Unicli Hub banner
teelukira teelukira

Unicli Hub

AI community

Description

A unified context management hub for AI CLI tools. Synchronize your agent.md, skills, and memory across Cursor, Claude Code, Kiro, and Gemini CLI.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

UniCLI-Hub

UniCLI-Hub is a mock/reference framework for keeping AI CLI configuration in one canonical place and fanning it out to multiple tools.

It is not an application project and should not contain customer, product, or delivery-workstream context. Its purpose is to demonstrate and maintain the mechanics for shared agents, skills, hooks, MCP servers, memory, and generated entry documents across AI CLIs.

For Korean documentation, see [README.ko.md](./README.ko.md).

What This Framework Does

UniCLI-Hub treats `hub/` as the single source of truth and renders generated files into tool-specific locations:

Asset Canonical source Generated targets
Entry docs .unicli-hub/templates/*.tmpl, hub/memory/, hub/project-context.md AGENTS.md, CLAUDE.md
Agents hub/agents/ .claude/agents/, .cursor/agents/, .agents/, .kiro/, .codex/agents/
Skills hub/skills/ .claude/skills/, .cursor/skills/, .agents/skills/, .kiro/steering/skill-*.md, .codex/skills/
Hooks hub/hooks/, hub/registry/hook-events.json .claude/settings.json, .cursor/hooks.json, .agents/settings.json
MCP servers hub/mcp-servers.json .mcp.json, .cursor/mcp.json, .agents/mcp_config.json, .codex/config.toml
Memory hub/memory/*.md embedded in generated entry docs

Supported CLIs

CLI Derived location Entry point
Antigravity / agy .agents/ AGENTS.md
Claude Code .claude/ CLAUDE.md
Cursor .cursor/ AGENTS.md plus Cursor files
Kiro .kiro/ generated steering and agent files
OpenAI Codex .codex/ AGENTS.md plus agent and skill files

Tool Capabilities (Skills, Subagents, MCP)

Different AI CLIs handle extended capabilities in their own distinct ways. This framework abstracts these differences, but it is helpful to understand how each tool implements them:

1. Google Antigravity (agy)

  • Skills: Fully support