AI Skills for Google Gemini

Extracts structured data from LLM responses using schema-constrained decoding for reliable JSON and typed objects.

RecallMax enhances AI agents with long-context memory, auto-summarizing and compressing conversations while preserving tone and intent.

Builds a low-latency voice assistant inspired by Iron Man using Pipecat, Google Gemini, and OpenAI technologies.

Facilitates autonomous multi-step research using Google Gemini for market analysis, competitive landscaping, and technical reviews.

Facilitates application development using Gemini API for multimodal content, function calling, and structured outputs.

AegisOps-AI automates security and financial audits for DevSecOps, enhancing compliance and cost management in cloud environments.

Generates images using Google Gemini for UI placeholders, documentation, and design assets, enhancing visual content creation.

Generates high-quality AI illustrations for academic papers using a multi-stage workflow with strict supervision for optimal results.

Generates high-quality figures for ML papers by extracting data and relationships, utilizing Gemini for diagrams and matplotlib/seaborn for charts.

Generates efficient prompts for AI tools, optimizing communication and reducing token waste for better results.

Automates Google Vertex AI multimodal operations based on context detection and relevant triggers for efficient workflows.

Generates and edits images using Nano Banana Pro, supporting text-to-image and image-to-image transformations in various resolutions.

Provides a dual-layer AI content guardrail to ensure safe communication from AI agents, utilizing a judge model for output evaluation.

Configures NewCLI as a model source for OpenClaw, enabling access to various AI models including Claude and GPT.

Summarizes text and transcripts from URLs, podcasts, and local files, providing quick insights and content extraction.

Builds RAG pipelines for enhanced research and fact-checking using web search and LLMs, ensuring accurate and grounded AI responses.

Summarizes text and transcripts from URLs, podcasts, and local files, providing quick insights and best-effort transcriptions.

Generates high-quality AI illustrations for academic papers using a multi-stage workflow with Claude supervision.

Automates Google Vertex AI multimodal operations based on context detection, enhancing workflow efficiency and error handling.

Generates and edits images using Nano Banana Pro, supporting text-to-image and image-to-image transformations in various resolutions.