🧠 Discover and evaluate advanced benchmark datasets for Large Language Model agents to enhance performance assessment in real-world tasks.
npx add-skill axxafo/awesome-agent-benchmarks🧠 Discover and evaluate advanced benchmark datasets for Large Language Model agents to enhance performance assessment in real-world tasks.
Source: https://github.com/axxafo/awesome-agent-benchmarks
Pushed: 2026-05-12T06:29:00Z Stars: 3
Security scanner for AI agent skills — 38 modules detecting credential theft, supply-chain attacks, prompt injection, and runtime abuse across any skill bundle.
Explore the inner voice model for AI that reflects on choices, adds self-checks, and improves human-like judgment
Connect Claude to Google Search Console, Google Analytics 4, and Bing Webmaster Tools to analyze actual site data and performance metrics.
Claude Code skill for academic paper search using the Semantic Scholar API
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
agentbits turns hashes into trustworthy narratives and agentSummary strings — deterministic JSON endpoints you can compose with taiko-ai MCP skills.