BestHub
Sign in
Tagged articles

Skill

104 articles · Page 1 of 2
PMTalk Product Manager Community
PMTalk Product Manager Community
Sep 10, 2026 · Product Management

MCP vs Skill: A Decision Framework for AI Product Managers

This article defines MCP as atomic tools for deterministic needs and Skill as orchestration workflows for dynamic multi-step tasks, provides a selection framework based on requirement certainty, outlines technical division of labor between business developers and product/AI teams, recommends a phased integration approach, and answers seven common product manager questions about implementation.

AI integrationAI product managementMCP
0 likes · 9 min read
MCP vs Skill: A Decision Framework for AI Product Managers
Alibaba Cloud Native
Alibaba Cloud Native
Sep 9, 2026 · Artificial Intelligence

From DingTalk Queries to Code Delivery: Building a Team-Level Agent Infrastructure with Domino

Alibaba Cloud's Domino platform evolves from a code execution tool into a team-level Agent infrastructure, combining ConsoleAgent for DingTalk group interactions, SandboxAgent for real repository execution, layered context (Session, KBase memory, knowledge bases), and domain-specific SKILLs to enable continuous learning and end-to-end delivery.

Agent infrastructureConsoleAgentDomino
0 likes · 25 min read
From DingTalk Queries to Code Delivery: Building a Team-Level Agent Infrastructure with Domino
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 9, 2026 · Artificial Intelligence

Clearing AI Confusion: Function Calling, MCP, Tools, Skills, Vectors, Tensors, Tokens, Embeddings

This article clarifies commonly confused AI concepts by grouping them into four categories: model-tool interaction (Function Calling vs MCP), task execution (Tools vs Skills), internal data representation (vectors vs tensors), and text processing (Tokens vs Embeddings), explaining their distinct roles and relationships.

EmbeddingFunction CallingMCP
0 likes · 27 min read
Clearing AI Confusion: Function Calling, MCP, Tools, Skills, Vectors, Tensors, Tokens, Embeddings
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 2, 2026 · Artificial Intelligence

How LLM Applications Are Built: Workflows, Agents, MCP & Skills

This article explains the architecture of large language model applications, distinguishing between simple chat, fixed workflows, autonomous agents, the Model Context Protocol (MCP) for tool integration, and reusable skills, providing a decision framework for choosing the right approach based on task complexity and stability requirements.

AI architectureAgentLLM Applications
0 likes · 18 min read
How LLM Applications Are Built: Workflows, Agents, MCP & Skills
DataFunSummit
DataFunSummit
Aug 11, 2026 · Artificial Intelligence

Beyond RAG: Using Skill + CLI to Build Persistent Agent Knowledge

The article argues that traditional Retrieval‑Augmented Generation (RAG) discards experience after each query, and proposes RDS ContextDB’s Skill‑defined abilities and CLI‑driven paths as a way for agents to continuously capture, reuse, and evolve business knowledge, with a live demo announced for Agentic DB Day.

AI AgentsCLIContextDB
0 likes · 2 min read
Beyond RAG: Using Skill + CLI to Build Persistent Agent Knowledge
James' Growth Diary
James' Growth Diary
Aug 9, 2026 · Backend Development

How One Backend Serves Three Audiences: OpenAPI, CLI, and Frontend

The article walks through a real‑world agent platform backend, showing how the same OpenAPI contract is split into three distinct faces—OpenAPI for developers, a CLI for AI agents, and a web frontend for humans—detailing the architecture, lifecycle, command tree, and two concrete pitfalls with code examples.

AI agentArchitectureBackend
0 likes · 18 min read
How One Backend Serves Three Audiences: OpenAPI, CLI, and Frontend
AI Engineering
AI Engineering
Aug 9, 2026 · Artificial Intelligence

Six Major Vendors Release Unified AI Agent Plugin Packaging Standard

Six leading AI companies—Google, Microsoft, OpenAI, Cursor, Vercel, and AWS—have jointly published the Agent Plugins 1.0.0 specification, standardizing the directory layout, plugin.json and mcp.json formats, and discovery rules to enable "write once, run on any client" while highlighting current security limitations.

AI agentAgent PluginsMCP
0 likes · 12 min read
Six Major Vendors Release Unified AI Agent Plugin Packaging Standard
Wuming AI
Wuming AI
Aug 4, 2026 · Artificial Intelligence

Why CLI Is the Key to Fully Connecting Enterprise Systems for AI Agents

The article explains why command‑line interfaces are a low‑cost, highly controllable way for AI agents to reliably invoke internal enterprise systems, compares CLI with MCP, and walks through practical steps—from login and basic commands to testing and Skill packaging—to demonstrate measurable business value.

CLIFDEMCP
0 likes · 10 min read
Why CLI Is the Key to Fully Connecting Enterprise Systems for AI Agents
Advanced AI Application Practice
Advanced AI Application Practice
Aug 2, 2026 · Artificial Intelligence

Create a Test Case Generation & Review Skill and Execute It in Lobster

This article walks through extracting TestHub’s test case generation and review prompts, using the Trae tool to craft a custom Skill named generator‑testcase, importing it into the Lobster AI IDE, and generating high‑quality test cases with SiliconFlow’s Kimi 2.6 model, while highlighting best‑practice tips for prompt and model selection.

AI TestingKimi2.6Lobster
0 likes · 6 min read
Create a Test Case Generation & Review Skill and Execute It in Lobster
Shuge Unlimited
Shuge Unlimited
Jul 20, 2026 · Artificial Intelligence

Practical grill‑me Guide: Let an AI Agent Fully Clarify Requirements Before Coding

This guide walks through the /grill-me and /grilling skills, explains their hierarchical design, demonstrates a complete export‑feature scenario, extracts five hard rules to prevent scope drift, shows how a shared‑understanding gate safeguards decisions, and advises when to use or avoid grill‑me in modern AI‑assisted development workflows.

