else. Do not fabricate ontology entries.extract → python skills/llm-wiki/scripts/wiki_graph_extract.py wiki/lint → python skills/llm-wiki/scripts/wiki_graph_lint.py wiki/neighbors --node <id> → python skills/llm-wiki/scripts/wiki_graph_query.py wiki/ neighbors --node <id>edges --subject <id> [--predicate <p>] → python skills/llm-wiki/scripts/wiki_graph_query.py wiki/ edges --subject <id> [--predicate <p>]path --from <id> --to <id> [--max-depth N] → python skills/llm-wiki/scripts/wiki_graph_query.py wiki/ path --from <id> --to <id>facts --about <id> → python skills/llm-wiki/scripts/wiki_graph_query.py wiki/ facts --about <id>[[wikilinks]] to wiki pages, not graph rows. The graph accelerates navigation; the wiki page and its raw source remain the evidence.lint, present findings as proposed edits — do not silently rewrite typed graph.relationships. After approved fixes, suggest re-running extract so the compiled artifacts stay in sync with the markdown.graph.sqlite is older than the most recent ingest line in log.md, suggest running extract first.Full reference: skills/llm-wiki/references/graph-workflow.md.