Skill UI

This skill monitors the progress, blockers, and task ownership of an AI team. It summarizes completed, active, and blocked work while distinguishing assertions from verified evidence. It surfaces decisions for the user and ensures budget reporting accuracy without claiming unverified execution.

Generate adult (18+) images, image-to-video clips, and image edits via SpicyAPI with cost quotes, consent checks, and explicit user confirmation.

This skill manages and stores approved team context securely using RuVector isolation. It ensures tenant-local data privacy by excluding sensitive credentials and personal information. During retrieval, it preserves provenance and treats data as untrusted. It prevents memory transfer between teams, maintaining strict security boundaries for AI team operations.

This skill enables reviewing AI team results against acceptance criteria using an evidence bundle. It involves retrieving task artifacts, separating verified facts from assertions, and identifying missing work. It ensures completion recommendations are made only when all criteria are met with evidence, while reporting budget accurately without billing implications.

This skill provides advanced guidelines for designing robust and effective tools specifically for autonomous AI agents. It shifts the focus from traditional developer APIs to contracts optimized for Language Models (LLMs). Key topics covered include treating tool descriptions as prompt engineering, implementing namespacing, applying the Consolidation Principle, and utilizing Architectural Reduction patterns (like file system access) to maximize agent reliability and workflow complexity.

An advanced reliability wrapper for AI agents that monitors, manages, and recovers from tool call failures. It automatically handles common issues such as truncated JSON responses, API timeouts, rate limits, and mid-chain process breakdowns. By implementing sophisticated failure classification, checkpointing, and learning mechanisms, Guardian ensures complex, multi-step agent workflows remain stable and resilient.

Fetch and explain TraderSpy's AI crypto futures signals: entry, take-profit ladder, stop, triggers, status against the live price, and how recent signals resolved. Use for 'latest signals'.

Train or fine-tune SentenceTransformer, CrossEncoder, and SparseEncoder models for retrieval, similarity, clustering, classification, reranking, and embedding tasks. This skill provides production-ready templates with proper loss functions, evaluators, and training configurations for various NLP tasks including bi-encoder, reranker, and sparse vector models.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes like Node.js, Bun, and Deno, enabling text analysis, image classification, speech recognition, and multimodal AI applications without a Python backend.

Analyzes travel health data, assesses destination health risks, provides vaccination recommendations, and generates multilingual emergency medical cards. Supports WHO/CDC data integration for professional-grade travel health risk assessment.

Train and fine-tune transformer language models with Hugging Face TRL via CLI. Covers SFT, DPO, GRPO, RLOO, KTO and reward model training, plus LoRA adapters, YAML configs and distributed multi-GPU runs.

Operate and evaluate a local Unified AI System through governed MCP tools without provider credentials. This skill enables secure inspection of AI gateways, including prompt enhancement and authorization boundaries, ensuring safety through content review and Docker image analysis before deployment.