AI agentPromptSkill
0 likes · 23 min read
Practical grill‑me Guide: Let an AI Agent Fully Clarify Requirements Before Coding
Efficient Ops
Efficient Ops
Jul 16, 2026 · Operations

Why Harness, Not Model, Is the Real Key for Deploying AI Agents in Production

After a 40‑minute GOPS talk on "one person + an AI Agent army," the author argues that the decisive factor for putting AI agents into production is not the model itself but a disciplined harness engineering that creates a verifiable, roll‑backable closed loop, turning a single operator into a minimal delivery unit.

AI AgentsAutomationHarness Engineering
0 likes · 13 min read
Why Harness, Not Model, Is the Real Key for Deploying AI Agents in Production
KooFE Frontend Team
KooFE Frontend Team
Jul 16, 2026 · Artificial Intelligence

Why Do Hundreds of Skills Slow Down GPT‑5.6 Codex?

After upgrading to GPT‑5.6, many Codex users find that the large number of accumulated Skills no longer speeds up work but actually lengthens execution time, increases token consumption, and adds extra tool calls because the model now reads and enforces Skill rules more rigorously, turning Skills from execution helpers into contextual overhead.

AI model performanceAgentGPT-5.6
0 likes · 12 min read
Why Do Hundreds of Skills Slow Down GPT‑5.6 Codex?
Yunqi AI+
Yunqi AI+
Jul 15, 2026 · Artificial Intelligence

How to Build Enterprise AI Management Agents: Path, Design, and Governance

The article analyzes how to construct enterprise AI management agents by distinguishing them from personal efficiency agents, defining data semantics and governance, designing two capability chains for query and analysis, and outlining a step‑by‑step implementation roadmap with security, evaluation, and ownership practices.

AIAgentData Governance
0 likes · 18 min read
How to Build Enterprise AI Management Agents: Path, Design, and Governance
ByteDance SE Lab
ByteDance SE Lab
Jul 13, 2026 · Artificial Intelligence

Turning Agents into an Audio‑Video Workbench with AI MediaKit CLI + Skill

The AI MediaKit CLI and Skill, announced at the 2026 Force conference, expose over 100 audio‑video capabilities as a unified, agent‑friendly workbench, enabling natural‑language driven editing, enhancement, and delivery of videos through structured commands, long‑task handling, and edge‑cloud collaboration.

AI MediaKitAgentAudio Video Processing
0 likes · 11 min read
Turning Agents into an Audio‑Video Workbench with AI MediaKit CLI + Skill
PaperAgent
PaperAgent
Jul 12, 2026 · Artificial Intelligence

Three Must-Have Skills Unlock GPT‑5.6’s Super‑Human Performance

The author tests GPT‑5.6 with three custom skills—Anthropic’s frontend‑design, the guizang‑ppt skill, and DeepSeek’s Deli_AutoResearch framework—showing token savings, superior design judgment, automated Swiss‑style PPT generation, and a zero‑interaction autonomous agent that logs its own progress and pivots.

AI designGPT-5.6Skill
0 likes · 7 min read
Three Must-Have Skills Unlock GPT‑5.6’s Super‑Human Performance
Huajiao Technology
Huajiao Technology
Jul 10, 2026 · Backend Development

Six Real‑World Skill Templates Unveiled: Full Code, Structure, and Design Rationale

The article publishes six de‑identified Skill examples—covering Go server standards, a shared ranking service, Archery‑compliant DDL, interface‑contract generation, test/review workflows, and a frontend D2C standard—showing their directory layouts, complete SKILL.md files, and the concrete design decisions that keep AI‑generated code aligned with project rules.

AIBackendGo
0 likes · 25 min read
Six Real‑World Skill Templates Unveiled: Full Code, Structure, and Design Rationale
AI Architecture Hub
AI Architecture Hub
Jul 10, 2026 · Artificial Intelligence

Why Claude Code Rules Fail and How to Build a Layered CLAUDE.md Governance

The article analyzes why Claude Code often ignores constraints in CLAUDE.md, identifies four root causes—including incomplete rule loading, vague descriptions, context overload, and lack of hard enforcement—and proposes a five‑layer governance architecture with concrete migration and troubleshooting steps.

Claude CodeLLMRule Governance
0 likes · 15 min read
Why Claude Code Rules Fail and How to Build a Layered CLAUDE.md Governance
JavaGuide
JavaGuide
Jul 9, 2026 · Fundamentals

Automate Draw.io Diagrams with the New Open‑Source drawio‑chart Skill

The article introduces the open‑source drawio‑chart Skill, explains why draw.io remains valuable for editable technical diagrams, compares it with other AI drawing projects, details the workflow, constraints, installation steps, and shows how to generate and refine diagrams for documentation.

AI automationDraw.ioSkill
0 likes · 15 min read
Automate Draw.io Diagrams with the New Open‑Source drawio‑chart Skill
DataFunTalk
DataFunTalk
Jul 8, 2026 · Artificial Intelligence

How Harness + Skill Enable a New ChatBI Paradigm

The article explains why stronger LLMs demand robust infrastructure, outlines the persistent pain points of traditional data products, and details Ctrip's ChatBI solution that combines a multi‑agent framework, memory management, Harness tool orchestration and Skill management, with a comparison of Claude SDK and Ali Agent Scope and a rigorous quality‑monitoring process.

ChatBIData AnalyticsHarness
0 likes · 3 min read
How Harness + Skill Enable a New ChatBI Paradigm
DataFunSummit
DataFunSummit
Jul 8, 2026 · Artificial Intelligence

Ctrip’s New ChatBI Paradigm Using Harness and Skill

The article explains how Ctrip leveraged mature large‑language models to overcome traditional data‑product challenges—such as inconsistent metrics and manual attribution—by designing a ChatBI system that combines a multi‑agent framework, memory management, Harness‑driven tool orchestration, and Skill‑based data access, while also evaluating alternatives like Claude SDK and Ali Agent Scope.

ChatBICtripHarness
0 likes · 3 min read
Ctrip’s New ChatBI Paradigm Using Harness and Skill
JD Tech Talk
JD Tech Talk
Jul 8, 2026 · Artificial Intelligence

Turning Business Processes into High‑Quality Skills: A Practical Path

The article analyzes the real pain points of AI‑driven business workflow automation, then details a step‑by‑step method using Codex Record & Replay to create, refine, and upgrade Skills—covering recording, SKILL.md generation, API migration, multi‑machine validation, and scheduled execution, illustrated with a JoyHR resume‑search case study.

