iflytek/skillhub

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

What it solves

SkillHub provides a centralized, private, and governed way for organizations to manage "agent skills" (reusable skill packages). It solves the problem of fragmented skill distribution by allowing teams to publish, discover, and version skills behind their own firewall, ensuring proprietary logic remains secure while remaining accessible to authorized users.

How it works

SkillHub acts as a self-hosted registry. It uses a Spring Boot backend and a React frontend to manage skill packages. Users can upload skills using a CLI or REST API, organize them into team-specific namespaces with role-based access control (RBAC), and discover them via full-text search. The platform supports semantic versioning and pluggable storage (local filesystem or S3/MinIO) for the actual skill files.

Who it’s for

It is designed for enterprises and teams building AI agents that need a private infrastructure to share and govern the capabilities (skills) their agents can use across different projects or departments.

Highlights

  • Self-Hosted & Private: Full data sovereignty with on-premise deployment.
  • Versioning & Governance: Supports semantic versioning, custom tags (e.g., beta, stable), and admin review flows for promoting skills to global scopes.
  • Team Namespaces: Organized scopes with dedicated members, roles (Owner/Admin/Member), and publishing policies.
  • CLI-First Workflow: Native CLI for searching, installing, and publishing skills.
  • Pluggable Storage: Compatible with local storage for development and S3/MinIO for production.
  • Enterprise Features: Includes audit logging, API token management, and multi-language support.

Related

  • Project
    chujianyun/skills

    A Chinese‑language repo that bundles dozens of reusable “Agent Skills” – small, documented plugins for Claude Code and similar LLM‑agent platforms. Skills cover wiki look‑ups, prompt optimisation, career assessments, diagram generation, document interpretation, audio‑to‑text, image watermarking, web‑scraping, and service run‑books. They are organized under `skills/`, registered in `config/skills.json`, and installed via Claude Code’s marketplace, an installer agent, or the `openskills` CLI.

  • Project
    xingkongliang/skills-manager

    Skills Manager is a cross‑platform desktop and CLI tool for collecting, organising, and deploying AI‑agent skill packages (prompt‑code bundles) across many coding assistants. It offers a unified library, marketplace, presets, global/project workspaces, multi‑tool sync, Git‑backed backup, and agent‑aware management, all built with React/Tauri (frontend) and Rust/SQLite (backend).

  • Project
    FrancyJGLisboa/agent-skills-platform

    A platform that converts real-world workflows into tested, installable agent skills that can be governed and distributed via a team marketplace.

  • Project
    skilld-dev/skilld

    A curated registry and CLI for managing Agent Skills, allowing users to discover and install standardized AI instructions across multiple AI agents and IDEs.

  • Project
    CreminiAI/skillpack

    An open-source framework for packaging AI skills into runnable local agents that can be integrated with Slack and Telegram to keep team data private.