
How to Install Claude Skills from GitHub
Learn how to install Claude Skills from GitHub the safe way: copy the SKILL.md folder, add a plugin marketplace, verify it loaded, and vet untrusted code.
Category
Hands-on guides to Claude Code — Anthropic's terminal coding agent — from install and first run to MCP, subagents, hooks, and the errors you'll actually hit.
Claude Code is the agent we run all day: this entire site is built and maintained in it, so the guides in this category are written from the driver's seat. That means the workflow advice, the model-routing habits, and the troubleshooting come from real sessions on a real project, not a feature tour. Where a fix only reveals itself after you've hit it a dozen times, that's the kind of detail we try to capture here.
Start with what Claude Code is and how to install it, then move into the pieces that make it powerful — MCP servers, subagents, memory files, permissions, and headless automation — and keep the error guides handy for when a run stalls. Whether you're deciding if it's worth a subscription or wiring it into CI, the goal of this collection is to shorten the gap between installed and genuinely productive.


Learn how to install Claude Skills from GitHub the safe way: copy the SKILL.md folder, add a plugin marketplace, verify it loaded, and vet untrusted code.

Claude Code environment variables explained: which ones matter, what each one does, and how to set them safely in your shell or a settings.json env block.

Worried Claude Code deleted my database? Here is why AI agents run destructive commands, how to prevent data loss, and what to do if it already happened.

Super Claude Code — the SuperClaude framework — adds 20+ slash commands, 9 personas, and MCP servers to Claude Code. What it does and how to install it.

An honest roundup of the best claude code alternatives — Cursor, Copilot, Aider, Codex CLI, Gemini CLI, and Cline — with a comparison table and guidance.

Learn how to install and run Claude Code on Windows with the native PowerShell installer or npm, set up your terminal, log in, and fix common gotchas.

Learn how to check your Claude Code token usage in a session. Use /context to see the context window and /cost to track tokens, with quick tips to free space.

The best Claude model for coding is Sonnet 5 for everyday work and Opus 5 for hard, architectural problems. See how Opus, Sonnet, and Haiku compare.

Learn how to build a Claude Skill from scratch: the SKILL.md structure, writing a description that triggers it, clear instructions, and how to test it.

The full math behind our Claude Code cost calculator: what an hour burns in tokens, per-model API rates, plan hour caps, and worked API-vs-plan examples.

What Claude Code really costs one developer: what Pro's $20 covers, the honest triggers for Max 5x and Max 20x, why Team never fits one person, and when the API wins.

Claude Code cost per developer is $20-$200 a month on a seat, or $150-$250 metered. Real seat math, the Team seat misconception, and costs by team size.

Claude Code Bedrock setup explained: the exact env vars, IAM policy, region and model pinning, plus honest trade-offs against the Anthropic API.

How to add MCP to Claude Code with claude mcp add — stdio and HTTP servers, local/project/user scopes, the .mcp.json file, and how to verify and manage them.

The Claude Code plugin marketplace installs commands, agents, MCP servers, and hooks in one command. How to add a marketplace, install, and build your own.

Claude Code ultrathink is still a real keyword, but not the old token-budget trick. Here's what it actually does now, and when deeper thinking is worth it.

Claude skills for designers turn mockups into code, generate assets, and build design systems. See the best skills for UI/UX work and how to add them fast.

The best Claude skills to install, from document and PDF handling to Obsidian, LinkedIn, and design — what each does, who it's for, and how to add them.

Run Claude Code in Zed through the ACP integration. Learn how it works, how to set it up and log in, and how it compares to using the plain terminal CLI.

Learn how the claude code max output tokens setting works, how to set CLAUDE_CODE_MAX_OUTPUT_TOKENS in your shell or settings, and how to fix truncated replies.

Learn the claude code spec workflow: turn a feature into requirements, design, and tasks, then have Claude build it phase by phase with reviews you can trust.

A complete Claude Code installation guide: prerequisites, the native installer, the npm command, platform notes for macOS, Linux, and Windows, and fixes.

A practical guide to the Claude Code security review: run the /security-review command and the GitHub Action to catch vulnerabilities before you merge.

A practical guide to the figma claude mcp setup: connect Figma to Claude via a Figma MCP server so Claude can read your designs and build accurate code.