AI automationAPI migrationBusiness workflow
0 likes · 11 min read
Turning Business Processes into High‑Quality Skills: A Practical Path
BirdNest Tech Talk
BirdNest Tech Talk
Jul 6, 2026 · Artificial Intelligence

How to Quickly Learn and Master AI‑Generated Projects with the /teach Skill

The article explains why traditional code‑review methods are inefficient for AI‑generated projects and presents a three‑skill workflow—/teach, /insight-diagram, and /architecture-diagram—demonstrated on the open‑source Zero coding agent to turn codebases into lasting, self‑contained learning courses and professional diagrams.

AIArchitecture DiagramSkill
0 likes · 21 min read
How to Quickly Learn and Master AI‑Generated Projects with the /teach Skill
DataFunSummit
DataFunSummit
Jul 6, 2026 · Artificial Intelligence

A New Paradigm for Deploying ChatBI with Harness and Skill

The article explains how Ctrip leveraged mature large‑language models to overcome traditional data‑product pain points by building a ChatBI solution that combines a Multi‑Agent framework, memory management, Harness‑driven tool orchestration and Skill‑based standardization, and it details the technical choices, quality controls, and an upcoming AI meetup.

AIChatBIData Analytics
0 likes · 3 min read
A New Paradigm for Deploying ChatBI with Harness and Skill
DataFunTalk
DataFunTalk
Jul 2, 2026 · Industry Insights

From Hackathon First Prize to a Codex Skill: My Real‑World Playbook

I won the Beijing Global Hackathon’s Coding Agent track solo while battling a cold, and later distilled the 48‑hour trial‑and‑error journey with Codex into an open‑source skill that captures direction‑finding, rapid tech‑stack evaluation, and trustworthy AI‑agent loop engineering.

AB testingAI AgentsHackathon
0 likes · 24 min read
From Hackathon First Prize to a Codex Skill: My Real‑World Playbook
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Jul 2, 2026 · Artificial Intelligence

Is Changing Session, Skill, or Model the Same? Why Claude Code’s Self‑Review Fails

The article explains why Claude Code’s self‑review is inherently unreliable and distinguishes four distinct remedies—starting a new session, swapping a review Skill, changing the underlying model, and using Sub‑Agent or Worktree isolation—each solving a different problem and none interchangeable, then outlines a risk‑based workflow for AI‑assisted code review.

AIClaudeSkill
0 likes · 12 min read
Is Changing Session, Skill, or Model the Same? Why Claude Code’s Self‑Review Fails
Data Party THU
Data Party THU
Jul 1, 2026 · Artificial Intelligence

How Leading AI Labs Build and Use Claude Skills Effectively

The article reveals Anthropic’s internal approach to Claude Skills, detailing a nine‑category taxonomy, key principles such as focus and verification, practical writing guidelines, and strategies for scaling, governance, and composition, offering actionable insights for teams deploying Claude Code.

AIAnthropicAutomation
0 likes · 16 min read
How Leading AI Labs Build and Use Claude Skills Effectively
AgentGuide
AgentGuide
Jun 29, 2026 · Artificial Intelligence

What Is Loop Engineering in AI Agents? Definition, Components, and Use Cases Explained

Loop Engineering replaces manual prompt writing with autonomous AI-driven cycles that automate task initiation, parallel isolation, skill definition, tool integration, sub‑agent delegation, and persistent memory, enabling agents to self‑manage complex workflows across diverse scenarios.

AI agentAutomationLoop Engineering
0 likes · 8 min read
What Is Loop Engineering in AI Agents? Definition, Components, and Use Cases Explained
Linyb Geek Road
Linyb Geek Road
Jun 29, 2026 · Artificial Intelligence

Deep Dive into Loop Engineering: From Prompt Engineering to System Design

Loop Engineering replaces manual prompting with system‑designed loops that let AI agents iterate autonomously, covering its definition, origins, five core modules plus memory, a full‑stack example, experimental results, limitations, and a comparison between Claude Code and Codex.

AI AgentsAutomationConnector
0 likes · 16 min read
Deep Dive into Loop Engineering: From Prompt Engineering to System Design
AliExpress Tech
AliExpress Tech
Jun 26, 2026 · Artificial Intelligence

From LLM-as-Judge to Agent-as-Judge: A Technical Evolution

The article analyzes why using a large language model alone as a judge is unreliable for complex AI evaluation, introduces the Agent-as-Judge architecture with sandboxed execution, Skill‑driven workflows, and a three‑layer assessment framework, and discusses its benefits, costs, and practical outcomes.

AI TestingAgentEvaluation
0 likes · 14 min read
From LLM-as-Judge to Agent-as-Judge: A Technical Evolution
Programmer DD
Programmer DD
Jun 24, 2026 · Artificial Intelligence

Building a Content Creation Agent Team with Vercel Eve Subagents and Skills

This tutorial shows how to transform the previously built Vercel Eve agents into a full‑featured content creation team by defining reusable skills for topic planning, article writing, and review, and by splitting responsibilities into dedicated subagents for researcher, writer, and reviewer, with detailed code examples and workflow guidance.

AI agentContent automationNode.js
0 likes · 17 min read
Building a Content Creation Agent Team with Vercel Eve Subagents and Skills
Su San Talks Tech
Su San Talks Tech
Jun 24, 2026 · Artificial Intelligence

Top 10 Common Claude Code Issues and Practical Solutions

The article compiles the ten most frequently asked questions about Claude Code, covering CLAUDE.md usage, token cost reduction, MCP and Skill configuration, permission management, tool comparison, Hooks, context limits, IDE integration, and prompt engineering, each illustrated with concrete examples and data.

