4 design skills that improved my UIs
Give AI the taste it's missing! 🎨
Anthropic's frontend-design, Emil Kowalski's design skill, Taste Skill, and Impeccable give AI agents the taste to ship interfaces that actually stand out.
Blog
Articles tagged "Agent Workflows"
-
- Mini
What Is a Claude Code Plugin?
Install one, enable it, disable it — and when you'd actually want to. 🚦
Claude Code plugins extend your agent with skills, agents, hooks, and MCP servers — packaged and distributed through marketplaces. Here's how they work and how to use them.
- Mini
Superpowers: Stop Claude From Vibe Coding
Skills, workflows, and guardrails for turning Claude into a disciplined coding agent. 🤖
Superpowers is an open-source plugin that injects structured development skills — TDD, debugging, planning, code review — into Claude Code and other AI agents. Here's how it works.
-
Git Worktrees: Stop Being Afraid of Them
One repo, multiple working directories; the safest way to let AI agents work in parallel.
Git worktrees let you check out multiple branches simultaneously in separate directories. For AI agents running in parallel, they're not a nice-to-have — they're the only way to avoid chaos.
-
What is Harness Engineering?
Prompt → Context → Harness: the infrastructure layer for AI agents 🔧
Harness engineering is the complete environment you build around an AI model — tools, constraints, feedback loops, and context. Learn what it is, how it differs from prompt and context engineering, and how to start building one.
-
10 Tools to Stop Burning Your Claude Code Tokens
Your context window is leaking. Some ideas to fix it. 🐑
A hands-on guide to 10 tools that cut Claude Code token usage by 40–98%. Covers installation, usage, and when to use each one.
-
RTK 101: Cut Your Claude Token Usage by 80%
Stop paying for output noise your AI doesn't need 🪙
A hands-on guide to installing RTK, wiring it to Claude Code in minutes, and immediately slashing the token cost of every git, test, and file command you run.
-
AGENTS.md, Instructions, and Path-Specific Rules
Right layer. Right context. 🏗️
Most teams are not bad at giving AI context. They're bad at putting the right context in the right layer. Here's a practical, architecture-aware framework for AGENTS.md, repo-wide instructions, and path-specific overrides.
-
Spec-Driven Development and GitHub Spec Kit
Stop vibe coding. Start with intent. 🎯
Spec-driven development is the antidote to vibe coding. Learn what it is, how GitHub's Spec Kit operationalizes it with slash commands and artifacts, and whether it's worth the overhead.
-
Copilot Hooks Preview: Master lifecycle control over your AI agent
trigger → condition → action 🎣
Learn how VS Code Copilot hooks let you run shell commands at key agent lifecycle points — block dangerous operations, auto-format code, inject context, and build audit trails.
-
Getting Started with WebMCP: Expose Your Website to AI Agents
Make your site agent-ready 🤖
Learn how to use WebMCP to expose structured tools from your website to in-browser AI agents. Set up Chrome Canary, implement declarative and imperative APIs, and build agent-aware forms — no MCP server required.
-
Create your first Copilot Agent with full context
Learn to feed the beast! 🤖
Learn how to create AI agents that understand your entire codebase using Repomix and GitHub Copilot. Build intelligent assistants for your development team.