An enterprise-grade, open-source agent skill registry — publish, discover, and manage reusable skill packages across your organization.
SkillHub is a self-hosted platform that gives teams a private, governed place to share agent skills. Publish a skill package, push it to a namespace, and let others find it through search or install it via CLI. Built for on-premise deployment behind your firewall, with the same polish you'd expect from a public registry.
- Self-Hosted & Private — Deploy on your own infrastructure.
Keep proprietary skills behind your firewall with full data
sovereignty. One
make dev-allcommand to get running locally. - Publish & Version — Upload agent skill packages with semantic
versioning, custom tags (
beta,stable), and automaticlatesttracking. - Discover — Full-text search with filters by namespace, downloads, ratings, and recency. Visibility rules ensure users only see what they're authorized to.
- Team Namespaces — Organize skills under team or global scopes. Each namespace has its own members, roles (Owner / Admin / Member), and publishing policies.
- Review & Governance — Team admins review within their namespace; platform admins gate promotions to the global scope. Governance actions are audit-logged for compliance.
- Social Features — Star skills, rate them, and track downloads. Build a community around your organization's best practices.
- Account Merging — Consolidate multiple OAuth identities and API tokens under a single user account.
- API Token Management — Generate scoped tokens for CLI and programmatic access with prefix-based secure hashing.
- CLI-First — Native REST API plus a compatibility layer for existing ClawHub-style registry clients. Native CLI APIs are the primary supported path while protocol compatibility continues to expand.
- Pluggable Storage — Local filesystem for development, S3 / MinIO for production. Swap via config.
- Internationalization — Multi-language support with i18next.
Start the full local stack with one of the following commands:
Official images:
rm -rf /tmp/skillhub-runtime
curl -fsSL https://imageless.oss-cn-beijing.aliyuncs.com/runtime-github.sh | sh -s -- upThe default command pulls the latest stable release images. Use
--version edge if you want the newest build from main.
Aliyun mirror shortcut:
rm -rf /tmp/skillhub-aliyun
curl -fsSL https://imageless.oss-cn-beijing.aliyuncs.com/runtime.sh | sh -s -- up --home /tmp/skillhub-aliyun --aliyun --version latestIf deployment runs into problems, clear the existing runtime home and retry.
- Docker & Docker Compose
make dev-allThen open:
- Web UI:
http://localhost:3000 - Backend API:
http://localhost:8080
By default, make dev-all starts the backend with the local profile.
In that mode, local development keeps the mock-auth users below and also
creates a password-based bootstrap admin account by default:
local-userfor normal publishing and namespace operationslocal-adminwithSUPER_ADMINfor review and admin flows
Use them with the X-Mock-User-Id header in local development.
The local bootstrap admin is enabled by default in application-local.yml:
- username:
BOOTSTRAP_ADMIN_USERNAME(adminby default) - password:
BOOTSTRAP_ADMIN_PASSWORDIn local app-level fallback it isChangeMe!2026. - For local source startup, set the environment variable
BOOTSTRAP_ADMIN_ENABLED=falsebefore starting the backend. - For container or release environments, configure the same value in
.env.releaseor the Compose environment. - The shipped release template still uses
replace-this-admin-passwordand must be changed before first login.
Stop everything with:
make dev-all-downReset local dependencies and start from a clean slate with:
make dev-all-resetRun make help to see all available commands.
Useful backend commands:
make test
make test-backend-app
make build-backend-appDo not run ./mvnw -pl skillhub-app clean test directly under server/.
skillhub-app depends on sibling modules in the same repo, and a standalone clean build
can fall back to stale artifacts from the local Maven repository, which surfaces misleading
cannot find symbol and signature-mismatch errors. Use -am, or the make test-backend-app
and make build-backend-app targets above.
For the full development workflow (local dev → staging → PR), see docs/dev-workflow.md.
OpenAPI types for the web client are checked into the repository. When backend API contracts change, regenerate the SDK and commit the updated generated file:
make generate-apiFor a stricter end-to-end drift check, run:
./scripts/check-openapi-generated.shThis starts local dependencies, boots the backend, regenerates the frontend schema, and fails if the checked-in SDK is stale.
Published runtime images are built by GitHub Actions and pushed to GHCR.
This is the supported path for anyone who wants a ready-to-use local
environment without building the backend or frontend on their machine.
Published images target both linux/amd64 and linux/arm64.
- Copy the runtime environment template.
- Pick an image tag.
- Start the stack with Docker Compose.
cp .env.release.example .env.releaseRecommended image tags:
SKILLHUB_VERSION=edgefor the latestmainbuildSKILLHUB_VERSION=vX.Y.Zfor a fixed release
Start the runtime:
make validate-release-config
docker compose --env-file .env.release -f compose.release.yml up -dThen open:
- Web UI:
SKILLHUB_PUBLIC_BASE_URL对应的地址 - Backend API:
http://localhost:8080
Stop it with:
docker compose --env-file .env.release -f compose.release.yml downThe runtime stack uses its own Compose project name, so it does not
collide with containers from make dev-all.
The production Compose stack now defaults to the docker profile only.
