Livestream Skill: Warehouse Audio Pipeline
Warehouse audio pipeline for live capture, transcription, and narration from meeting room mics via Tailscale. Triggers: livestream, warehouse audio, transcription pipeline, meeting capture, whisper.
Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.

Warehouse audio pipeline for live capture, transcription, and narration from meeting room mics via Tailscale. Triggers: livestream, warehouse audio, transcription pipeline, meeting capture, whisper.
Headless University of Toronto Outlook email access via IMAP/SMTP with OAuth2. Uses Thunderbird's pre-authorized client ID to bypass admin consent requirements (AADSTS65002). Device code flow for initial auth, macOS Keychain for token cache.
Voice Channel UWD Skill
Unified messaging via Beeper Desktop MCP. Search chats, send messages, manage conversations across all networks (iMessage, WhatsApp, Signal, Telegram, Discord, Slack, etc.)
Community knowledge from bivector.net - GA tutorials, discussions, and best practices
Use macOS text-to-speech for agent narration and announcements. Sub-agents announce themselves using different language voices speaking English. Use for multi-agent workflows where each agent has a distinct voice identity.
ACSet-structured messaging world with real social graph resources from Outlook, Gmail, and Beeper
Scrivener project format internals, data model, and programmatic access. Use when parsing .scriv bundles, querying DuckDB exports, extracting manuscript text, or building AI-assisted novel tools from Scrivener data. Covers Windows-origin projects, cross-platform migration, and RTF content.
Deep multi-source research combining academic MCPs (arxiv, semantic-scholar, paper-search, deepwiki), Exa semantic search, and local ~/.topos knowledge base. Use for comprehensive research requiring multiple sources. NEVER fall back to web_search - ask user for help instead.
Remove signs of AI-generated writing from text to make it sound more natural and human-written. Use when editing or reviewing any form of document including: markdown, technical docs, emails, blog posts, PRDs, or any dedicated writing content. Based on Wikipedia's comprehensive "Signs of AI writi...
Bilingual German-English pun generator with Fröhlich.jl color mapping
Record, stream, and replay libghostty-vt terminal sessions for documentation, debugging, and LLM training.
Analyze video files from chaotic_media_lake.duckdb with deterministic color assignment and GF(3)-balanced trit allocation.
Digital forensics techniques for detecting device compromise, analyzing malware indicators, and investigating targeted surveillance. Based on methodologies from Citizen Lab's Pegasus Project and Predator investigations.
Large-scale graph analytics for entity resolution, network analysis, and relationship mapping. Based on methodologies from Project Domino (1B+ node COVID misinformation graphs) and ICIJ's Panama/Paradise Papers investigations.
Document processing pipeline for large-scale leak analysis. Based on ICIJ's methodologies from Panama Papers, Paradise Papers, and Pandora Papers investigations. Coordinates between forensic validation (-1) and graph generation (+1).
Transform single property/neighborhood images into photorealistic 3D Gaussian Splats using Apple's ml-sharp, enabling virtual walkthroughs from a single photograph. Bridge to PropertyPriceOracle for valuation analytics.
Gene correlation network analysis bridging WGCNA, pgmpy Bayesian networks, and monad-bayes posterior inference. Connects zubyul's genomics background to the plurigrid interactome via HyperNetX hypergraph topology.
Bridge layer connecting Vertex AI / Google Cloud to plurigrid/asi protein-scale biology skills. Wires AlphaFold, ESM, DiffDock, DeepChem, and TorchDrug into Vertex AI Pipelines, Endpoints, and BigQuery genomics for protein design-predict-validate loops.
- `alphafold-database` - Protein structure prediction
Automate "one sec" app-blocking setup on iOS via Shortcuts automations using WebDriverAgent (WDA). Use when the user wants to bulk-configure one sec for multiple apps on a connected iPhone.
Build, deploy, and manage the MagicTodoWatch iOS/watchOS voice-to-task pipeline app. Use when building for device or simulator, fixing Xcode project issues, or running the 7-world backend pipeline.
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.