#AI Agent Skill
2061 related articles
·3 min
Stop Flying Blind: A Complete Practical Guide to Writing Evals for AI Agent Skills
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.
Read more →
·3 min
Stop Flying Blind: A Complete Practical Guide to Writing Evals for AI Agent Skills
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.
Read more →
·2 min
Breaking Down the AI Agent Execution Flow: How Tools and Skills Work Together
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.
Read more →
·2 min
Breaking Down the AI Agent Execution Flow: How Tools and Skills Work Together
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.
Read more →
·4 min
Teaching AI to Have "Taste": Exploring Multi-Agent Design with Open-Source Skill Taste
Why does AI-generated UI all look the same? Designer SEN open-sourced a Skill called Taste that uses a four-agent pipeline to reverse-engineer website "taste" into verifiable design principles called Taste DNA.
Read more →
GitHub Daily · July 21: The Agent Skil…
·3 min
GitHub Daily · July 21: The Agent Skills Ecosystem Explodes, Intelligence Dashboard Tops the Charts
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.
Read more →
·3 min
Can You Make an AI Short Film in 30 Minutes? A Full Flowva Agent+Skill Walkthrough
Full Flowva review: complete AI short film pipeline via Agent chat — from script breakdown to asset generation, storyboarding, and editing, all without switching platforms.
Read more →
·2 min
BrowserSkill: A Controlled Channel for AI Agents to Safely Borrow Your Logged-In Browser
Tencent's open-source BrowserSkill (BSK) lets AI agents reuse your real browser login state via a separate window, single-tab borrowing, and human takeover — safely and within clear boundaries.
Read more →
·2 min
The Four Core Concepts of AI Agents Explained: Function Calling, Tool, MCP, and Skill
A clear breakdown of the four core AI Agent concepts: Function Calling, Tool, MCP, and Skill — understand the full tech stack behind intelligent agent development.
Read more →
·2 min
unDream AI in Practice: One-Click Storyboard-Driven Video Generation with Agent + Skill
unDream AI workflow tested: activate the Expert Director Storyboard Skill via Agent, generate annotated storyboards from reference images, then refine and render video in one seamless pipeline.
Read more →
·2 min
Skill + Agent in Action: A Complete AI Workflow for Home Furnishing Ad Video Production
Use Skill + Agent to complete a full home furnishings ad workflow — from asset sourcing and character consistency to video storyboarding and final compositing — all within one canvas.
Read more →
Deep Dives
Deep Dive into AI Agent Skill Design: …
·3 min
Deep Dive into AI Agent Skill Design: Engineering Practices from Anthropic and Perplexity
A deep dive into Skill design philosophy from Anthropic's Claude Code team and Perplexity's Agent team, covering the Tax Test, Gotchas Flywheel, progressive disclosure, and Eval-First practices for building high-quality AI Agent skill systems.
Read more →
·2 min
MCP vs. Skills: A Clear Breakdown of AI Agent Architecture Layers
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.
Read more →
·3 min
Empowering AI Agents with Skills to Automate WeChat Official Account Analytics
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.
Read more →
·3 min
Skill Pack-Driven AI Agents: An Efficient Alternative to Complex Workflows
Ditch complex workflow nodes. Use Agent Skill packs to dynamically load AI capabilities, build stable intelligent automation, and understand RAG, LLM limits, and Scale Agent plugin setup.
Read more →
·2 min
Microsoft Open-Sources .NET Skills: Making AI Coding Agents Master C# Development
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.
Read more →
·3 min
Google Open-Sources Stitch Skills: A New Practice in AI Agent Skill Standardization
Google Labs open-sourced stitch-skills, a standardized skill encapsulation solution for AI Agents, compatible with Gemini CLI, Claude Code, Cursor and more.
Read more →
·3 min
GitHub Daily · July 12: The Explosion of the Agent Skills Ecosystem and the Rust Rewrite Wave
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.
Read more →
·2 min
Agent Skills: Bringing Production-Grade Engineering Capabilities to AI Coding Agents
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.
Read more →
·3 min
GitHub Daily · July 11: Agent Skills Ecosystem Explodes, AI Programming Enters the Era of 'Skill Standardization'
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.
Read more →