productivity▌

Build visually engaging scientific presentations with AI-generated slides, research-backed citations, and professional design. \n \n Generates complete slide decks as PDF images using Nano Banana Pro AI, with support for PowerPoint and LaTeX Beamer workflows for editable or publication-quality output \n Enforces visual-first design philosophy: high-quality figures, diagrams, and graphics dominate each slide, with minimal text (3–4 bullets, 4–6 words each) serving as speaker notes \n Integrates r

32 specialized agents with smart model routing, persistent execution loops, and real-time visibility for Claude Code workflows. \n \n Six orchestration modes (Team, Autopilot, Ralph, Ultrawork, Pipeline, Swarm) handle everything from coordinated multi-stage pipelines to autonomous single-agent execution and maximum parallelism \n Team mode runs a canonical five-stage pipeline: plan → PRD → execute → verify → fix, with automatic looping until tasks complete \n Magic keywords (autopilot, ralph, ul

Client-side SDK for database queries, authentication, file uploads, AI features, real-time messaging, and edge function invocation. \n \n Six core modules: Database (CRUD, filters, RPC), Auth (sign up/in, OAuth, sessions), Storage (upload/download/delete), Functions (edge function invoke), AI (chat, image generation, embeddings), and Real-time (WebSocket channels, publish/subscribe) \n All SDK methods return { data, error } objects; database inserts require array format and storage operations ne

Use this skill when the user asks about:

Skill by ara.so — Daily 2026 Skills collection

Provides expertise in Natural Language Processing systems design and implementation. Specializes in text classification, named entity recognition, sentiment analysis, and integrating modern LLMs using frameworks like Hugging Face, spaCy, and LangChain.

Colosseum Copilot is a research API for startup opportunity discovery in crypto and Solana, with support for suggesting new archive sources.

Use this skill to understand how .NET code works internally by decompiling compiled assemblies.

Comprehensive Ktor patterns for building robust, maintainable HTTP servers with Kotlin coroutines.

Native Home Assistant constructs for automations, helpers, scripts, and Lovelace dashboards. \n \n Prioritizes built-in conditions, triggers, and helpers over Jinja2 templates; includes decision workflow for choosing between native state conditions, numeric_state, time triggers, and template helpers \n Covers automation modes (single, restart, queued, parallel) with scenarios, entity_id vs device_id usage, and Zigbee button/remote patterns for ZHA and Zigbee2MQTT \n Provides safe refactoring wor