Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
OpenClaw vs. Claude Code vs. Codex: Understanding Skill Distribution Across AI Coding Agents
Three AI coding agents now dominate the skill ecosystem: Claude Code, OpenAI Codex, and OpenClaw. All three use SKILL.md files. All three can run scripts, read references, and activate skills based on natural language prompts. But the way each agent distributes skills — how you install them, where they live, and who controls the catalog
-
Build a Skill That Writes SEO-Optimized Blog Posts Automatically
Step-by-step tutorial for building an agent skill that writes SEO-optimized blog posts. Covers SKILL.md structure, progressive disclosure with references/, keyword integration, and real gotchas.
-
Runbook Skills: Turn Your Incident Response Into Reusable Agent Playbooks
Learn how runbook skills encode your team’s incident response knowledge into reusable agent playbooks. Includes a complete SKILL.md example for server triage.
-
Skill Spotlight: The Frontend Design Skill That Makes Beautiful UIs Automatic
Explore the frontend-design skill that gives AI agents expert-level UI knowledge. See how it structures layouts, picks modern fonts, and generates polished interfaces without manual design work.
-
The Gotchas Section: The Single Most Valuable Part of Any Skill
Anthropic engineer Thariq called it the “highest-signal content” in any skill. After reviewing hundreds of SKILL.md files submitted to AgentSkillExchange, we agree—but we’d go further. The gotchas section is the single thing that separates skills that work from skills that frustrate everyone who installs them. This post breaks down what makes a gotchas section effective,
-
The Agent Skills Ecosystem Is Exploding — March 2026 Roundup
March 2026 saw 87K GitHub stars, 30+ platform adoptions, and the first major security audits. Here is what happened in the agent skills ecosystem this month.
-
MCP vs. Agent Skills: What’s the Difference and When to Use Each
MCP vs agent skills explained clearly: what each one does, where each fits, and how to combine them for better AI workflows.
-
How to Build a Code Review Skill That Catches What Linters Miss
Build a code review agent skill that enforces architectural patterns, catches security issues, and applies team conventions that static analysis tools can’t detect. Full SKILL.md walkthrough with examples.
-
Library & API Reference Skills: Teaching AI to Use Your Stack Correctly
Library & API reference skills fix the stale-knowledge problem by teaching Claude how to use your specific libraries, CLIs, and SDKs correctly. Here’s how to build them.
-
Skill Spotlight: How the GitHub Issues Skill Automates Your Entire Bug Workflow
The gh-issues skill fetches GitHub issues, spawns parallel sub-agents to implement fixes, opens PRs, and handles review comments — all without human intervention.