Voice mode for Claude Code: reads assistant replies aloud (TTS) with auto language detection (de/en) and optional summarization. Also provides the WhatsApp / Telegram / Discord / Slack / Email bridges that funnel inbound messages into a Claude subprocess.
1 skill · 42 commands · hooks
Multi-Persona-Layer for Claude Code. Per-chat agent roles (Coder, Browser, Inbox, Research, ...) — each with its own tools, MCP servers, and system prompt. Optional, on top of voice or standalone.
1 skill · 7 commands
CorvinOS install and update from Claude Code. /corvin:install runs the installer of your local CorvinOS clone (repo-only — nothing is downloaded) and verifies the console really serves the app; /corvin:update checks origin/main for a newer version, runs the clone's updater (with automatic rollback) and re-verifies. Both are safe to re-run.
2 commands
Runtime tool generation: chat-pinned personas can register and execute schema-bound tools, sandboxed via bubblewrap + rlimits, hash-chain audited, with task/session/project/user scope routing.
1 skill
Runtime skill generation: chat-pinned personas can create Markdown skills with front-matter and prompt-inject them into sub-agents. Lint-gated, hash-chain audited, auto-purges ungraded skills after 7 days.