OSSbenchflow-ai/skillsbench Agent Skills BenchmarkGitHub·high signalFirst standardized benchmark for agent skills. Key finding: curated skills boost 16.2% but self-generated skills provide zero benefit.SourceSource pageGitHub↳ Follow the threadThreat pattern / Update threadMicrosoft Agent Framework python-1.11.0 adds Progressive MCP Disclosure and GA Skills APIGitHub (Microsoft Agent Framework)Policy dependency / Stack layerFirst Recon AI ships AI Security Runtime GA — inline policy enforcement on every agent-to-agent and agent-to-tool callBusiness WirePolicy dependency / Stack layerCodenotary ships AgentMon 3 for agent runtime policy and compliance loggingAI Agent StorePolicy dependency / Stack layerPattern: A Provider-Abstraction / BYOK Layer Is Hardening Beneath Agent HarnessesGitHubStack layer / ContrastCut agent scraping token spend with Scrapling — adaptive element-signature relocation plus a built-in MCP serverGitHubPolicy dependency / Stack layerHugging Face Transformers v5.13.0 Adds a Unified Export Pipeline and Kimi K2.5 ArchitectureHugging FaceStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivStack layer / Update threadclaude-video Turns 'Watch This Video' Into a Portable Agent Skill — 8K Stars in WeeksGitHub