/graph-retrieval

Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

study8677@study8677

GitHub

From plugin

repobrain

1.3k5 skills4 commands1 hook

Install

$ npx -y skills add study8677/repobrain --skill graph-retrieval --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/graph-retrieval

Context preview

The summary Claude sees to decide when to auto-load this skill.

Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

SKILL.md

graph-retrieval.SKILL.md

name: graph-retrieval
description: Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

Graph Retrieval Skill

Purpose

Expose graph-based retrieval as a tool capability without breaking the existing RepoBrain execution chain.

Tool

`query_graph(query, max_hops=2, workspace='.')`

Behavior

Reads normalized graph store files under `.repobrain/graph/`.
Builds a query-relevant subgraph.
Returns LLM-friendly semantic triples plus replayable evidence metadata.

Output Contract

{
  "summary": "...",
  "triples": [["subject", "predicate", "object"]],
  "evidence": [{"retrieval_id": "...", "tool_name": "..."}],
  "nodes": [...],
  "edges": [...]
}