Graph Retrieval

Graph Retrieval is an AI Engineering skill for Claude Code, published by study8677 in repobrain.

1.3K stars265 forkson study8677/repobrainAdded 2026/08/20Repository updated 2026/08/14

agents-sdkai-agentclaude-codecode-intelligencecode-searchcodebase-qacodex-clicopilotcursordeveloper-toolside-pluginknowledge-graphllmmcpmcp-servermulti-agentopenaipythonragwindsurf

Install in seconds

Install Graph Retrieval

Copy Graph Retrieval into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/study8677/repobrain/tree/main/engine/repobrain_engine/skills/graph-retrieval ~/.claude/skills/graph-retrieval

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/study8677/repobrain.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: engine/repobrain_engine/skills/graph-retrieval/SKILL.md in study8677/repobrain
Installs to: ~/.claude/skills/graph-retrieval
Collection: One of 6 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Graph Retrieval does

Graph Retrieval queries a normalized graph store to return semantic triples and evidence for codebase structure and dependency questions. Use it when an agent needs replayable, context-enriching graph data without bypassing the existing pipeline.

Graph Retrieval is cataloged under AI Engineering on DirSkills. Graph Retrieval comes from a repository tagged agents-sdk, ai-agent, claude-code, code-intelligence and code-search.

Documentation

README

From the original repository

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": [...]
}

Design Notes

Keeps tool-driven and replayable architecture.
Does not bypass pipeline.
Intended for structure/dependency questions and context enrichment.

Frequently asked about Graph Retrieval

What else does study8677 publish alongside Graph Retrieval?
Graph Retrieval is one of 6 skills that DirSkills catalogs from study8677/repobrain, the repository it ships in. Its siblings there include Agent Repo Init, Agent Repository Init and Agent Workspace Init. Each one is a separate skill with its own page in this directory, installs the same way Graph Retrieval does, and is maintained by study8677 in that same repository. The rest of the collection is listed on the study8677/repobrain page.
How does Graph Retrieval compare to other AI Engineering skills?
Graph Retrieval ranks #1100 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Graph Retrieval against them. Open each page to compare what they document and how they install.