Skill UI

This skill automates the process of renting, managing, and terminating cloud GPU instances on vast.ai. It analyzes your AI/ML task—determining VRAM, required GPU count, and estimated runtime—and then searches for the most cost-effective and reliable GPU offers, presenting optimized options for your training workflow.

This skill enables systematic assessment of cloud infrastructure configurations across AWS, Azure, and GCP to identify security misconfigurations such as IAM privilege escalation paths, public storage exposure, and network over-permissioning. It maps findings to MITRE ATT&CK frameworks and provides remediation guidance for preventive security management rather than active incident response.

AWS Detective automatically analyzes log data from CloudTrail, VPC Flow Logs, GuardDuty, and EKS audit logs to build interactive behavior graphs. This tool enables security analysts to investigate suspicious activity, trace lateral movement across accounts, profile compromised entities (IAM users, EC2 instances), and reconstruct complex attack timelines without manual log parsing. Ideal for triaging GuardDuty findings or investigating suspected AWS compromises.

Utilize Modal, a serverless GPU cloud, for running complex machine learning workloads, including training, fine-tuning, and inference. This tool provides a zero-config environment, eliminating the need for SSH setup or Docker management. It features automatic scale-to-zero billing and local-first execution, making high-powered GPU compute accessible for debugging and small-scale experiments.

Creates new Feishu Cloud Docs from Lark-flavored Markdown, letting you optionally target folders, wiki nodes, or knowledge spaces while ensuring structured, rich, and visually varied content.

Fetches Feishu cloud document content as Lark-flavored Markdown, extracts media tokens, and guides invoking feishu_doc_media to download images, files, and whiteboards while handling wiki token resolution.

Guidance for implementing Cloud Firestore in Flutter: selecting the database, configuring offline persistence, designing schemas, querying with filters and pagination, writing batched transactions, indexing, optimizing for scale, and avoiding write hotspots.

A guide for Flutter developers on correctly calling Firebase callable Cloud Functions. Covers setup, passing structured data to server-side logic, handling FirebaseFunctionsException and timeouts, configuring regions, and testing locally with the Emulator Suite.

Guidance for integrating Firebase Realtime Database in Flutter apps: data modeling, real-time sync, queries, offline persistence, presence, transactions, fan-out, and security rules. Choose Realtime Database for simple models and low latency or Cloud Firestore for complex querying and scalability.

Guidance for integrating Firebase Cloud Messaging (FCM) in Flutter apps: setup, permissions, token management, foreground/background handling, and platform-specific behavior.

A practical guide for using Firebase Cloud Storage in Flutter apps. Covers setup, file upload/download, metadata management, error handling, progress monitoring, and security rules.

This skill provides comprehensive functionality for reading, creating, editing, and downloading content from Lark Feishu Docs (Docx/Wiki). Whether accessing via URL or token, it supports structured content manipulation using both XML and Markdown formats (v2 API). Use it for fetching document details, updating specific blocks, and managing embedded media and resources like whiteboards and images. Note that it requires prerequisite knowledge for advanced operations.