CLAUDE.mdClaude CodeIDE integration
0 likes · 21 min read
Top 10 Common Claude Code Issues and Practical Solutions
JavaGuide
JavaGuide
Jun 12, 2026 · Artificial Intelligence

Integrating Agnes AI Free Tokens with Claude Code for Multimodal Tasks

This article walks through connecting the free Agnes AI multimodal API to Claude Code, detailing the required setup, a small Java code‑generation task, image and video generation examples, skill creation, and performance observations to help developers evaluate its suitability for their workflows.

AgentAgnes AICC Switch
0 likes · 15 min read
Integrating Agnes AI Free Tokens with Claude Code for Multimodal Tasks
DataFunSummit
DataFunSummit
Jun 11, 2026 · Big Data

How MaxCompute Enables Multimodal Storage and Hybrid Computing for Powerful Digital Agents

The article details MaxCompute's three‑stage approach—production‑ready Agent access via MCP and Skill, a business‑oriented semantic layer, and multimodal Blob storage with hybrid compute—culminating in a CPU‑only home‑design demo that showcases end‑to‑end Agent workflows, security controls, and mobile integration.

BLOBDigital AgentHybrid Computing
0 likes · 11 min read
How MaxCompute Enables Multimodal Storage and Hybrid Computing for Powerful Digital Agents
JavaGuide
JavaGuide
Jun 10, 2026 · Artificial Intelligence

Kimi Work Review: 300 Parallel Agents Power Automated Stock Analysis

Kimi Work, the desktop agent mode of Kimi’s AI client, can read local files, control browsers via WebBridge, schedule tasks, and run up to 300 parallel sub‑agents, which the author demonstrates through an AI‑driven stock‑analysis radar and a custom Skill, noting strong capabilities but slower speed and stability issues.

AI AgentsKimi WorkSkill
0 likes · 15 min read
Kimi Work Review: 300 Parallel Agents Power Automated Stock Analysis
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 9, 2026 · Artificial Intelligence

Scientific, Controllable Skill Self‑Evolution: Deep Dive into Trace2Skill, EvoSkill and SkillOpt

This article analyzes three recent papers—Trace2Skill, EvoSkill, and SkillOpt—detailing their methodologies for automatically evolving Agent Skills, comparing their assumptions, processes, strengths, and limitations, and offering guidance on selecting the appropriate approach for scalable, reliable skill self‑improvement.

AgentArtificial IntelligenceSkill
0 likes · 33 min read
Scientific, Controllable Skill Self‑Evolution: Deep Dive into Trace2Skill, EvoSkill and SkillOpt
Old Zhang's AI Learning
Old Zhang's AI Learning
Jun 8, 2026 · Artificial Intelligence

Open‑Source AI Digital Employees for SMBs: One‑Line Install for Claude Code/Codex

The article introduces a set of open‑source AI Agent Skills that turn Claude Code, Qoder, Cursor and similar tools into digital employees for small‑to‑medium businesses, showing how to install them with a single command, configure them for tasks like email handling, PDF parsing, markdown‑to‑Excel conversion, and Excel editing, and combine them into fully automated workflows.

AI agentAutomationClaude Code
0 likes · 17 min read
Open‑Source AI Digital Employees for SMBs: One‑Line Install for Claude Code/Codex
AI Waka
AI Waka
Jun 8, 2026 · Artificial Intelligence

Building Reliable Snowflake AI Agents: SKILL‑Based SOPs for Production Analytics

The article explains how Snowflake’s AI agents can achieve production‑grade reliability by encoding standard operating procedures as version‑controlled, declarative SKILL contracts that enforce deterministic logic, validation, guardrails, and progressive disclosure, supported by a GitOps‑driven zero‑ETL deployment pipeline.

AI agentCortex SearchGitOps
0 likes · 14 min read
Building Reliable Snowflake AI Agents: SKILL‑Based SOPs for Production Analytics
macrozheng
macrozheng
Jun 2, 2026 · Artificial Intelligence

Why the 200k‑Star Claude Code Plugin Is a Must‑Have for AI Programming

This article walks through the superpowers plugin for Claude Code—its 200 k star popularity, built‑in 20 AI‑assisted workflow skills, installation via npm, step‑by‑step usage to build a full‑stack Markdown editor, and key considerations such as sub‑agent isolation and test‑driven development.

AI programmingClaude CodePlugin
0 likes · 5 min read
Why the 200k‑Star Claude Code Plugin Is a Must‑Have for AI Programming
Lin is Dream
Lin is Dream
Jun 2, 2026 · Artificial Intelligence

Exploring Agent Skill Management: Treating Agent Capabilities Like Software Packages

The article proposes a systematic Agent Skill Hub that organizes, versions, releases, deploys, and rolls back AI Agent capabilities using software‑package‑style practices, illustrated with a concrete image‑download skill, directory conventions, metadata files, and a Spring AI Alibaba runtime loading strategy.

AIAgentGitHub
0 likes · 15 min read
Exploring Agent Skill Management: Treating Agent Capabilities Like Software Packages
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 1, 2026 · Artificial Intelligence

Turning a Web‑Only StarAgent WebTerminal into a Full‑Featured CLI

This article details how the author refactored the StarAgent/Drogo WebTerminal from a purely web‑based UI into a stable CLI‑driven execution layer (wt), adding black‑screen commands (wsh/wcp), session reuse, file‑transfer APIs, interactive debugging, and Skill‑based operation guides so AI agents can dynamically run, observe, and iterate on remote troubleshooting tasks such as GPU‑hang analysis and coredump debugging.

AI agentCLIRemote Debugging
0 likes · 26 min read
Turning a Web‑Only StarAgent WebTerminal into a Full‑Featured CLI
ZhiKe AI
ZhiKe AI
May 28, 2026 · Artificial Intelligence

Why Your LLM Skill Gets Ignored and 5 Proven Design Patterns to Make Agents Work

Even after spending hours crafting a Skill, many LLM agents ignore it, leading to failed automation; this article analyzes why and presents five validated design patterns—linear flow, decision tree with lazy loading, iterative loops, baton passing, and multi‑stage checkpoints—plus concrete examples and a minimal Skill template to ensure reliable, production‑grade agent behavior.

