Skill Base Web Deploy Agent Skill
>- Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port mapping, SQLite database backup, and platform capabilities (collections, tags, GitHub import). For deploying and operating the Skill Base platform itself only.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/ginuim/skill-base --skill skill-base-web-deployThe instruction itself
12 sections, as written by the authorSkill Base Web Server Deployment
This skill guides you through setting up and operating the Skill Base platform server. Requires Node.js >= 18.
When to Use This Skill
- When users request private deployment, hosting, or running the Skill Base server (
npx skill-baseor Docker). - When users ask about Skill Base server host/port configuration (
-h,-p), data directory (-d), or how to back up the database.
When NOT to Use This Skill
- When users want to use the
skbcommand to search, install, or publish specific skills (refer toskill-base-cliinstead). - When users ask about Docker, ports, or database configuration for non-Skill Base projects (avoid misuse).
Quick Start (npm package)
# Recommended: fix the data directory for easy backup and migration
npx skill-base -d ./skill-data -p 8000
Default port is 8000; if -d is not specified, data will be stored in npm cache-related paths. In production, always use -d to point to a specific directory.
Startup Options (npx skill-base)
| Option | Description |
|--------|-------------|
| -p, --port | Listening port, default 8000 |
| -h, --host | Listening address, default 0.0.0.0 (listens on all local network cards/IPv4 addresses, accessible from both internal and external networks; set to 127.0.0.1 for local-only access) |
| -d, --data-dir | Data root directory; sets DATA_DIR and DATABASE_PATH=<dir>/skills.db |
| --base-path | Deployment base path prefix, default / (e.g., /skills/ for subpath deployment) |
| --no-cappy | Disable Cappy the capybara mascot |
| -v, --verbose | Enable debug logging |
| --help | Show help information |
| --version | Show version number |
Intranet or local hardening example: npx skill-base --host 127.0.0.1 -p 8000 -d ./data
Subpath deployment example: npx skill-base --base-path /skills/ -p 8000
Debug mode example: npx skill-base -v -d ./data
First Access
When no administrator exists, opening the site in a browser will launch the initialization wizard: create a system administrator account and password. Afterward, team members need to be added by the administrator, and users log in via Web and CLI.
Platform Capabilities (Post-Deploy)
After the server is running, the Web UI and CLI share the same backend:
| Capability | Web UI | CLI |
|------------|--------|-----|
| Browse / search skills | Yes | skb search |
| Version history & changelogs | Yes | skb update |
| Tags & favorites | Yes (admin tag library; owner assigns tags) | — |
| Collections (admin-curated packs, max 10 skills) | Browse on home | skb install --collection <id_or_slug> |
| GitHub import (public repos only) | Publish page | skb import-github |
| Desktop client | docs/desktop.md | Same install/update logic as CLI |
Collections are flat recommendation packs maintained by admins — they link to skills via collection_skills, not a folder hierarchy. Clients install the whole pack in one zip download.
Development/Production Run from Source Directory
pnpm install
pnpm start
# Or for development: `pnpm dev`
Docker (Recommended for Production)
Build in the repository root directory containing the Dockerfile:
docker build -t skill-base .
Image conventions: DATA_DIR=/data, DATABASE_PATH=/data/skills.db, PORT=8000. For host persistence, mount to /data inside the container:
docker run -d -p 8000:8000 -v "$(pwd)/data:/data" --name skill-base-server skill-base
If you need to change the port, map both host and container ports and set PORT, e.g., -p 3000:3000 -e PORT=3000.
Data Directory Structure (Backup)
After specifying -d or mounting /data, typical contents:
data/
├── skills.db
├── skills.db-wal
└── skills/
└── <skill-id>/
└── vYYYYMMDD.HHmmss.zip
Backup: Simply copy the entire data directory during low write activity or off-peak hours.
Troubleshooting Tips
- Port: Ensure firewall/security groups allow
PORT; cloud hosts need to allow corresponding inbound traffic. - CLI can't connect: Client uses
skb init --server <root URL>(without/api); verify the site is accessible from that machine. - Permissions: The
-dpath must be readable/writable by the process; for Docker volumes, check host directory permissions.
Relationship with skill-base-cli
After deploying the Web server, users on the client side use skb pointing to the same site root URL; see the skill-base-cli skill within the project.
Other skills for the same job
different authors, same section of the catalogue
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
How to use it
Take ginuim/skill-base-web-deploy from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm, npx, docker.
Without those the skill loads but fails at the first command.