What problem does it solve? Coordinating AI agent squads that run on different machines, CI runners, or partner organizations is hard because agents can only read local files. This Skill solves that by using git as the transport layer to materialize remote squad state onto the local filesystem before agents read it. ## Core Features & Use Cases - Mesh topology configuration: Generates a mesh.json file mapping each squad to a zone (local, remote-trusted, or remote-opaque) with its connection details. - Bundled sync scripts: Copies pre-built sync-mesh.sh and sync-mesh.ps1 scripts that pull Zone 2 state via git and fetch Zone 3 published contracts via HTTPS. - State repo initialization: Scaffolds a shared mesh state repository with per-squad directories and placeholder SUMMARY.md files using the --init flag. - Use Case: A developer laptop squad and a CI squad need to share results. The skill generates mesh.json, installs the sync scripts, and each squad runs git pull before work and git push after, with write partitioning preventing merge conflicts. ## Quick Start Ask the agent to set up a distributed mesh for your squads and answer its questions about which squads participate and which zone each one belongs to.
