Extract semantic context from ScreenApp recordings via a CLI pipeline.
npx skills add https://github.com/Zpankz/mcp-skillset --skill screenapp-cli
Please help me install this Agent Skill. Skill: screenapp-cli Source: https://github.com/Zpankz/mcp-skillset/tree/main/screenapp-cli Command: npx skills add https://github.com/Zpankz/mcp-skillset --skill screenapp-cli
ScreenApp CLI addresses the challenge of making multimodal media (video, audio transcripts, screen captures) searchable and context-rich by providing a unified command-line interface that surfaces organized context through transcripts, frames, and graph-based associations.
Run screenapp config init to bootstrap the CLI and begin indexing your recordings.
High-intent search queries and answers about installing and using this skill.
To make multimodal video recordings searchable, you can extract semantic context from transcripts, video frames, and screen captures using a unified CLI pipeline. This enables per-recording queries, speaker analysis, and cross-recording graph-based relevance searches.
Yes, you can perform cross-recording semantic searches by applying graph-based context retrieval over embeddings. This surfaces topic extraction, speaker linking, and similarity relationships across multiple video transcripts and screen captures.
You can extract topics and analyze speakers from multimodal meeting recordings by applying semantic extraction to transcripts and video frames. Graph-based context maps the speaker linking and topic associations for targeted retrieval.
Yes, the ScreenApp CLI supports exporting transcripts and context to formats like Obsidian. You can integrate these workflow pipelines into daily digests, enabling structured context retrieval from your multimodal recordings.
The best way to query time-segmented video frames and screenshots is through multimodal AI queries within the CLI. This allows you to analyze specific video segments, obtain AI insights, and retrieve relevant context directly from the visual data.
Yes, you need to run the configuration initialization command to bootstrap the CLI before indexing your multimodal screen recordings. This setup establishes the necessary environment for file operations and graph-based embeddings.
CharlesWiltgenProvides AVFoundation audio API reference for iOS apps.
pacphiSummarize web articles and YouTube transcripts into structured notes for Logseq or Obsidian.
PixelMLIngest video files into a searchable database with transcription and embeddings.
barefootfordTranscribes video audio into timestamped JSON transcripts with word-level timing using WhisperX.
