Understand Onboard

This generates an onboarding guide by reading the knowledge graph created by /understand and turning it into a structured markdown document. It pulls project metadata, architecture layers, the recommended tour, and file-level nodes to create sections on architecture, key concepts, a guided walkthrough, a file map, and complexity hotspots. The smart part is it uses grep to extract only what it needs instead of dumping the entire graph into context, keeping things efficient. It skips function and class level details to stay high level, which makes sense for onboarding. The output gets saved to docs/ONBOARDING.md so new team members have something concrete to read when they join.

skills.sh installs: 1.2K
GitHub stars: 73.8K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add lum1104/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[]}