AgentAutomationDesign Patterns
0 likes · 12 min read
Why Your LLM Skill Gets Ignored and 5 Proven Design Patterns to Make Agents Work
AI Insight Log
AI Insight Log
May 26, 2026 · Frontend Development

How Taste Skill Gives AI‑Generated Front‑Ends Real Design Sense

Taste Skill, a 21.5k‑star GitHub project, adds a set of design rules that AI coding agents can follow, turning generic, “slop” front‑end pages into more aesthetically pleasing layouts by banning common pitfalls and offering adjustable parameters for variance, motion, and visual density.

AIAutomationDesign
0 likes · 10 min read
How Taste Skill Gives AI‑Generated Front‑Ends Real Design Sense
Tencent Cloud Developer
Tencent Cloud Developer
May 26, 2026 · Artificial Intelligence

What Hidden Secrets Does the Agent’s System Prompt Code Reveal?

This article dissects OpenClaw's agent architecture, detailing how the System Prompt, Skill modules, and Agent Loop interact, explaining PromptMode variations, safety rules, tool definitions, skill loading pipelines, heartbeat handling, sub‑agent spawning, silent replies, and the context engine that assembles messages for LLMs.

Agent LoopContext EngineLLM
0 likes · 17 min read
What Hidden Secrets Does the Agent’s System Prompt Code Reveal?
James' Growth Diary
James' Growth Diary
May 25, 2026 · Artificial Intelligence

How Agents Turn a Single Success into a Reusable Skill

The article explains how Hermes separates memory from skills, automatically creates structured SKILL.md files from successful interactions, prioritizes updates over new creations, manages supporting files, tracks usage, and compares its approach with other agent frameworks, offering a detailed, code‑driven walkthrough of the entire skill‑generation pipeline.

AIAgentHermes
0 likes · 16 min read
How Agents Turn a Single Success into a Reusable Skill
Linyb Geek Road
Linyb Geek Road
May 23, 2026 · Artificial Intelligence

Why Most Claude Code Skills Fail and How to Rebuild Them Using the Official Specification

The article explains that many Claude Code skills are never invoked because their description fields are missing or too long, then walks through the official directory layout, three‑layer loading, description budgeting, fork vs. inline execution, frontmatter groups, and shell pre‑processing, providing concrete examples and best‑practice guidelines.

AI WorkflowClaude CodeSkill
0 likes · 15 min read
Why Most Claude Code Skills Fail and How to Rebuild Them Using the Official Specification
Linyb Geek Road
Linyb Geek Road
May 21, 2026 · Artificial Intelligence

Understanding Prompt, MCP, and Skill: Three Essential AI Concepts

The article explains how Prompt, Model Context Protocol (MCP), and Skill serve distinct but complementary roles in AI interaction—Prompt provides instant, conversational instructions, MCP connects the model to external tools and data, and Skill offers pre‑packaged expert capabilities, together forming a layered control hierarchy.

AIMCPPrompt
0 likes · 8 min read
Understanding Prompt, MCP, and Skill: Three Essential AI Concepts
Baidu Geek Talk
Baidu Geek Talk
May 20, 2026 · Artificial Intelligence

How We Tamed AI Output with a Three‑Layer Architecture for Android Code Migration to KMP

This article details how we used a three‑layer AI architecture—Skill for stable execution, SubAgent for context‑aware scheduling, and Agent Team for parallel collaboration—to reliably migrate a large Android codebase to a Kotlin Multiplatform project, addressing instability, context inflation, and efficiency challenges.

AIAgent TeamAndroid
0 likes · 15 min read
How We Tamed AI Output with a Three‑Layer Architecture for Android Code Migration to KMP
Baidu Geek Talk
Baidu Geek Talk
May 18, 2026 · R&D Management

Automating the Full Development Cycle with Claude Code’s /prd, /goal, and /after-goal

Using a real-world case, the article demonstrates how Claude Code’s three slash commands—/prd, /goal, and /after-goal—can fully automate a development workflow, turning requirement decomposition into structured PRDs, card‑based implementation, and automatic code submission, review, and closure, thereby boosting efficiency and consistency.

AI automationCI/CDCLI
0 likes · 14 min read
Automating the Full Development Cycle with Claude Code’s /prd, /goal, and /after-goal
AgentGuide
AgentGuide
May 18, 2026 · Artificial Intelligence

AI Agent Essentials: Tokens, Skills, RAG, MCP, SDD & Harness Engineering

The article explains AI Agents as LLM‑based entities with planning, memory, and tool‑use capabilities, covering model pre‑training, fine‑tuning, hallucinations, the Model Context Protocol (MCP), tokenization, Retrieval‑Augmented Generation (RAG), multi‑layer memory, Skill packaging, ReAct reasoning‑action loops, self‑reflection, Harness engineering, and Spec‑Driven Development (SDD).

AI agentHarness EngineeringLLM
0 likes · 9 min read
AI Agent Essentials: Tokens, Skills, RAG, MCP, SDD & Harness Engineering
Linyb Geek Road
Linyb Geek Road
May 18, 2026 · Artificial Intelligence

Building High‑Availability Claude Skills: From Core Mechanics to Production‑Ready Development

This article explains why a perfectly written Claude Skill may never be invoked, reveals the underlying meta‑tool architecture, demonstrates the three‑level progressive loading model that saves up to 80% of token usage, and provides a step‑by‑step guide, code samples, debugging checklists, and best‑practice patterns for creating robust, production‑grade Claude Skills.

AI toolsClaudeSkill
0 likes · 30 min read
Building High‑Availability Claude Skills: From Core Mechanics to Production‑Ready Development
Wuming AI
Wuming AI
May 12, 2026 · Operations

How Two Custom Skills Eliminate Manual Photo Downloads

The article explains how the author packaged repetitive photo‑album download tasks into two Skills—alltuu-downloader and photoplus-downloader—so that an AI Agent can automatically fetch original images from cloud albums, saving users from clicking each picture individually.

