Skill Graphs - Indexed Agent Knowledge

PyPI - Version MCP Server

Version: 2.2.0

Documentation — The curated catalog of distilled documentation skill-graphs, the environment flags that enable each domain, and the workflow for building new graphs are maintained in the official documentation.

Overview

Skill Graphs is a dedicated repository for structured, documentation-based skills. It is designed to host "knowledge graphs" transformed from technical documentation, APIs, and web crawls, specifically for use with Pydantic AI Agents.

Enabling Skill Graphs

By default, all skill-graphs included in this package are disabled. You can enable specific skill-graphs by setting their corresponding environment variables to True.

Skill Directory	Description	Enable Flag
`aws-docs`	AWS Documentation	`AWS_DOCS_ENABLE=True`
`azure-docs`	Azure Documentation	`AZURE_DOCS_ENABLE=True`
`c-docs`	C Language Documentation	`C_DOCS_ENABLE=True`
`chakra-ui-docs`	Chakra UI Documentation	`CHAKRA_UI_DOCS_ENABLE=True`
`chromadb-docs`	ChromaDB Documentation	`CHROMADB_DOCS_ENABLE=True`
`couchbase-docs`	Couchbase Documentation	`COUCHBASE_DOCS_ENABLE=True`
`django-docs`	Django Documentation	`DJANGO_DOCS_ENABLE=True`
`docker-docs`	Docker Documentation	`DOCKER_DOCS_ENABLE=True`
`falkordb-docs`	FalkorDB Documentation	`FALKORDB_DOCS_ENABLE=True`
`fastapi-docs`	FastAPI Documentation	`FASTAPI_DOCS_ENABLE=True`
`fastmcp-docs`	FastMCP Documentation	`FASTMCP_DOCS_ENABLE=True`
`flask-docs`	Flask Documentation	`FLASK_DOCS_ENABLE=True`
`framer-docs`	Framer Motion Documentation	`FRAMER_DOCS_ENABLE=True`
`gcp-docs`	GCP Documentation	`GCP_DOCS_ENABLE=True`
`go-docs`	Go Documentation	`GO_DOCS_ENABLE=True`
`huggingface-docs`	Hugging Face Documentation	`HUGGINGFACE_DOCS_ENABLE=True`
`java-docs`	Java Documentation	`JAVA_DOCS_ENABLE=True`
`langchain-docs`	LangChain Documentation	`LANGCHAIN_DOCS_ENABLE=True`
`laravel-docs`	Laravel Documentation	`LARAVEL_DOCS_ENABLE=True`
`linux-docs`	Linux Documentation	`LINUX_DOCS_ENABLE=True`
`mariadb-docs`	MariaDB Documentation	`MARIADB_DOCS_ENABLE=True`
`material-ui-docs`	Material UI Documentation	`MATERIAL_UI_DOCS_ENABLE=True`
`matplotlib-docs`	Matplotlib Documentation	`MATPLOTLIB_DOCS_ENABLE=True`
`minio-docs`	MinIO Documentation	`MINIO_DOCS_ENABLE=True`
`mongodb-docs`	MongoDB Documentation	`MONGODB_DOCS_ENABLE=True`
`mssql-docs`	MS SQL Server Documentation	`MSSQL_DOCS_ENABLE=True`
`neo4j-docs`	Neo4j Documentation	`NEO4J_DOCS_ENABLE=True`
`nestjs-docs`	NestJS Documentation	`NESTJS_DOCS_ENABLE=True`
`nextjs-docs`	Next.js Documentation	`NEXTJS_DOCS_ENABLE=True`
`nodejs-docs`	Node.js Documentation	`NODEJS_DOCS_ENABLE=True`
`numpy-docs`	NumPy Documentation	`NUMPY_DOCS_ENABLE=True`
`pandas-docs`	Pandas Documentation	`PANDAS_DOCS_ENABLE=True`
`postgres-docs`	PostgreSQL Documentation	`POSTGRES_DOCS_ENABLE=True`
`pydantic-ai-docs`	Pydantic AI Documentation	`PYDANTIC_AI_DOCS_ENABLE=True`
`pydantic-docs`	Pydantic Documentation	`PYDANTIC_DOCS_ENABLE=True`
`python-docs`	Python Documentation	`PYTHON_DOCS_ENABLE=True`
`pytorch-docs`	PyTorch Documentation	`PYTORCH_DOCS_ENABLE=True`
`qdrant-docs`	Qdrant Documentation	`QDRANT_DOCS_ENABLE=True`
`radix-ui-docs`	Radix UI Documentation	`RADIX_UI_DOCS_ENABLE=True`
`react-docs`	React Documentation	`REACT_DOCS_ENABLE=True`
`reactrouter-docs`	React Router Documentation	`REACTROUTER_DOCS_ENABLE=True`
`redis-docs`	Redis Documentation	`REDIS_DOCS_ENABLE=True`
`redux-docs`	Redux Documentation	`REDUX_DOCS_ENABLE=True`
`remix-docs`	Remix Documentation	`REMIX_DOCS_ENABLE=True`
`rust-docs`	Rust Documentation	`RUST_DOCS_ENABLE=True`
`scikit-learn-docs`	Scikit-learn Documentation	`SCIKIT_LEARN_DOCS_ENABLE=True`
`scipy-docs`	SciPy Documentation	`SCIPY_DOCS_ENABLE=True`
`shadcn-docs`	shadcn/ui Documentation	`SHADCN_DOCS_ENABLE=True`
`svelte-docs`	Svelte Documentation	`SVELTE_DOCS_ENABLE=True`
`tanstack-docs`	TanStack Documentation	`TANSTACK_DOCS_ENABLE=True`
`temporal-docs`	Temporal Documentation	`TEMPORAL_DOCS_ENABLE=True`
`tensorflow-docs`	TensorFlow Documentation	`TENSORFLOW_DOCS_ENABLE=True`
`terraform-docs`	Terraform Documentation	`TERRAFORM_DOCS_ENABLE=True`
`testing-library-docs`	Testing Library Documentation	`TESTING_LIBRARY_DOCS_ENABLE=True`
`vercel-docs`	Vercel Documentation	`VERCEL_DOCS_ENABLE=True`
`vitejs-docs`	Vite Documentation	`VITEJS_DOCS_ENABLE=True`
`vuejs-docs`	Vue.js Documentation	`VUEJS_DOCS_ENABLE=True`

