AI & ML

Local approval system for managing agent permissions. Use CLI to approve/deny requests, view history, and manage auto-approved categories.

Automate project management workflows in Shortcut -- create stories, manage tasks, track epics, and organize workflows through natural language commands.

Generate, remix, and edit images using fal.ai's AI models. Supports text-to-image generation, image-to-image remixing, and targeted inpainting/editing.

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.

Automate product management workflows in Productboard -- manage features, notes, objectives, components, and releases through natural language commands.

Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera angles, lighting, color grading). Also use for character consistency sheets, voice profiles, anachronism detection, and saving scripts to Google Drive.

> **The Intelligent Connection Bridge**: A high-signal scouting agent that runs nightly to bridge you with the right people.

Deep search via Perplexity API. Three modes: search (quick facts), reason (complex analysis), research (in-depth reports). Returns AI-grounded answers with citations.

Assignment: Write an analysis of how automation is changing the job market

Use when generating visual assets with Bria.ai - product photos, hero images, icons, backgrounds. Includes batch generation (multiple images concurrently), pipeline workflows (generate → edit → remove background), and parallel API patterns. Use for websites, presentations, e-commerce catalogs, or any task needing multiple AI-generated images.

Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.

, and Midjourney would fragment this into