Loading patterns…
Agent Skills(AS)
Capabilities packaged as self-contained folders. Each skill is a SKILL.md file with YAML frontmatter (name and description) plus optional scripts and resources. Agents discover skills by their metadata and load them through three levels of progressive disclosure: read name and description to judge relevance, load the full SKILL.md once activated, then execute bundled scripts and resources on demand. This keeps context small while exposing many capabilities, and the format is an open standard adopted across vendors.
In 30 seconds
- What
- Packages agent capabilities as self-contained folders with metadata, instructions, and scripts. Agents load only active skill content into context while keeping a lightweight index of all available skills.
- When to use
- Agents need access to many tools but limited context window, or when skills must be portable across different agent platforms and vendors.
- Watch out
- Scripts may fail silently or produce unexpected output if the agent misunderstands skill preconditions or mismatches input formats.
Ask the AI expert about this pattern
Opens the assistant with your question prefilled. You review it before sending.
Agent Skills: Overview
Capabilities packaged as self-contained folders. Each skill is a SKILL.md file with YAML frontmatter (name and description) plus optional scripts and resources. Agents discover skills by their metadata and load them through three levels of progressive disclosure: read name and description to judge relevance, load the full SKILL.md once activated, then execute bundled scripts and resources on demand. This keeps context small while exposing many capabilities, and the format is an open standard adopted across vendors.
- Self-contained folder with SKILL.md, scripts, and resources
- YAML frontmatter metadata (name, description) drives discovery
- Three-level progressive disclosure: metadata, full instructions, bundled files
- Only the active skill's full content enters the context window
- Bundled executable scripts run deterministic work outside the model
- Open, cross-vendor format that is portable between agents
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.
References
The papers, specifications, and repositories this pattern is based on.
From the engineer behind this catalog
Get your agent architecture reviewed
This page documents one pattern. Your system runs dozens, and most failures live in how they fit together. Have the whole design reviewed against the 288 patterns in this catalog: architecture, reliability, evaluation and cost, every finding mapped to the pattern that fixes it.
€750 instead of €1,500, one week, written report and walkthrough call, until 30 September