AI agentAutomationGitHub
0 likes · 6 min read
How Two Custom Skills Eliminate Manual Photo Downloads
IT Services Circle
IT Services Circle
May 6, 2026 · Artificial Intelligence

How to Cut Large‑Model Token Usage by Over 90%

The article analyses why AI Skills waste massive token counts, demonstrates a pure‑Skill implementation that costs $10 and 12 minutes, then shows a code‑plus‑model hybrid that reduces runtime to 17 seconds, API calls to one, and cost to $0.004, saving more than 99% of tokens.

ClaudeOpenRouterPlaywright
0 likes · 19 min read
How to Cut Large‑Model Token Usage by Over 90%
inShocking
inShocking
May 4, 2026 · Artificial Intelligence

When Claude’s Bad Schedule Made Me Laugh, I Built My First No‑Code Skill

After Claude Code produced a ridiculous daily plan, I dissected its flaws, derived five planning principles, designed a nine‑stage workflow, and created the smart‑planner skill that automatically checks weather, asks for personal constraints, breaks tasks, and delivers a human‑friendly schedule.

AI planningAutomationClaude
0 likes · 9 min read
When Claude’s Bad Schedule Made Me Laugh, I Built My First No‑Code Skill
Node.js Tech Stack
Node.js Tech Stack
Apr 28, 2026 · Artificial Intelligence

Turn Your Article Collection into an LLM‑Powered Wiki with a Single Skill

This article walks through using the youdaonote‑llm‑wiki skill to automatically ingest a set of Markdown articles into a cloud‑synced Youdao Note knowledge base, generate structured Wiki pages, perform cross‑document queries with citations, and keep the repository up‑to‑date, while comparing it to Karpathy's original script‑based approach.

AI AgentsKnowledge ManagementLLM Wiki
0 likes · 14 min read
Turn Your Article Collection into an LLM‑Powered Wiki with a Single Skill
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Apr 27, 2026 · Artificial Intelligence

SkVM: A Language VM for Skill Enables One‑Write, Everywhere‑Efficient Execution on Any LLM

SkVM, an open‑source language virtual machine from Shanghai Jiao Tong University’s IPADS team, compiles Skill code once and runs it efficiently across diverse LLMs and Agent harnesses, delivering up to 50× speedups, 40% token savings, and performance comparable to Opus 4.6 on 30B models.

AgentCompilationLLM
0 likes · 10 min read
SkVM: A Language VM for Skill Enables One‑Write, Everywhere‑Efficient Execution on Any LLM
AI Waka
AI Waka
Apr 22, 2026 · Artificial Intelligence

Hybrid MCP‑Skill Model: Keeping LLM Agent Skills Fresh

The article analyzes the trade‑offs between packaging new agent functionality as a static Skill versus a dynamic MCP server, proposes a hybrid thin‑CLI approach that combines the ease of Skills with the up‑to‑date guarantees of MCP, and illustrates the design with concrete code examples.

API VersioningCLI wrapperLLM Agents
0 likes · 7 min read
Hybrid MCP‑Skill Model: Keeping LLM Agent Skills Fresh
Machine Heart
Machine Heart
Apr 21, 2026 · Artificial Intelligence

Is Your Skill Document Slowing Down the Model? Strategy‑Based Genes Are the Better Solution

The article analyses why large, document‑style Skill packages often degrade large‑model performance under limited inference budgets, introduces the compact, control‑dense Gene representation and the Gene Evolution Protocol (GEP), and shows through thousands of controlled experiments and CritPt benchmarks that Genes consistently outperform Skills, especially when token budget is tight.

AgentGeneSkill
0 likes · 15 min read
Is Your Skill Document Slowing Down the Model? Strategy‑Based Genes Are the Better Solution
AI Waka
AI Waka
Apr 17, 2026 · Artificial Intelligence

Why Claude Code’s Slash Commands Matter and How They Evolve into Skills

This article examines Claude Code’s slash commands—defining their purpose, scope, parameter model, and limitations—while showing why they’re being folded into the newer Skill system to improve modularity, dynamic context injection, and long‑term maintainability for AI‑driven workflows.

AIClaudePromptEngineering
0 likes · 23 min read
Why Claude Code’s Slash Commands Matter and How They Evolve into Skills
Tech Verticals & Horizontals
Tech Verticals & Horizontals
Apr 15, 2026 · Artificial Intelligence

How Hermes Enables AI to Remember, Learn, and Grow Autonomously

The article dissects Hermes’s autonomous learning loop, detailing how immutable facts are stored in long‑term memory, reusable methods become skills, session history is searchable, and a background review process periodically consolidates knowledge while a pre‑compression rescue safeguards key information.

AIContext CompressionHermes
0 likes · 15 min read
How Hermes Enables AI to Remember, Learn, and Grow Autonomously
Wuming AI
Wuming AI
Apr 14, 2026 · Industry Insights

Why Chat History Isn't Enough: Building a Personal AI Knowledge Base

The article details a step‑by‑step journey of creating a private, continuously evolving AI knowledge base—from single‑file markdown archives to modular Skills, data sanitization, Git‑based version control, and automated daily curation—showing why richer personal data and closed‑loop feedback are essential for a truly useful AI assistant.

AI assistantOpenClawRAG
0 likes · 11 min read
Why Chat History Isn't Enough: Building a Personal AI Knowledge Base
Shuge Unlimited
Shuge Unlimited
Apr 10, 2026 · Artificial Intelligence

How Zilliz’s Two Skills Enable AI to Code with pymilvus and Manage Cloud Clusters

This article dissects Zilliz’s Milvus Skill and Zilliz Cloud Skill, showing how a modular set of reference files teaches AI agents to generate pymilvus Python code for vector databases and to operate Zilliz Cloud via CLI, while comparing their architecture, security design, and ecosystem role.

AI agentCloud ManagementHybrid Search
0 likes · 20 min read
How Zilliz’s Two Skills Enable AI to Code with pymilvus and Manage Cloud Clusters
Sohu Tech Products
Sohu Tech Products
Apr 8, 2026 · Artificial Intelligence

Turn GitHub Repo Search into an AI Skill: A Step‑by‑Step Guide

This article walks through creating an AI skill that leverages natural‑language queries to search GitHub repositories, explains how the skill parses input, applies synonym expansion and relevance filtering, and presents results in a table with stars, license and links, all demonstrated with a live example.

