arilivigni/gh-skills-builder

Design, build, review, and publish GitHub Skills-style exercises with one coordinating agent and five Agent Skills for learner journeys, workflow-backed validation, and release readiness.

Installation

Copilot CLI

Install directly from this repository:

copilot plugin install arilivigni/gh-skills-builder

[!WARNING] Copilot CLI currently supports direct repository installs but marks them as deprecated. Keep this path as a fallback until this plugin is indexed in a marketplace, then prefer plugin@marketplace installs.

Or from within an interactive Copilot session:

/plugin install arilivigni/gh-skills-builder

[!NOTE] Installing from arilivigni/gh-skills-builder performs a direct repository install. You can verify the install with:

copilot plugin list

After install, manage the plugin by name (gh-skills-builder) for update and uninstall commands.

To update to the latest version:

copilot plugin update gh-skills-builder

To remove the plugin:

copilot plugin uninstall gh-skills-builder

Copilot App

1. Open the Copilot App and go to Plugins.
2. Select Add plugin, then provide arilivigni/gh-skills-builder.
3. Confirm install, then enable the plugin for your chat/session.

[!TIP] If you prefer VS Code, open the Command Palette (⌘⇧P / Ctrl+Shift+P), run Chat: Plugins, then install gh-skills-builder from the plugin picker.

Plugin format

Starting with 3.0.1, the package follows Agent Plugins v1.0.0. Root plugin.json contains metadata and the canonical $schema, without legacy agents or skills arrays. Skills are discovered from skills/*/SKILL.md. The orchestrator is a Copilot-specific component in com.github.copilot/agents/, following the Copilot CLI plugin reference.

Use a Copilot client that supports Agent Plugins v1.0.0. The plugin, agent, and five skill names are unchanged from 3.0.0. Other Agent Plugins clients can discover the skills but may ignore the Copilot agent.

What’s Included

Agent

The orchestrator loads the relevant skill for each phase. Skills own stage-specific requirements; the agent keeps sequencing, approval gates, and publication authorization explicit.

[!IMPORTANT] Review reports findings and stops before fixes. This is a behavioral rule, not a restricted tool-permission boundary: the orchestrator still has edit tools. Reviewing its own work is not independent review. If you need independent review or enforced restricted access, arrange it separately.