Skill UI

Analyzes token implementations and integrations with ERC20/ERC721 standards, checks 20+ weird token patterns, assesses owner privileges, contract composition, and on-chain scarcity to highlight risks before deployment.

Automate Token Metrics operations through Composio’s toolkit by orchestrating Rube MCP searches, connection checks, and schema-compliant executions so every `RUBE_MULTI_EXECUTE_TOOL` call runs with up-to-date tooling details and pagination awareness.

Orchestrates Tomba tasks through Composio’s toolkit and Rube MCP, guiding initial schema discovery, connection checks, and schema-compliant executions so automation stays aligned with live tool definitions.

Uses Rube MCP and Composio's Tomtom toolkit to automate Tomtom workflows, from fetching live tool schemas with `RUBE_SEARCH_TOOLS` to validating `RUBE_MANAGE_CONNECTIONS` status and executing `RUBE_MULTI_EXECUTE_TOOL` calls with schema-compliant arguments.

Scans FunC-based TON smart contracts for boolean, Jetton, and gas handling vulnerabilities, reporting critical issues with file references and offering remediation guidance for auditors and secure dApp launches.

Coordinates Toneden operations through Composio's Rube MCP toolkit, ensuring tool discovery, connection validation, and schema-compliant executions for marketing workflows.

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.

Provides a structured reference covering the 100 most critical web vulnerabilities, including definitions, root causes, impacts, and mitigation guidance aligned with OWASP categories to support assessments and remediation planning.

Provides a structured reference of the 100 most critical web application vulnerabilities organized by category, helping security teams identify attack vectors, assess impacts, and follow remediation guidance during audits or penetration tests.

torchforge is Meta's advanced PyTorch-native library designed for agentic Reinforcement Learning (RL). It fundamentally separates core RL algorithms from complex distributed infrastructure concerns. This allows researchers to rapidly prototype and experiment with novel RL methods (like GRPO) using clean, PyTorch-native abstractions, while automatically handling large-scale tasks like distributed training across thousands of GPUs using Monarch and TorchTitan.

Assists with torchscript exporter tasks for ML deployment, offering automated guidance, code/config generation, and validation against industry standards whenever torchscript exporters are mentioned.

Automates generating TorchServe deployment configurations with guided best practices for model serving, MLOps pipelines, inference, and production monitoring so ML deployment workflows stay consistent and reliable.