kasetto

Kasetto is a declarative AI agent environment manager for syncing skills and MCP configs across one or many supported agents.

Use This Skill When

You need the right kst command, flag, or config shape for install, sync, inspection, cleanup, upgrade, uninstall, or completions.
You need to create or debug a kasetto.yaml config for skills or MCP sources.
You need to target agent presets such as Codex, Cursor, Claude Code, OpenCode, Copilot, Gemini CLI, or Windsurf.
You need to understand non-interactive output, auth for private git hosts, or version-specific behavior.

First identify the task type: install/setup, config authoring, sync/list/doctor/clean, MCP integration, auth, or upgrade behavior.
Read only the relevant reference file instead of loading everything.
Prefer exact upstream command syntax and the smallest config that solves the user's case.
For automation or CI, prefer documented non-interactive options such as --json, --plain, NO_TUI=1, and --dry-run when appropriate.
Call out destructive commands like kst clean and kst self uninstall before recommending them.
Start from bundled examples when the user needs a config snippet or a quick command sequence.