Loading...
Loading...
Found 126 Skills
Video & Podcast Digest — send a video/podcast link, get full transcript + structured summary. Supports YouTube, Bilibili, X/Twitter video, Xiaoyuzhou, Apple Podcasts, and direct audio/video links. Uses yt-dlp for subtitles and Groq Whisper for transcription.
Summarize Hebrew tech lectures and meetings from transcription files into structured Markdown. Use when the user asks to summarize a transcription, create meeting notes, summarize a lecture/presentation in Hebrew, or mentions סיכום/תמלול/הרצאה.
Read.ai platform help — meeting intelligence with engagement/sentiment analytics, Search Copilot across meetings/email/chat, Ada digital twin, REST API (beta) + MCP Server (`api.read.ai/mcp/`), OAuth auth, webhook automations (`meeting_end` events with HMAC signing), CRM sync to Salesforce/HubSpot, Zapier/n8n workflows, 20+ language transcription. Use when setting up Read.ai webhooks or API integration, connecting Read.ai transcripts to a CRM or data warehouse, configuring Read.ai engagement analytics for a sales team, comparing Read.ai pricing tiers, troubleshooting Read.ai auto-joining meetings without permission, or setting up the Read.ai MCP server with Claude or Cursor. Do NOT use for picking between note-takers (use /sales-note-taker) or reviewing a specific call for coaching (use /sales-call-review).
Verint Open Platform help — enterprise CX automation with Da Vinci AI bots (Quality Bot 100% QA, Coaching Bot real-time guidance, Wrap Up Bot auto-summaries, CX/EX Scoring, TimeFlex agent scheduling, Exact Transcription 80+ languages), WFM forecasting/scheduling/adherence, knowledge automation, IVA virtual assistants, speech/text analytics, financial compliance, Verint Marketplace 350+ listings. Use when Verint reports loading slowly or showing inconsistent data, Quality Bot not scoring interactions correctly, Coaching Bot recommendations irrelevant, WFM forecasts off vs actual volume, Verint API integration or developer portal questions, comparing Verint vs NICE vs Genesys WEM capabilities, or connecting Verint to your CCaaS or CRM. Do NOT use for choosing between CCaaS platforms (use /sales-ccaas-selection) or for QA tool comparison across vendors (use /sales-coaching).
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support
Convert audio/video to text using Whisper, with support for word-level timestamps. Use this when users need speech-to-text conversion, audio-to-text transcription, video-to-text extraction, subtitle generation, transcribe audio, speech to text, generate subtitles, or speech recognition.
Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.
Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.
Cluely platform help — real-time AI meeting assistant with live coaching overlay, pre-call briefs, meeting notes, conversation analytics, and knowledge base RAG. Use when setting up Cluely for live AI prompts during sales calls, configuring the knowledge base with company docs for real-time RAG retrieval, connecting Cluely to HubSpot or Salesforce via Merge.dev, troubleshooting transcription accuracy or speaker attribution errors, comparing Cluely Pro vs Pro + Undetectability plans, or setting up team coaching scorecards and missed opportunity tracking. Do NOT use for choosing between AI note-takers across vendors (use /sales-note-taker) or reviewing a call for coaching (use /sales-call-review).
Omi AI wearable platform help — open-source AI necklace for all-day conversation capture (in-person + online meetings), Developer API (`api.omi.me/v1/dev`, Bearer token, 100 req/min), app marketplace with webhook integrations, memories/conversations/action-items endpoints. Use when setting up an Omi wearable for meeting capture, building a custom Omi app or integration, troubleshooting Bluetooth disconnects or transcription accuracy, connecting Omi to Slack or CRM via webhooks, comparing Omi to Plaud or Limitless for in-person recording, or accessing Omi's API to export conversations and action items. Do NOT use for choosing between software-only note-takers without wearable needs (use /sales-note-taker).
Clean and reconstruct raw auto-generated captions (Zoom, YouTube, Teams, Google Meet, Otter.ai, etc.) into readable, coherent transcripts. Use when the user provides raw caption files (.txt, .vtt, .srt), meeting transcripts with timestamps and speaker tags, or asks to clean up/refine a transcript. Handles: timestamp removal, speaker tag normalization, filler word removal, broken sentence reconstruction, transcription error correction, paragraph formation. Preserves every piece of substantive content while removing noise. Trigger phrases: 'clean this transcript', 'refine captions', 'fix this transcript', 'process Zoom captions', 'clean up meeting notes'.