Skill Frontmatter - Claude Code
Configure model, effort, tools, MCP servers, and invocation scope.
Skill frontmatter is a YAML block at the top of a skill file that controls how the skill runs and when it triggers.
What it does
The frontmatter declares the skill's name, description, model preference, effort level, allowed tools, MCP servers, and other per-skill config. Claude reads these fields to decide when to auto-invoke the skill and how to execute it. The description field is especially important - it's what Claude uses to match user intent to the skill.
When to use it
- Locking a skill to a specific model or effort level for predictable results.
- Restricting tools so a skill can't do more than it should.
- Tuning descriptions for reliable auto-invocation.
- Declaring required MCP servers so the skill fails fast if they're missing.
Gotchas
- Bad descriptions lead to bad auto-invocation. Write them like ads: clear triggers and scope.
- Tool restrictions apply strictly. If a skill tries to use an unlisted tool, it fails.
- Model settings in frontmatter can override the session's current model - intentional, but surprising.
Official docs: https://code.claude.com/docs/en/skills.md#frontmatter-reference
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools - delivered free every week.
Was this helpful?
Related Guides
Related Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory...
View ToolCodeburn
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
View ToolZed
High-performance code editor built in Rust with native AI integration. Sub-millisecond input latency. Built-in assistant...
View ToolCursor
AI-native code editor forked from VS Code. Composer mode rewrites multiple files at once. Tab autocomplete predicts your...
View ToolRelated Videos

Composio: Connect OpenClaw & Claude Code to 1,000+ Apps via CLI
Composio: Connect AI Agents to 1,000+ Apps via CLI (Gmail, Google Docs/Sheets, Hacker News Workflows) Check out Composio here: http://dashboard.composio.dev/?utm_source=Youtube&utm_channel=0426&utm_...

Claude Code Channels in 8 Minutes
Anthropic has released Channels for Claude Code, enabling external events (CI alerts, production errors, PR comments, Discord/Telegram messages, webhooks, cron jobs, logs, and monitoring signals) to b...

Claude Code Loops in 7 Minutes
Claude Code “Loop” Scheduling: Recurring AI Tasks in Your Session The script explains Claude Code’s new “Loop” feature (an evolution of the Ralph Wiggins technique) for running recurring prompts that...
Related Posts

Anthropic Sonnet 4.5 in Claude Code
Anthropic's Claude Sonnet 4.5 isn't just another model increment. The company claims they've observed it maintaining foc...

12 Tools in One Night: An Honest Overnight Agent Report
I told an agent to improve the site every 10 minutes and went to sleep. Here is what 12 new repos, 60 PRs, and three goo...

Agent Replays with TraceTrail: Loom for Agent Runs
Agent runs are opaque. TraceTrail turns a Claude Code JSONL into a public share link with a stepped timeline of messages...
