Skill UI

A comprehensive guide for generating and manipulating images using Gemini models within a Flutter/Dart environment powered by Firebase AI. This skill covers best practices for multi-modal API calls, interpreting interleaved text and image responses, troubleshooting common setup issues (billing, App Check), and optimizing user inputs by handling downscaling and aspect ratios.

This tool initializes a dedicated AgentHub session for multi-agent collaborations. It requires defining the core task, specifying the number of parallel agents, and configuring detailed evaluation criteria (including the evaluation command, target metric, and measurement direction). Upon execution, it generates a unique session ID and prepares the entire environment for subsequent agent spawning and competitive evaluation, optionally capturing a performance baseline.

This planner skill creates a comprehensive Application Lifecycle Management (ALM) plan for deploying sites across multiple environments. It systematically gathers promotion strategies, target environments, and approval requirements, generating a visual HTML document for user review and approval. Crucially, this tool only *plans* deployments and does not execute any steps itself; subsequent individual ALM skills must be run to complete the process.

This advanced skill adjudicates name matches generated by various watchlists, including sanctions (OFAC, EU), PEP lists, and adverse media sources. It deterministically determines if a hit is a True Positive, False Positive, or requires human escalation. Designed specifically for compliance analysts, it utilizes a multi-tiered process to confirm matches and minimize false positives in high-volume screening environments.

This skill automates the final deployment phase of an agent system. It converts a validated build sheet into four ordered JSON payloads (environment, agent, session, kickoff) and generates a resumable `launch.sh` script. Crucially, this process enforces API-key safety by requiring the user to run the script in their shell, pulling the Anthropic API key from the environment variable, thus ensuring the key never appears in logs or files. It provides a structured, multi-step launch sequence.

This powerful Legal Project Management skill designs and maintains comprehensive communication architectures for complex legal matters. It guides users through four operating modes: mapping stakeholders (Mode 1), designing the communication rhythm (Mode 2), building multi-jurisdiction reporting hierarchies (Mode 3), and updating plans mid-matter (Mode 4). It ensures all relevant parties receive the appropriate information at the right time, preventing ad hoc communications and relationship surprises in high-stakes environments.

DeepSpot-M is a multimodal foundation model that generates virtual spatial transcriptomics from H&E histology images. It maps 224x224 tiles to spatial gene expression using deep learning, supporting over 19k protein-coding genes. Ideal for research in pathology and cancer genomics, requiring gated model access and Python environment.

Design and implement AWS Virtual Private Cloud (VPC) networking infrastructure. Configure subnets, route tables, security groups, and internet gateways for production environments. Supports multi-AZ architecture, VPC peering, and NAT gateway setup. Essential for establishing secure and isolated network segments within AWS cloud environments using CLI or infrastructure-as-code tools.

AWS CloudFormation enables Infrastructure as Code (IaC) for deploying AWS resources using YAML templates. It supports creating stacks, nested stacks, and managing multi-environment deployments. Features include change sets for safe deployments, drift detection, and rollback protection. Ideal for organizing large infrastructure and exporting values between stacks. Requires AWS CLI and IAM permissions.

Design robust CI/CD pipelines with approval gates and deployment strategies. Covers multi-stage flows, environment configuration, and rollback mechanisms to ensure secure and efficient software delivery.

Set up comprehensive debugging environments, distributed tracing, and diagnostic tools for development and production. Configure tracing, logging standards, and troubleshooting workflows to diagnose multi-service issues efficiently.

Define and run multi-container Docker applications using declarative YAML configuration. Ideal for local development, setting up environments, managing service dependencies, and creating reproducible setups. Supports networking, volumes, and resource limits.