Graph Skills Retriever

by davidliuk

Graph Skills Retriever is an AI Engineering skill for Claude Code, published by davidliuk in graph-of-skills.

205 stars26 forkson davidliuk/graph-of-skillsAdded 2026/09/05Repository updated 2026/08/30

View source on GitHub Download repo ZIP

claude-codeknowledge-graphskills

Install in seconds

Install Graph Skills Retriever

Copy Graph Skills Retriever 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/davidliuk/graph-of-skills/tree/main/skills/graph-skills-retriever ~/.claude/skills/graph-skills-retriever

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/davidliuk/graph-of-skills.git

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

In this catalog

Source file: skills/graph-skills-retriever/SKILL.md in davidliuk/graph-of-skills
Installs to: ~/.claude/skills/graph-skills-retriever
Collection: One of 3 skills cataloged from this repository
Category: AI Engineering — 3101 skills

What Graph Skills Retriever does

Graph Skills Retriever queries a prebuilt Graph of Skills workspace for a bounded bundle of relevant external skills. Use it when a task may need specialized skills, scripts, or references not already present in context.

Graph Skills Retriever is cataloged under AI Engineering on DirSkills. Graph Skills Retriever comes from a repository tagged claude-code, knowledge-graph and skills.

Documentation

README

Excerpt

Purpose

Use this skill instead of manually browsing a large skill library.

It assumes the environment already provides:

the graphskills-query CLI
a GoS workspace or a prebuilt workspace configured through GOS_WORKING_DIR and optionally GOS_PREBUILT_WORKING_DIR

If that wiring is missing, read references/container-layout.md.

Retrieve Relevant Skills

Construct the query yourself. Do not rely on the retrieval system to infer missing task structure for you.

A good query should usually include only the retrieval-critical fields that are actually known:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Graph Skills Retriever

What else does davidliuk publish alongside Graph Skills Retriever?
Graph Skills Retriever is one of 3 skills that DirSkills catalogs from davidliuk/graph-of-skills, the repository it ships in. Its siblings there include Graph Skills Retriever and Vector Skills Retriever. Each one is a separate skill with its own page in this directory, installs the same way Graph Skills Retriever does, and is maintained by davidliuk in that same repository. The rest of the collection is listed on the davidliuk/graph-of-skills page.
How does Graph Skills Retriever compare to other AI Engineering skills?
Graph Skills Retriever ranks #2797 by stars among the 3101 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 Skills Retriever against them. Open each page to compare what they document and how they install.