Agent Skills Hub

wycheproof

Validates cryptographic implementations using the Google Wycheproof test vector suite to detect security edge cases and known vulnerabilities.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

Global Documentation

Ensures adherence to standardized global documentation patterns for technical projects, maintaining consistency across repositories and agent-based workflows.

react-native-best-practices

React Native performance optimization guide covering FPS, TTI, bundle size, memory leaks, and profiling patterns based on Callstack's industry-standard expertise.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

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.

entry-point-analyzer

Map the attack surface of smart contract codebases by identifying and categorizing state-changing entry points.

help

Interactive guide for workspace discovery, providing access to specialist agents, automated workflows, CLI tools, and active lifecycle hooks.

synapse

Autonomous pattern detection and skill recommendation engine that monitors project memory, logs, and task lists to evolve your AI agent's capabilities automatically.

wrap

Automated session cleanup and documentation tool. Proactively updates CLAUDE.md, detects automation patterns, extracts insights, and organizes pending tasks.

codeql

Perform deep security analysis on codebases using CodeQL for interprocedural data flow, taint tracking, and automated vulnerability detection across multiple languages.

hive

Automate GitHub issue triage by analyzing reports against the codebase, verifying technical claims, and providing expert-driven responses to resolve invalid issues.