1592 related articles

An in-depth look at how AI Agents execute tasks: clarifying the difference between Tools and Skills, and reconstructing the complete eight-step flow from understanding goals to delivering results.

A deep dive into how AI Agents execute tasks: clarifying the core difference between Tools and Skills, and reconstructing the complete eight-step execution flow from understanding goals to delivering results.

A recursive technical proposition: Can we build a "meta-Skill" that auto-transforms any Skill into a Dify workflow? This article dissects the boundary between deterministic orchestration and autonomous Agent decisions.
GitHub Daily · July 21: The Agent Skil…
GitHub Trending July 21: The Agent Skills ecosystem explodes as pluggable skill packs top the charts, MCP becomes the de facto standard, and ai-agent-book surges 4,434 stars in a day.

Andrew Ng's DeepLearning.ai teams up with Anthropic to teach Agent Skills: file structure, progressive disclosure, MCP integration, and the full path from Claude.ai to the Agent SDK.

Google DeepMind engineer Philip reveals: almost everyone uses coding agent Skills, yet almost no one writes evals for them. A deep dive into Skill evaluation methods, 8 actionable tips, and a real Gemini API case study.

A deep dive into Agent Skills: what they are, how they differ from Function Calling, and a 3-step guide to understanding and customizing Skills for real business use cases.
Fine-Tuning Cosmos Models in One Day w…
NVIDIA uses Autonomous Coding Agents and Agent Skills with TAO to fine-tune Cosmos visual reasoning models in one day, achieving over 90% accuracy.

MCP and Skills aren't alternatives — they occupy different layers of AI Agent architecture. This article breaks down Function Call, MCP, and Skills to clarify each layer's role.

A deep dive into Agent Skills: SKILL.md structure, four core elements (workflow/docs/tools/assets), real-world case studies, and how Skills differ from prompts.

A deep dive into Agent Skills: learn the file structure (SKILL.md, references, scripts, assets), core principles, and how they differ from prompts. Build your own AI skill bundle from scratch.

Learn how Skill-powered AI Agents can automatically log in to WeChat Official Account backends, scrape data, sort it, and generate Excel reports — eliminating manual analytics work.

Microsoft open-sources dotnet/skills, packaging .NET/C# best practices as structured skills for AI coding agents. Bridges domain knowledge gaps in general LLMs, improving code quality for GitHub Copilot and other tools.

Google Labs open-sourced stitch-skills, a standardized skill encapsulation solution for AI Agents, compatible with Gemini CLI, Claude Code, Cursor and more.

July 12 GitHub trending: Agent Skills/MCP ecosystem explodes with superpowers hitting ~900 stars, pgrust rewrites Postgres in Rust passing 100% tests, plus solid engineering foundations.

Google engineer Addy Osmani's open-source project agent-skills (76k+ GitHub stars) injects production-grade engineering skills into AI coding agents, covering performance, security, and code quality.

July 11 GitHub Daily: Three Agent Skills projects surge on the same day, signaling AI programming's shift to skill standardization, with cross-platform open standards and local Agent memory leading the way.

A deep dive into Agent Skills: from basic prompts to fully encapsulated AI capability units. Five levels of human-AI interaction evolution, with clear distinctions between Skills, MCP, and Workflow.

July 10 GitHub Daily: The Agent Skills ecosystem explodes as over half of trending projects revolve around AI coding Agent skill libraries, with MCP as the standard interface.

A deep dive into Anthropic's Agent Skills architecture — clarifying its difference from MCP, and how modular Skill packages enable scalable, maintainable enterprise agent development.