AIAutomationGitHub
0 likes · 4 min read
Turn GitHub Repo Search into an AI Skill: A Step‑by‑Step Guide
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Apr 7, 2026 · Artificial Intelligence

One‑Click White‑Label ClaudeCode: Custom Commands, Startup Screen, and Isolated Config via a Reusable Skill

The article explains how the author built a reusable Skill that automates the creation of a white‑labeled ClaudeCode CLI, allowing custom branding, commands, startup animation, third‑party API integration, and configuration isolation, while avoiding the pitfalls of manual source modification.

AI CLIClaudeGitHub
0 likes · 6 min read
One‑Click White‑Label ClaudeCode: Custom Commands, Startup Screen, and Isolated Config via a Reusable Skill
ByteDance Data Platform
ByteDance Data Platform
Apr 3, 2026 · Industry Insights

From Personal Assistant to Enterprise Digital Partner: How AI Can Run an Entire Store in 12 Hours

The article analyzes Volcano Engine's AI-driven "digital partner" strategy, detailing how functional Skills transform generic assistants into enterprise‑level collaborators that automate end‑to‑end store operations, from data retrieval and analysis to decision‑making and report generation.

AIAutomationBusiness Intelligence
0 likes · 10 min read
From Personal Assistant to Enterprise Digital Partner: How AI Can Run an Entire Store in 12 Hours
DeWu Technology
DeWu Technology
Apr 1, 2026 · Backend Development

How AI‑Powered /log‑diagnosis Skill Automates Bug Tracing in Backend Logs

This article explains how the /log‑diagnosis Skill, built on Claude Code and the Model Context Protocol (MCP) log platform, creates a closed‑loop workflow that automatically fetches logs, extracts key information, maps it to source code, diagnoses root causes, and generates remediation suggestions, dramatically speeding up backend debugging.

AI debuggingClaude CodeLog Analysis
0 likes · 17 min read
How AI‑Powered /log‑diagnosis Skill Automates Bug Tracing in Backend Logs
Tencent Tech
Tencent Tech
Mar 24, 2026 · Artificial Intelligence

Unlocking AI Power: How Skill Packages Transform Large Language Models

This article provides a comprehensive technical guide to Skill packages—standardized knowledge containers that give large language models expert-level execution capabilities—covering their definition, architecture, integration with the Model Context Protocol (MCP), creation workflow, best‑practice tips, collaborative patterns, debugging strategies, philosophical implications, and future directions.

AI toolingKnowledge ManagementLLM
0 likes · 18 min read
Unlocking AI Power: How Skill Packages Transform Large Language Models
SuanNi
SuanNi
Mar 19, 2026 · Artificial Intelligence

5 Proven Design Patterns for Building Smarter Google AI Agents

Google's engineers distilled five recurring design patterns for Agent Skills—Tool Wrapper, Generator, Reviewer, Inversion, and Pipeline—providing concrete guidance, example implementations, and visual decision trees to help developers craft more reliable and context‑aware AI agents.

AI AgentsAgent Development KitDesign Patterns
0 likes · 9 min read
5 Proven Design Patterns for Building Smarter Google AI Agents
Black & White Path
Black & White Path
Mar 17, 2026 · Artificial Intelligence

Supercharge OpenClaw with Skills: A Complete Usage Guide

This guide explains what OpenClaw Skills are, why they matter, how to install and enable them, how to create custom Skills, and highlights the curated Awesome-openclaw-skills repository that categorizes thousands of high-quality Skills for AI agents, plus practical tips for combining and optimizing them.

AI agentAutomationCLI
0 likes · 7 min read
Supercharge OpenClaw with Skills: A Complete Usage Guide
Tencent Cloud Developer
Tencent Cloud Developer
Mar 17, 2026 · Artificial Intelligence

Why Anthropic Skips Function Calling: Inside the 5 Skill Execution Modes

This article dissects Anthropic's Skill framework, revealing how it drives AI agents through five distinct execution modes—pure prompt injection, script execution, library calls, progressive document loading, and workflow orchestration—while avoiding function‑calling registration and optimizing token usage.

AIAgentFunction Calling
0 likes · 32 min read
Why Anthropic Skips Function Calling: Inside the 5 Skill Execution Modes
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 13, 2026 · Artificial Intelligence

Why Your AI Agent Feels Stupid and How a Word‑Card Skill Makes It an Expert in 5 Minutes

The article shows that an AI Agent becomes useful only when equipped with Skills, walks through creating a word‑card generation Skill in four steps, demonstrates a high‑vs‑tall example that cuts production time from 45‑85 minutes to 5 minutes, and explains how similar Skills can automate information integration, mining, and output across many domains.

AutomationInformation IntegrationMulti‑agent
0 likes · 11 min read
Why Your AI Agent Feels Stupid and How a Word‑Card Skill Makes It an Expert in 5 Minutes
Baidu Geek Talk
Baidu Geek Talk
Mar 9, 2026 · Artificial Intelligence

Mastering Agent Skills: Design, Implementation, and Evaluation for Efficient AI Workflows

This article explains why large‑model agents need structured Skills to capture team‑specific knowledge and workflows, describes the evolution from MCP to Skill, details the progressive‑disclosure design, shows how to write, organize, and install Skills, and provides a systematic evaluation and iteration process to ensure high‑quality, token‑efficient agent behavior.

AISkill
0 likes · 26 min read
Mastering Agent Skills: Design, Implementation, and Evaluation for Efficient AI Workflows
Java Backend Technology
Java Backend Technology
Mar 5, 2026 · Artificial Intelligence

How to Slash AI Token Costs: MCP vs Skill and 6 Proven Optimization Techniques

This article explains the fundamental differences between web session tokens and AI tokens, compares MCP and Skill token consumption, presents pricing formulas for major models, and offers practical strategies—including prompt compression, context management, and dynamic toolsets—to dramatically reduce AI token expenses.

