2471 related articles

Agent Skills is a lightweight open-source format that lets AI agents extend professional capabilities on demand, like loading plugins. Learn what Agent Skills are, the problems they solve, and their modular advantages.

A deep dive into DeepAgents' sandbox backend and Agent Skills: why Agents need sandboxes to isolate code execution, how Skills enable modular capability reuse, and how the two work together to build reliable AI Agent systems.

A deep dive into DeepAgents' sandbox backend and Agent Skills: why Agents need sandbox isolation to run code, how Skills enable modular capability reuse, and how the two combine to build reliable AI Agent systems.

Agent Skills is a lightweight open-source format that extends AI agent capabilities via plug-and-play skill packages. Learn its architecture, progressive disclosure, and how it differs from Multi-Agent.

Through a complete case of auto-generating test cases from requirement docs, this article explains Claude Code's Agent Skills packaging mechanism—turning proven AI workflows into reusable skills with on-demand loading.

Ponytail, GitHub's #1 monthly open-source Skill, injects a 'less is more' philosophy into AI Agents, cutting code volume by an average of 54%. Compatible with 20+ Agents including Claude Code, Cursor, and Copilot.

Ponytail, GitHub's #1 monthly open-source Skill, injects a 'less is more' engineering philosophy into AI Agents, cutting code volume by 54% on average. Compatible with 20+ Agents like Claude Code and Cursor.

Claude Desktop's new Record Skill: no prompt writing needed—just record a demo once, and AI learns and reuses the entire workflow. Two real-world cases explained.

A Google DeepMind engineer reveals that over 50,000 AI agent skills come with almost no evals. Learn how to write skill evaluations, from description tuning to test design.

A Google DeepMind engineer reveals that over 50,000 AI agent skills come with almost no evals. This guide covers skill descriptions, test design, eval harnesses, and retirement strategies.

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.

When your AI skill library grows to 50, repeated installs, difficult searches, and memory overload become core pain points. This article introduces an MCP-based unified management tool.

A must-read for test engineers: use Cursor Skill to auto-parse PRDs and generate XMind mind map test cases with one click. Supports functional, API, and performance testing—no coding needed.

An in-depth look at the Vibe Coding paradigm: how AI tools shift engineers from 'writing code' to 'directing AI,' exploring frontend skill tiers, polarization trends, and building irreplaceable value.

A systematic map of today's AI coding landscape: the evolution from ChatGPT to Claude Code, LLM capability tiers, tool camps like Cursor/Copilot, and the three key weapons of the Agent era — MCP, Skills, and CLI.

A developer shares a test case automation solution built on Claude Code + Skills: encapsulating requirement splitting, test point extraction, and case generation into independent Skills. The full workflow takes under 10 minutes.

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.

Learn how Claude Code and its Skill mechanism can automatically convert a requirements document into production-ready test cases in under 10 minutes with a 3-stage pipeline.
The Rise of Claude Skills Ecosystem: A…
Explore the Claude Skills ecosystem: from prompt engineering to modular skills, covering skill libraries, MCP integrations, and dev frameworks. The awesome-claude-skills list has 68K+ Stars.