skills.rest
hashimiche
hashimicheCOMMUNITY
Explore all skills by this author →
GitHub

plus

Deploy HAL Plus as a local web UI for HAL, proxied to Ollama and HAL MCP.

29|8|Updated Mar 24, 2026
Search Tags:#ui#mcp#ollama#model-management#hal#hal-plus
One-click install
npx skills add https://github.com/hashimiche/hal --skill plus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: plus
Source: https://github.com/hashimiche/hal/tree/main/internal/skills/data/plus
Command: npx skills add https://github.com/hashimiche/hal --skill plus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

HAL Plus provides a local web UI layer for HAL, allowing users to run and manage the HAL Plus service with a straightforward, container-native deployment. It bridges the HAL MCP runtime with an Ollama-backed model, enabling interactive queries and model switching without external hosting.

Core Features & Use Cases

  • Local web UI: Launch HAL Plus alongside HAL MCP to provide a browser-based interface.
  • Model management: Switch between presets like qwen3.5 and gemma4 for different performance profiles.
  • Health and connectivity: Verify the health of HAL Plus, its connection to Ollama, and its access to HAL MCP within the same network.
  • Use Case: A developer wants a local UI to test queries, adjust models, and confirm connectivity with Ollama before integrating into workflows.

Quick Start

Run hal plus create to start HAL Plus and hal plus status to verify.

Frequently Asked Questions about plus

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I launch a local web UI for Ollama and HAL MCP?▼

To launch a local web UI for Ollama and HAL MCP, use HAL Plus. It deploys a container-native browser interface that bridges the HAL MCP runtime with an Ollama-backed model for interactive queries.

What are the requirements to run HAL Plus in a single-host environment?▼

Running HAL Plus requires Ollama running on the host and HAL MCP on the same container network. It accesses Ollama via host.containers.internal:11434 and defaults to the qwen3.5 model preset with a 32k context.

How do I switch models in HAL Plus?▼

You can switch models in HAL Plus using its model management feature. It allows you to toggle between presets like qwen3.5 and gemma4 directly from the local web UI to apply different performance profiles.

How can I verify the connectivity between HAL Plus, Ollama, and HAL MCP?▼

Verify connectivity by running health checks in HAL Plus. You can confirm the service status and its connection to Ollama and HAL MCP within the same network using the status command.

Does HAL Plus need external hosting to manage local models?▼

No, HAL Plus does not need external hosting to manage local models. It operates entirely as a local web UI layer, enabling interactive queries and model switching without relying on external infrastructure.

Related Skills

Explore More Software Engineering Skills→
jeffreykthomasjeffreykthomas

add-ollama-tool

Expose on-host Ollama models to NanoClaw agents via an MCP server.

Community
Intermediate
arthrodarthrod

browser-test-agent

Automate web browser interactions and quality assurance testing for local development environments.

Community
Advanced
TitoPrauseeTitoPrausee

ollama-launch-setup

Configures Ollama launch integrations for third-party coding agents.

Community
Intermediate
euroconiceuroconic
1

local-model-management

Automate local AI model lifecycle management with startup sequencing and health monitoring.

Community
Advanced