v0.3 · Updated 2026-05-22 · A-to-Z guide

Everything Claude,
in one place.

The pro reference for working with Claude across every surface — skills, MCP servers, plugins, slash commands, hooks, the API, and the 4.x model family. Built for engineers who ship.

0skills indexed
0MCP servers
0guide pages
0Claude surfaces
📄 pdf 🎨 figma-use 🔒 security-review
Features / Bento · 6 cols × 2 rows
Concept

What is a Claude Skill?

A portable, model-agnostic capability bundle. Three pieces, one folder.

SKILL.md is the contract

YAML frontmatter says when the skill loads. Markdown body says what to do. That's the whole interface — no SDK, no compile step, no runtime.

--- name: my-skill description: Trigger when… ---

Bundled assets

Scripts, templates, schemas, reference docs — anything Claude reads or executes while the skill is active. Loaded lazily.

Progressive disclosure

Only the description is always loaded. Body + bundled files pulled only when the skill triggers.

1 Description always loaded
2 Body loaded on trigger
3 Files opened on demand

Cross-surface

Same folder works in Claude Code, API, claude.ai, and desktop.

Scoped tools

allowed-tools caps what a skill can do. Safer by default.

Composable

Skills stack. One prompt can light up many at once.

Install / Surfaces · Grid 2×2
Install

Install on any Claude surface

Skills work in Claude Code (CLI + IDE), the Claude API, claude.ai, and the desktop apps.

CLI

Claude Code

Drop a skill folder into ~/.claude/skills/ (user) or .claude/skills/ (project). Restart the session — Claude auto-discovers it.

# user-wide
git clone https://github.com/anthropics/skills ~/.claude/skills-src
cp -r ~/.claude/skills-src/document-skills/pdf ~/.claude/skills/
Full Claude Code instructions →
API

Claude API

Use the code_execution tool plus the Skills container. Upload skill folders to the Files API and reference them in your request.

# Anthropic SDK
client.beta.messages.create(
  model="claude-opus-4-7",
  betas=["skills-2025-10-02"],
  container={"skills": ["pdf", "xlsx"]},
  ...
)
Full API instructions →
WEB

claude.ai

Settings → Capabilities → Skills. Toggle the official Anthropic skills (PDF, Word, Excel, PowerPoint) or upload a custom one as a folder.

Walkthrough with screenshots →
MCP

via Plugins / MCP

Some skills ship as part of a Claude Code plugin or MCP server (e.g., Figma, Playwright). Install via the plugin marketplace or claude plugin install.

Plugin install guide →
FAQ

Common questions

Short answers to the questions people ask most often about Claude, skills, MCP, and the API.

What is a Claude Agent Skill?

A skill is a folder containing a SKILL.md file (YAML frontmatter + markdown body) plus optional scripts and reference files. Claude loads the skill on demand when a user's prompt matches its description — extending what Claude can do without bloating every prompt. See the concept guide.

Where do I put my Claude skills?

User-scope skills go in ~/.claude/skills/<skill-name>/. Project-scope skills go in .claude/skills/ inside the repo. Claude Code auto-discovers both at session start. For claude.ai, upload skills via Settings → Capabilities → Skills.

What is MCP (Model Context Protocol)?

MCP is the open JSON-RPC protocol Claude uses to talk to external systems — databases, APIs, your own tools. You install MCP servers (Postgres, GitHub, Slack, Figma, etc.) and Claude can call their tools mid-conversation. Read the MCP guide.

Which Claude model should I use?

Default to Claude Sonnet 4.6 — strong, fast, ~5× cheaper than Opus. Use Claude Opus 4.7 for hard reasoning, large refactors, and multi-step plans. Use Claude Haiku 4.5 for high-volume routing and classification. See the model comparison.

How do I install Claude Code?

Run npm install -g @anthropic-ai/claude-code, then claude in your project. Sign in with claude.ai (subscription) or an API key. Full setup walkthrough in the Quickstart.

What's the difference between a skill, a slash command, and an MCP server?

Skills trigger automatically from natural-language matching. Slash commands are user-typed shortcuts (/review). MCP servers are long-running processes that expose tools Claude can call. They layer together — skills can call MCP tools, slash commands can invoke skills.

How does prompt caching reduce API costs?

Mark a stable prompt prefix (system prompt, big context doc, tool definitions) with cache_control: {"type": "ephemeral"} and cache hits within 5 minutes are ~90% cheaper. Heavy users see the cache extend for hours. See the API caching guide.

Is ClaudeBro affiliated with Anthropic?

No. ClaudeBro is an unofficial community resource. All Claude trademarks and skill names belong to their respective owners. Official documentation lives at docs.claude.com.