understand-explain

Explains a specific file, function, or module using a codebase knowledge graph.

Updated Jun 28, 2026
One-click install
npx skills add https://github.com/AO-HyS/aohys.com --skill understand-explain-ao-hys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: understand-explain
Source: https://github.com/AO-HyS/aohys.com/tree/main/.agents/skills/understand-explain
Command: npx skills add https://github.com/AO-HyS/aohys.com --skill understand-explain-ao-hys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Understanding an unfamiliar code component requires manually tracing imports, callers, and dependencies across many files. This Skill uses a pre-built knowledge graph to locate a component and its connections, then produces a deep-dive explanation grounded in the actual source code. ## Core Features & Use Cases - Graph-Guided Lookup: Searches the knowledge graph JSON by file path or function name to find the target node's type, summary, tags, and complexity. - Dependency Neighborhood Mapping: Traces incoming and outgoing edges (imports, calls, depends_on, contains) to show how the component connects to the rest of the codebase. - Architectural Context: Identifies which architectural layer the component belongs to and explains its role, internal structure, and data flow in plain language. - Use Case: A new team member asks how src/auth/login.ts:verifyToken works; the Skill locates the node, maps its callers and dependencies, reads the source, and explains the full picture. ## Quick Start Run /understand-explain with a file path or function path like src/auth/login.ts:verifyToken to get a deep-dive explanation of that component.

Frequently Asked Questions about understand-explain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get a deep explanation of a function in my codebase?▼

Run the skill with a file path or function notation like src/auth/login.ts:verifyToken. It searches the knowledge graph for the node, traces its connected edges, reads the source file, and explains the component's role, structure, and data flow.

What is the knowledge graph JSON structure used for code explanation?▼

The graph contains a project object, nodes with id, type, filePath, summary, tags, and complexity, edges with source, target, and type such as imports or calls, plus layers and tours that group nodes architecturally.

Why does the skill say to run /understand first?▼

The explanation depends on .understand-anything/knowledge-graph.json, which is generated by the /understand skill. If that file does not exist, there is no graph to search, so you must run /understand before requesting component explanations.

Can I search the knowledge graph without loading the whole file?▼

Yes. The skill instructs using Grep to search for specific filePath, name, source, or target fields within the JSON, reading only the relevant sections instead of dumping the entire graph into context.

What are the limitations of graph-based code explanation?▼

Explanations are only as current as the last graph generation, so recent code changes may not be reflected. Components missing from the graph cannot be located, and dynamic runtime behavior is not captured by static edges.