Skill UI

Guides teams through migrating complex AI agents into Lindy with scope assessment, consolidation, phased rollouts, data transforms, rollback checks, and validation checklists for production readiness.

Reasoning-Driven Image Briefs skill transforms agent prompts into logic-based Gemini 3 style instructions for muapi.ai, adding structured creative briefs (subject/action/context/composition/lighting), precise text cues, and physics-grounded constraints before invoking generation scripts.

Reference for building Graph Neural Networks with PyTorch Geometric, covering data objects, datasets, transforms, convolution layers, lazy initialization, and heterogeneous support so you can quickly tackle node, link, and graph tasks.

Transforms vague or inconsistent prompts into precision-engineered instructions so any LLM delivers structured, hallucination-resistant, token-efficient outputs.

A comprehensive solution for building advanced, intelligent voice skills for Amazon Alexa. This system transforms standard Alexa devices into ultra-smart assistants by integrating the power of Claude (LLM) as the core brain. It utilizes the full AWS ecosystem, including Lambda, DynamoDB, Polly, and Lex, to enable complex functionalities like smart home control, persistent memory, and natural language understanding.

Transforms a refined research proposal or method idea into a concise, claim-backed experiment roadmap, covering ablations, evaluation protocols, compute budgets, and execution order so papers can defend the problem, novelty, and any LLM/VLM/Diffusion/RL contribution.

Transforms Claude Code into a continuous autonomous agent with persistent memory, scheduled operations, remote dispatch, computer automation, and task queuing for repeatable workflows and monitoring.

Transforms user articles, reports, or documentation into natural two-host conversational podcasts by building structured JSON scripts and running the bundled TTS pipeline to emit MP3 audio plus transcripts.

Transforms Finnish text by spotting 26 AI markers (12 language-specific, 14 universal) and rewriting them to match native rhythms, so prompts or .md/.txt content read like human-written copy.

Transforms the AI into a highly personalized virtual tutor, adopting a defined persona, teaching style, and emotional relationship. This skill uses the Socratic method and advanced psychological principles (like Self-Determination Theory and memory scaffolding) to guide users through discovery learning. It doesn't just deliver answers; it fosters genuine engagement, maintains continuity across sessions, and motivates the user to learn by simulating the experience of a caring, challenging human mentor.

Reference for building Graph Neural Networks with PyTorch Geometric, covering data objects, datasets, transforms, convolution layers, lazy initialization, and heterogeneous support so you can quickly tackle node, link, and graph tasks.