It does not enable local mock auth. Bootstrap admin is disabled by default;
if you turn it on explicitly, the backend seeds a local admin account from
environment variables for the first login:
- username:
BOOTSTRAP_ADMIN_USERNAME - password:
BOOTSTRAP_ADMIN_PASSWORD
Recommended production baseline:
- set
SKILLHUB_PUBLIC_BASE_URLto the final HTTPS entrypoint - keep PostgreSQL / Redis bound to
127.0.0.1 - use external S3 / OSS via
SKILLHUB_STORAGE_S3_* - keep
BOOTSTRAP_ADMIN_ENABLED=falseunless you intentionally need bootstrap login - rotate or disable the bootstrap admin after initial setup
- run
make validate-release-configbeforedocker compose up -d
If the GHCR package remains private, run docker login ghcr.io before
docker compose up -d.
A Prometheus + Grafana monitoring stack lives under monitoring/.
It scrapes the backend's Actuator Prometheus endpoint.
Start it with:
cd monitoring
docker compose -f docker-compose.monitoring.yml up -dThen open:
- Prometheus:
http://localhost:9090 - Grafana:
http://localhost:3001(admin/admin)
By default Prometheus scrapes http://host.docker.internal:8080/actuator/prometheus,
so start the backend locally on port 8080 first.
Basic Kubernetes manifests are available under deploy/k8s/:
configmap.yamlsecret.yaml.examplebackend-deployment.yamlfrontend-deployment.yamlservices.yamlingress.yaml
Apply them after creating your own secret:
kubectl apply -f deploy/k8s/configmap.yaml
kubectl apply -f deploy/k8s/secret.yaml
kubectl apply -f deploy/k8s/backend-deployment.yaml
kubectl apply -f deploy/k8s/frontend-deployment.yaml
kubectl apply -f deploy/k8s/services.yaml
kubectl apply -f deploy/k8s/ingress.yamlA lightweight smoke test script is available at scripts/smoke-test.sh.
Run it against a local backend:
./scripts/smoke-test.sh http://localhost:8080┌─────────────┐ ┌─────────────┐ ┌──────────────┐
│ Web UI │ │ CLI Tools │ │ REST API │
│ (React 19) │ │ │ │ │
└──────┬──────┘ └──────┬──────┘ └──────┬───────┘
│ │ │
└───────────────────┼───────────────────┘
│
┌──────▼──────┐
│ Nginx │
└──────┬──────┘
│
┌──────▼──────┐
│ Spring Boot │ Auth · RBAC · Core Services
│ (Java 21) │ OAuth2 · API Tokens · Audit
└──────┬──────┘
│
┌────────────┼────────────┐
│ │ │
┌──────▼───┐ ┌─────▼────┐ ┌────▼────┐
│PostgreSQL│ │ Redis │ │ Storage │
│ 16 │ │ 7 │ │ S3/MinIO│
└──────────┘ └──────────┘ └─────────┘
Backend (Spring Boot 3.2.3, Java 21):
- Multi-module Maven project with clean architecture
- Modules: app, domain, auth, search, storage, infra
- PostgreSQL 16 with Flyway migrations
- Redis for session management
- S3/MinIO for skill package storage
Frontend (React 19, TypeScript, Vite):
- TanStack Router for routing
- TanStack Query for data fetching
- Tailwind CSS + Radix UI for styling
- OpenAPI TypeScript for type-safe API client
- i18next for internationalization
SkillHub works as a skill registry backend for several agent platforms. Point any of the clients below at your SkillHub instance to publish, discover, and install skills.
OpenClaw is an open-source agent skill CLI. Configure it to use your SkillHub endpoint as the registry:
# Configure registry URL
export CLAWHUB_REGISTRY=https://skillhub.your-company.com
# Authenticate once if needed
clawhub login --token YOUR_API_TOKEN
# Search and install skills
npx clawhub search email
npx clawhub install my-skill
npx clawhub install my-namespace--my-skill
# Publish a skill
npx clawhub publish ./my-skill📖 Complete OpenClaw Integration Guide →
AstronClaw is a cloud AI assistant built on OpenClaw's core capabilities, providing 24/7 online service through enterprise platforms like WeChat Work, DingTalk, and Feishu. It features a built-in skill system with over 130 official skills. You can connect it to a self-hosted SkillHub registry to enable one-click skill installation, search repository, dialogue-based automatic installation, and even custom skills management within your organization.
Loomy is a desktop AI work partner focusing on real office scenarios. It integrates deeply with local files and system tools to build efficient automated workflows for individuals and small teams. By connecting Loomy to your SkillHub registry, you can easily discover and install organization-specific skills to enhance your local desktop automation and productivity.
astron-agent is the iFlytek Astron agent framework. Skills stored in SkillHub can be referenced and loaded by astron-agent, enabling a governed, versioned skill lifecycle from development to production.
🌟 Show & Tell — Have you built something with SkillHub? We'd love to hear about it! Share your use case, integration, or deployment story in the Discussions → Show and Tell category.
Contributions are welcome. Please open an issue first to discuss what you'd like to change.
- Contribution guide:
CONTRIBUTING.md - Code of conduct:
CODE_OF_CONDUCT.md
-
💬 Community Discussion: GitHub Discussions
-
🐛 Bug Reports: Issues
-
👥 WeChat Work Group:
Apache License 2.0
