Loading...
Loading...
Found 1,008 Skills
Run molecular dynamics (MD) simulations via the FastFold Workflows API. Today supports the CALVADOS+OpenMM workflow (calvados_openmm_v1) from either an existing fold job (AF structure + PAE auto-resolved) or manual PDB+PAE upload, then waits for completion, fetches metrics/plots/CSV artifacts, and extracts trajectory frames as PDB files. Use when running an MD simulation with FastFold, CALVADOS + OpenMM, reading MD metrics/plots, extracting frames, or scripting submit → wait → results for an MD run.
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.
Create custom Genfeed nodes using the SDK. Triggers on "create a new node", "add a custom node type", "build a node for X".
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.
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.