MCP 与 Skills

AI agent engineering readings for September 18 to 19, 2026, with key findings, engineering implications, suggested sections, and primary sources.

AI agent engineering readings for September 11 to 18, 2026, with key findings, engineering implications, suggested sections, and primary sources.

Alibaba skill-up resumes real sessions turn by turn, letting skill evaluations test context continuity, intermediate state, and per-turn assertions.

How Tool Search loads definitions on demand, affects prompt caching, and differs from MCP connections and ARD resource discovery.

AI agent engineering readings for September 11 to 17, 2026, with key findings, engineering implications, suggested sections, and primary sources.

AI agent engineering readings for September 11 to 16, 2026, with key findings, engineering implications, suggested sections, and primary sources.

Skills Manager distributes a local skill library to Claude Code, Codex, Cursor, and Gemini CLI while managing version and configuration consistency.

How the Google Cloud Developer Plugin packages Skills, MCP configuration, and rules, and what this means for distribution, versions, and permissions.

AI agent engineering readings for September 4 to 10, 2026, with key findings, engineering implications, suggested sections, and primary sources.

Munim Computer Use reads the accessibility tree and operates desktop controls by element ID, reducing reliance on fragile screenshot-coordinate automation.

Strands harness-sdk, Harness MCP Server, and HydraFusion show why agent engineering needs control over context, permissions, state, validation, and recovery.

Coding agents read and execute skills, MCP tools, dependencies, and repository instructions. These need software supply-chain controls.