understand-chat
Agent skill fromEgonex-AI/Understand-Anything
Use when you need to ask questions about a codebase or understand code using a knowledge graph
How to install understand-chat
install understand-chat
# install the Understand-Anything pack with the skills CLI
npx skills add Egonex-AI/Understand-Anything# or add only this skill to Claude Code: copy the folder
understand-anything-plugin/skills/understand-chat/
# into
~/.claude/skills/understand-chat/ (all projects)
.claude/skills/understand-chat/ (one project)
1# /understand-chat23Answer questions about this codebase using the knowledge graph in the project's data directory (`.ua/knowledge-graph.json`, or the legacy `.understand-anything/knowledge-graph.json` when that directory is present).45## Graph Structure Reference67The knowledge graph JSON has this structure:8- `project` — {name, description, languages, frameworks, analyzedAt, gitCommitHash}9- `nodes[]` — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}10 - Code node types: file, function, class, module, concept11 - Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource12 - Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source13 - IDs use the node type as prefix, e.g. `file:path`, `function:path:name`, `config:path`, `article:path`14- `edges[]` — each has {source, target, type, direction, weight}15 - Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites16- `layers[]` — each has {id, name, description, nodeIds[]}17- `tour[]` — each has {order, title, description, nodeIds[]}1819## How to Read Efficiently20211. Use Grep to search within the JSON for relevant entries BEFORE reading the full file222. Only read sections you need — don't dump the entire graph into context233. Node names and summaries are the most useful fields for understanding24…
Excerpt shown under the repository's MIT license.
