953 skills · sorted by relevance
Build Java applications that exchange live audio with AI assistants using Azure AI VoiceLive. The skill covers authentication, streaming sessions, speech detection, voice selection, transcription, and handling responses over WebSocket, a persistent two-way connection.
Build AI agents that make phone calls and send or receive SMS through the AgentPhone API. Manage phone numbers, configure voice agents and event notifications, and inspect call transcripts and account usage.
Analyze Claude Code session transcripts and create an interactive HTML usage report. Explore token consumption, cache performance, subagents, skills, and costly prompts, with findings and improvement suggestions tied to the actual usage data.
Build a connected Markdown Wiki from documents, notes, transcripts, research, and code. Organize knowledge by subject, attach evidence to claims, maintain a navigation index, and integrate new material into existing pages while preserving disagreements and context.
Manually sync OpenClaw chat transcripts to OpenViking and search stored memories using explicit commands. Receive a sync summary or relevant memory entries while leaving the OpenClaw contextEngine slot available for its existing use.
Turn internal meeting transcripts or notes into concise minutes that emphasize decisions and next steps. Record attendees, decision reasons, assigned actions with deadlines, unresolved issues, and references in a consistent format for team follow-up.
Manage Google Meet meeting spaces and conference records through the gws command. Create or update spaces, end active conferences, and work with meeting records and related participants, recordings, smart notes, and transcripts.
Transcribe audio files through 9Router using models from providers such as OpenAI, Groq, and Deepgram. Receive plain text, structured results with timestamps, or SRT and VTT subtitles, depending on the selected model’s support.
Build custom browser video applications with Zoom Video SDK using JavaScript or TypeScript. Guidance covers session setup, participant video rendering, screen sharing, recording, and live transcription, with implementation patterns and troubleshooting for common integration problems.
Keep customer records and sales deals current using emails, meetings, and call transcripts. Prepare activity summaries, follow-up drafts for quiet deals, cleanup proposals, and a next-step queue with owners and dates.
Find customers’ exact words about a feature, objection, or competitor across meeting transcripts and emails. Organize quotes with speaker details, dates, sources, and context, while showing which accounts lack source coverage.
Analyze closed sales opportunities to explain patterns behind wins and losses. Compare win rates, deal sizes, and sales stages, then use available transcripts and emails to recommend evidence-based process improvements and coaching priorities.
Record founder-approved decisions with chosen options, success measures, stop conditions, and dissent. Keep approved decisions separate from discussion transcripts so future advisory sessions use confirmed choices, with a review scheduled after 90 days.
Keeps board meeting transcripts separate from founder-approved decisions, with owners, deadlines, and action items. Supports decision searches, overdue reviews, and conflict checks so later meetings can refer to approved outcomes without treating rejected proposals as agreements.
Turn speech from audio or video recordings into text using OpenAI. Save transcripts as text or JSON, with optional speaker labels and reference recordings to help identify known speakers in meetings or interviews.
Check Screenpipe's process, API, screen capture, and audio transcription status. Inspect logs, storage, resource usage, and processing metrics to identify problems, then report the findings with relevant errors and suggested fixes.
Generate a client in your chosen language for live, two-way communication with Gemini Enterprise LiveAPI. Includes token renewal, session recovery, tests, and a demo interface for trying text, audio, video, and transcription.
Turn a sales call transcript into an updated HubSpot deal, Linear tasks for commitments, and a recap email draft. Ambiguous deal matches are flagged for a person to check, and the email stays unsent for the representative's review.
Compare options through a debate among agents given distinct expertise and positions for the topic. Choose a three-round discussion with a visible transcript and synthesis, or a one-round check that presents initial perspectives.
Answer questions about videos from URLs or local files using timestamped visual and spoken evidence. Choose extracted frames and transcripts, or let Gemini view the full video with a configured API key.
Prepare video clips with yt-dlp, whisper, and ffmpeg, covering downloads, speech transcription, subtitle files, trimming, and vertical formatting. Also includes methods for adding generated speech and sending finished videos through messaging APIs.
Find 飞书 meeting records, AI notes, and transcripts, or create and edit 妙记 recording summaries. Review ongoing meeting content, let an application bot join, and send chat messages during meetings.
Analyze meeting transcripts to understand speaking habits, interruptions, conflict avoidance, and listening patterns. Get specific examples with timestamps and practical suggestions, then compare meetings over time to track changes in communication and facilitation.
Help QM organization admins inspect settings, stored memory, conversations, files, and operational records across the organization. It also supports confirmed configuration changes and external user management, while keeping admin grant changes in the dashboard.