Artificial IntelligenceCost ManagementMCP
0 likes · 16 min read
How to Slash AI Token Costs: MCP vs Skill and 6 Proven Optimization Techniques
Alibaba Cloud Developer
Alibaba Cloud Developer
Mar 2, 2026 · Artificial Intelligence

Why Spec Coding Beats Vibe Coding: Proven Practices for AI‑Assisted Development

The article examines the evolution of AI‑assisted programming in 2025, contrasts Vibe Coding with Spec Coding, outlines five core context‑engineering patterns, details the Skill vs. Subagent model, and presents a practical workflow system (kuspec) for building, initializing, and executing AI‑driven development tasks.

AI codingAutomationSkill
0 likes · 14 min read
Why Spec Coding Beats Vibe Coding: Proven Practices for AI‑Assisted Development
BirdNest Tech Talk
BirdNest Tech Talk
Feb 19, 2026 · Artificial Intelligence

How to Automate Daily News Briefings with OpenClaw: Skill vs Prompt

This guide walks through two practical approaches—Skill and Prompt—to configure OpenClaw for automated RSS aggregation, AI‑driven filtering, summarization, and channel delivery, comparing their setup steps, code examples, advantages, limitations, and when to choose each method.

AI assistantAutomationOpenClaw
0 likes · 8 min read
How to Automate Daily News Briefings with OpenClaw: Skill vs Prompt
AI Tech Publishing
AI Tech Publishing
Feb 18, 2026 · Artificial Intelligence

Empowering Agents with Skills: Let Specialized Agents Handle Expert Tasks

This tutorial shows how to extend the MiniManus agent framework with Skill support, explains why Skills are needed compared to plain MCP, details the Claude Skill specification, provides concrete command‑line operations, code implementations, and demonstrates Skill‑MCP collaboration through practical examples.

AgentGitHubMCP
0 likes · 10 min read
Empowering Agents with Skills: Let Specialized Agents Handle Expert Tasks
IT Services Circle
IT Services Circle
Feb 9, 2026 · Artificial Intelligence

Explore 6 Open‑Source AI Skills for Video, Docs, and Social Media Automation

This article introduces six open‑source AI skills—including Remotion video generation, YouTube clipping, expert‑knowledge extraction, NotebookLM integration, Markdown publishing to X, and Anthropic's public skill repository—detailing their purpose, core functionality, installation commands, and repository links for developers seeking automation solutions.

AIClaudeNotebookLM
0 likes · 7 min read
Explore 6 Open‑Source AI Skills for Video, Docs, and Social Media Automation
Alibaba Cloud Developer
Alibaba Cloud Developer
Feb 4, 2026 · Artificial Intelligence

Progressive Disclosure: Making Multi‑Skill LLM Agents Efficient and Scalable

This article examines the core challenge of giving large‑language‑model agents many abilities while keeping context size limited, compares three common loading strategies, introduces a progressive‑disclosure skill mechanism with three loading layers, and details its implementation, benefits, limitations, and suitable use cases in AgentScope‑Java.

AgentContext ManagementJava
0 likes · 17 min read
Progressive Disclosure: Making Multi‑Skill LLM Agents Efficient and Scalable
AI Tech Publishing
AI Tech Publishing
Jan 29, 2026 · Industry Insights

Why You Might Skip Skills to Avoid Repeating MCP’s Failure

The article examines the rise and fall of MCP, explains why simply adding AI‑driven Skills without rethinking workflows leads to “skill debt,” and outlines three hidden costs—expert knowledge capture, version drift, and context explosion—while proposing practical solutions such as experience capture, Skill‑as‑Code testing, and dynamic routing.

AIMCPOrganizational Change
0 likes · 9 min read
Why You Might Skip Skills to Avoid Repeating MCP’s Failure
AI Tech Publishing
AI Tech Publishing
Jan 27, 2026 · Artificial Intelligence

Step‑by‑Step: Adding Skill Capabilities to Your Agent System

This article walks through the design patterns, three‑level loading mechanism, and practical implementation steps for integrating reusable, domain‑specific Skills into an existing Agent system, covering both local and distributed deployments with Redis‑based versioning and sandboxed execution.

AgentLLMMeta-Tool Pattern
0 likes · 14 min read
Step‑by‑Step: Adding Skill Capabilities to Your Agent System
Efficient Ops
Efficient Ops
Jan 26, 2026 · Artificial Intelligence

Why AI Skills Will Redefine Agents Beyond MCP

This article explains how AI Skills serve as structured knowledge bases that complement, rather than replace, Model Context Protocols, enhance Retrieval‑Augmented Generation, and drive three major trends—standardized agent stacks, low‑code knowledge engineering, and the emergence of personal AI agents.

AI AgentsAI ecosystemKnowledge Engineering
0 likes · 8 min read
Why AI Skills Will Redefine Agents Beyond MCP
Alibaba Cloud Developer
Alibaba Cloud Developer
Jan 22, 2026 · Artificial Intelligence

How to Build a Prompt‑Optimizer Skill for Claude Using AI Coding Tools

This article explains the common difficulties of writing effective prompts, introduces the open‑source prompt‑optimizer skill that automatically selects and refines professional prompt frameworks, and provides step‑by‑step instructions for preparing materials, packaging the skill for Claude and Chrome, and installing it via GitHub repositories.

AI codingClaudeGitHub
0 likes · 10 min read
How to Build a Prompt‑Optimizer Skill for Claude Using AI Coding Tools
Frontend AI Walk
Frontend AI Walk
Jan 9, 2026 · Frontend Development

From Pitfalls to Skill: Implementing a Peekable Horizontal Card Swipe with Vant

This article walks through common issues when using Vant's van-swipe for a horizontal card list—such as the last card being clipped and the peek effect being hidden—and presents a three‑layer nesting solution with detailed CSS, Vue code, a self‑test checklist, and a reusable skill definition to streamline future development.

CSSSkillVant
0 likes · 15 min read
From Pitfalls to Skill: Implementing a Peekable Horizontal Card Swipe with Vant