Agent Skills Hub

rt.safety.auditor

Analyze C++ code for real-time safety violations including heap allocations, locks, blocking calls, and non-deterministic operations in high-performance audio threads.

patterns

A collection of design patterns for the Langroid multi-agent framework, covering agent configuration, tool handling, task orchestration, and external integrations.

qveris

Search and execute dynamic external tools via the QVeris API for real-time data retrieval, stock market analysis, and web-based tasks.

guard

Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

k0ntext

RPI Plan Phase: Create chunk-based, dependency-aware implementation plans from research documents for structured, atomic development.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.

using-superpowers

The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.

digest

Create curated news, tech, and research paper digests using high-quality sources. Perfect for daily roundups, topic tracking, and filtering noise.

debugging

Standardized debugging and diagnostic guidelines for AI coding agents.

lsp-setup

Automated LSP detection, installation, and configuration for intelligent code analysis, navigation, and diagnostics.