Understand Onboard

Turns knowledge graphs into actual onboarding docs. It reads the graph JSON that /understand generates and pulls out project metadata, architecture layers, the guided tour, and file-level nodes while skipping granular function details to keep things digestible. Then it builds a structured markdown guide with project overview, layer breakdown, key concepts, a walkthrough, file map, and complexity hotspots so new developers know where to tread carefully. The smart part is it uses grep to search the JSON instead of dumping everything into context, which keeps it fast. Outputs to docs/ONBOARDING.md and you can commit it so the next person doesn't have to bug you with setup questions.

skills.sh installs: 4.2K
GitHub stars: 91.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add egonex-ai/understand-anything --skill understand-onboard --agent claude-code

Installs into .claude/skills of the current project.

Files

/understand-onboard

Generate a comprehensive onboarding guide from the project's knowledge graph.

Graph Structure Reference

The knowledge graph JSON has this structure:

project — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
nodes[] — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
- Code node types: file, function, class, module, concept
- Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
- Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
- IDs use the node type as prefix, e.g. file:path, function:path:name, config:path, article:path
edges[] — each has {source, target, type, direction, weight}
- Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
layers[] — each has {id, name, description, nodeIds[]}
tour[] — each has {order, title, description, nodeIds[]}