tnghia903

Loomwatch — AI skill for Claude Code

AI community

Put your AI apps to work as a team.

How to install Loomwatch

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tnghia903/loomwatch and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Loomwatch does

Put your AI apps to work as a team. Connect Claude Code, Codex and OpenCode on one canvas, ask in plain words, watch every step, and approve the work before the next agent builds on it. Free, open source, runs on your Mac.

Alternatives in AI

  • Business Model — Generate Business Model Canvas with all 9 building blocks 7.8k ★
  • AI Research SKILLs — Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code 5.7k ★
  • Agent Watch Approve — ⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 Approve your AI coding agent's risky actions from your 121 ★

README

LoomWatch. Put AI agents to work as a team. Build a team from the AI apps already on your computer, ask in plain words, and review every step before you use the result.

Quickstart · How it works · Features · Recipes · First run · FAQ · Guides

Runs on your computer Platform: macOS First run: offline demo, no AI account Agents over ACP Built with Rust and React

The offline demo in LoomWatch: a three-step team is built, the request is typed, the team pauses for the operator's review, the operator approves, and the team response appears with a run receipt.
The bundled offline demo: build a team, ask in plain words, approve at the review step, read the result.

**Install on a Mac** (macOS 11 or newer, with [Docker Desktop](https://docs.docker.com/desktop/) or [OrbStack](https://orbstack.dev/)), then follow [Try your first run](#try-your