Installation

pip install skill-graphs

Usage

Skill graphs are typically loaded using the get_skill_graphs_path() utility from skill_graphs.skill_graph_utilities.

from skill_graphs.skill_graph_utilities import get_skill_graphs_path
from pydantic_ai_skills import SkillsToolset

# Load enabled skill graphs
skills_directories = get_skill_graphs_path()
skills = SkillsToolset(directories=skills_directories)

Building New Skill Graphs

Use the skill-graph-builder from the universal-skills package to generate new graphs:

python scripts/generate_skill.py https://ai.pydantic.dev pydantic-ai

By default, the builder will now target this repository if it is present in your workspace.

Development Status
- 5 - Production/Stable
Environment
- Console
License
- Public Domain
Operating System
- OS Independent
Programming Language
- Python :: 3

Metadata

Development Status
- 5 - Production/Stable
Environment
- Console
License
- Public Domain
Operating System
- OS Independent
Programming Language
- Python :: 3

Release files for skill-graphs 2.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for skill-graphs 2.2.0
File	Size	Uploaded	Provenance	Actions
skill_graphs-2.2.0.tar.gz	44.1 MB	Nov 4, 2026	Without provenance	Details for skill_graphs-2.2.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for skill-graphs 2.2.0
File	Interpreter	ABI	Platform	Actions Reset
skill_graphs-2.2.0-py3-none-any.whl 60.3 MB Nov 4, 2026 Without provenance	Python 3	none	any	Details for skill_graphs-2.2.0-py3-none-any.whl

Total release size: 104.4 MB

Release files / skill_graphs-2.2.0.tar.gz

Download URL	skill_graphs-2.2.0.tar.gz
Size	44.1 MB
Tags	Source
SHA-256 checksum How to use checksums	`faf594a2f5b6019904bc540f331325ca31a9cb8f2dfe564fd1c599796db33f56`
BLAKE2b-256 checksum How to use checksums	`17cfe6a2c5c80164b4fd09152a8b92e86590e7ed767f0fb155d3488a83f900ee`
Upload date	Nov 4, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.4`

Release files / skill_graphs-2.2.0-py3-none-any.whl

Download URL	skill_graphs-2.2.0-py3-none-any.whl
Size	60.3 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`548000bfdeb497e8a31be91bc6603200e3cb34a15d54e9a58205671c447dc3d6`
BLAKE2b-256 checksum How to use checksums	`bb7b6411155013223f9567b260a947caeef82160454ab11b5b12a6b4a8b556d0`
Upload date	Nov 4, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.4`

Security for skill-graphs 2.2.0

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

2.2.0 This release

Nov 4, 2026 2 release files No provenance

skill-graphs 2.2.0