Backend

Generate music using ElevenLabs Music API.

Use ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation.

Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine.

Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer…

Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API.

FunSearch (Program Search) method skill.

Searches current documentation, release notes, API references and public repository issues for libraries, frameworks, SDKs, APIs and CLI tools with `firecrawl…

Use when doing ANY task involving Supabase.

Configure Claude Code authentication for Cyrus — API key, OAuth token, or third-party provider.

Sets up and manages Postgres using the clickhousectl CLI — runs a local Docker-backed Postgres for development, and creates and operates managed ClickHouse…

Write, edit, or debug JavaScript that uses the Note Toolbar `ntb` API inside Obsidian.

Build a music video from an existing song and lyrics, either as p5.js/p5.brush animation or by assembling local images and clips.

Add ElevenLabs to a project from scratch.

Fix or hand-configure an existing ElevenLabs API key.

Use MCP (Model Context Protocol) servers from bash with `shelley mcp`.

Use when the user needs Node.js or npm installed, or is running a JS framework dev server (Next.js, Vite, webpack, etc.) on an exe.dev VM — especially if the…

Write, return, validate, or troubleshoot character-faithful spoken replies for RabiRoute's current RabiSpeech workflow.

Email marketing operating manual for AI agents, with hard send-safety gates.

Generate TypeScript/JavaScript code that reads/decodes AND writes/encodes ClickHouse RowBinary streams for the ClickHouse HTTP server.

PostgreSQL best practices, query optimization, connection troubleshooting, and performance improvement.

Design and build use cases, POCs and production systems with TypeSafe's Jev decision model (System One): choose a design mode and a use-case archetype, build…

Use this skill when implementing/refactoring frontend/backend code and you need Dekart-specific conventions for naming, code organization, architecture…

运行或更新 RabiSpeech 本机语音模型闭环基准。用于新增、替换或比较本地 TTS / ASR 模型，测试首请求、加载、预热、热态耗时、RTF、显存、波形和 CER，并从统一公开语料生成 JSON、CSV 及 RibiWebGUI 内可查看的 HTML 报告；也用于维护 TTS / ASR…

通过 RabiSpeech 的本地 IndexTTS2 模型生成中文或音色复刻语音。用户指定 IndexTTS2、中文参考音频、情绪/风格指令、角色声线或本地 WAV 验证时使用。不得直接运行技能内 worker、启动 OumuQ 或调用云端 API。