Loading...
Loading...
Found 889 Skills
Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasked with recovering internal parameters (weights, biases) of a neural network that can only be queried for outputs, particularly two-layer ReLU networks. Use this skill for model extraction, model stealing, or neural network reverse engineering tasks.
Analyze footnotes and accounting policies from SEC filings using Octagon MCP. Use when researching revenue recognition policies, critical estimates, lease obligations, pension assumptions, stock compensation, contingencies, and new accounting pronouncements.
Catalog of non-obvious behaviors, gotchas, and platform-specific quirks in MultiversX that often lead to bugs. Use when debugging unexpected behavior, reviewing code for subtle issues, or learning platform-specific pitfalls.
Skill for working with the Lucid Agents SDK - a TypeScript framework for building and monetizing AI agents. Use this skill when building or modifying Lucid Agents projects, working with agent entrypoints, payments, identity, or A2A communication. Activate when: Building or modifying Lucid Agents projects, working with agent entrypoints, payments, identity, or A2A communication, developing in the lucid-agents monorepo, creating new templates or CLI features, or questions about the Lucid Agents architecture or API.
Guides error handling in Zhin using the built-in error hierarchy, ErrorManager, RetryManager, and CircuitBreaker. Use when implementing resilient error handling, retry logic, or circuit breaker patterns in Zhin plugins.
Guides interactive user input collection using the Zhin Prompt class. Covers text, number, confirm, list, and pick prompts with timeout handling and Schema-based input. Use when a plugin needs to collect input from users in a conversational flow.
Guides setup and usage of the Zhin MCP (Model Context Protocol) server plugin. Covers configuration, available tools, resources, and prompts for AI assistant integration. Use when integrating Zhin with AI coding assistants like Claude or Cursor via MCP.
Guide for performing linear cryptanalysis attacks on FEAL and similar Feistel ciphers. This skill should be used when tasks involve breaking FEAL encryption, recovering cipher keys using known plaintext-ciphertext pairs, or implementing linear cryptanalysis techniques. Applies to cryptographic challenges mentioning "linear attack," "FEAL," "Feistel cipher analysis," or key recovery from plaintext-ciphertext pairs.
Guide for debugging crashes related to custom memory heaps, particularly use-after-free issues caused by static destruction ordering, DEBUG vs RELEASE discrepancies, and custom allocator lifecycle problems. This skill should be used when investigating crashes that occur only in RELEASE builds, memory-related crashes involving custom allocators, static initialization/destruction order issues, or use-after-free bugs in C++ applications.
Guidance for implementing tensor parallelism in PyTorch, including ColumnParallelLinear and RowParallelLinear layers. This skill should be used when implementing distributed tensor parallel operations, sharding linear layers across multiple GPUs, or simulating collective operations like all-gather and all-reduce for parallel computation.
Use when researching or implementing anything related to Apple platforms (iOS, iPadOS, macOS, watchOS, tvOS, visionOS), Swift/Objective-C APIs, Apple frameworks, WWDC sessions, or Apple Developer Documentation. Triggers include: "find Apple's docs", "latest API guidance", "WWDC session", "platform availability", "SwiftUI/UIKit/AppKit/Combine/AVFoundation/etc.", or any Apple SDK coding question where authoritative docs are needed. Always use the apple-docs MCP tools for discovery and citations instead of general web search.
Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.