Slash Command

/graph

Compiles, lints, or queries the wiki's typed graph layer from markdown pages. Supports extract, lint, and query subcommands like neighbors, edges, path, facts.

Python

SQLite

Markdown

database

documentation

Install

npx claudepluginhub praneybehl/llm-wiki-plugin --plugin llm-wiki

Details

Namespacewiki/

Prompt Preview

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...

Command Content

Other plugins with /graph

/graph

Displays related memories as an indented knowledge-graph tree up to 3 hops from a given ID or prefix, showing relationship types and directions (e.g., → supersedes, ← derived_from).

/graph

Render a Mermaid dependency graph of specs, concrete specs, and managed files

unslop

/graph

Generate a dependency graph of all markdown links, rendered as PNG (or .dot if graphviz not installed).

Bash

md-linker

/graph

Generate an on-demand D3 link graph of llm-wiki/wiki into .tmp/llm-wiki-graph (GitHub-dark styled).

llm-wiki

/graph

Explore the knowledge graph by asking questions

BashRead

mos

/graph

Render the current evidence-tree state as a Mermaid graph — which MSCs are sealed (PASS), which are pending, which failed. Optional --run-id scopes to one forge run. Read-only.

ReadGlobGrep+1

crucible

Stats

Stars25

Forks0

Last CommitApr 25, 2026

Actions

View Source View Plugin View on GitHub View README

Tags

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...

Run a graph-layer operation against the wiki using the llm-wiki skill's graph workflow.

Arguments: $ARGUMENTS

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.
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_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>
For query subcommands, after running the script, follow the most relevant edges back to their wiki pages and summarize. Cite with [[wikilinks]] to wiki pages, not graph rows. The graph accelerates navigation; the wiki page and its raw source remain the evidence.
For 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.
If 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.