SkillNet CLI
A CLI and Python SDK to search, install, create and evaluate reusable agent skills from a shared library
- 1,453 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Downloads third-party skill folders from GitHub into a local directory, which should be reviewed before use
- Makes network requests and calls external LLM endpoints for create, evaluate and orchestration
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/skillnetDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Downloads third-party skill folders from GitHub into a local directory, which should be reviewed before use
- Makes network requests and calls external LLM endpoints for create, evaluate and orchestration
This is third-party code. Review the repository files before installing.
What it does
SkillNet installs as the skillnet-ai package and provides a skillnet command and a SkillNetClient client. It searches a shared public library by keyword or meaning and downloads skill folders from GitHub into a local working directory. It can create new skills from repositories, documents, prompts and execution traces, score them for safety, completeness, executability, maintainability and cost awareness, analyze relationships between local skills, and select them for a scenario with a ready prompt for a downstream execution agent. Search and public downloads work without keys. Create, evaluate and analyze need an OpenAI-compatible endpoint, and orchestration relies on the Claude Agent SDK.
Who it is for. For developers and agent builders who reuse and tidy up skills instead of rebuilding them from scratch.
Good fit when
- You need to find a ready skill for a task and download it into a project
- You need to build a skill from a repository, a document or a prompt
- You need to assess skill quality and map relationships between them
Not a fit when
- You need a ready skill for a specific task rather than a tool to manage skills
- You have no access to an OpenAI-compatible endpoint but need create, evaluate or orchestration specifically
Example request
Find a skill for PDF understanding and download it into my project folderLimitations
Search and public downloads run without keys, while create, evaluate, analyze and orchestration need an OpenAI-compatible key and endpoint; base_url can point at another compatible gateway. The default OpenAI path is not reachable from Russia without a VPN, so availability depends on the chosen endpoint. Graph analysis and orchestration need extra packages, and Python 3.10 or newer is required. Downloaded skill folders are third-party code that you should review before use.
How to disable. Remove the package with pip uninstall skillnet-ai. Any previously downloaded skill folders are removed from the working directory separately.
FAQ
Do I need a key just to search and download skills?
No. Search and public downloads work without keys. A key is only needed for create, evaluate, analyze and orchestration.
Is there MCP access?
The README notes a SkillNet MCP server exists and is maintained by a third party, which is a separate project. This entry is about the skillnet-ai CLI and SDK.
Discussion
No questions or reviews yet.
Related
CLI toolsA CLI installer and package manager for coding agent skills: one command installs skills into many runtimes and helps build your own
A CLI skill manager for AI agents: install from repositories, translate between agent formats and deploy into their configs
An open catalogue of over three thousand skills, each backed by a real project, with industry collections and categories.
The `askit` command line toolkit for agent skills: lint, security scan, tests, forging new ones and export to any agent.
A CLI and MCP server for Agent Skills: spec validation, installs from GitHub and on-demand loading of the right skill
A command-line skill manager: installs skills from a marketplace, GitHub, private Git and npm into 45 agents' folders and scans them first
README in short
The README describes SkillNet as infrastructure that treats agent skills as software packages: searchable, installable, inspectable, evaluable and composable. The quick start is pip install skillnet-ai plus search and download commands that need no keys. Through the SDK and CLI you get skill creation from repositories, documents and prompts, quality evaluation, relationship analysis and scenario orchestration. Create, evaluate and analyze work with OpenAI-compatible endpoints, and orchestration runs through the Claude Agent SDK. There is a visual library explorer on the site, separate examples and experiments folders, an arXiv paper, and an MIT license.