What are Agent Skills?
Agent Skills are folders of instructions, prompts, examples, and resources that an LLM can load when relevant to perform specialized tasks consistently. Instead of putting everything in the system prompt, skills let you modularize expertise.
"Skills are like apps for your agentâinstall them once, use them whenever needed."
Just as you install apps on your phone for specific functions, skills give agents specialized capabilities without bloating every conversation.
How Agent Skills Work
Skill Discovery
When a user request comes in, the agent checks if any available skills match the task based on triggers, keywords, or explicit invocation.
Skill Loading
The relevant skill's instructions, examples, and context are loaded into the agent's working memory. This adds specialized knowledge without polluting the base system prompt.
Skill Execution
The agent follows the skill's instructions to complete the task, using any provided templates, checklists, or scripts. Results are returned to the user.
Interactive Skill Demo
Explore how skills are triggered, their manifest structure, and skill chaining
User Input
Type a message to see which skill would be triggered
Try these examples:
Skill Match
The skill that would be triggered
Type a message to see skill matching in action
Available Skills
Skill Structure
Anatomy of a skill folder
SKILL.md is the entry point. It contains metadata (name, triggers, description) and the core instructions the agent follows.
Types of Agent Skills
Domain Skills
Specialized knowledge for specific fieldsâlegal contracts, medical terminology, financial analysis. Turn a general agent into a domain expert.
Workflow Skills
Multi-step processes with defined stagesâcode review workflows, content publishing pipelines, incident response procedures.
Format Skills
Consistent output formattingâAPI documentation, changelog entries, meeting summaries. Ensure outputs match your standards.
Integration Skills
Instructions for working with specific tools or servicesâGitHub workflows, Jira ticket creation, Slack notifications.
Skills vs. Tools
Tools
- â˘Execute actions (read files, call APIs, run code)
- â˘Defined by function signatures and schemas
- â˘The "hands" of the agent
Skills
- â˘Provide knowledge and methodology (how to approach tasks)
- â˘Defined by instructions and examples
- â˘The "expertise" of the agent
Skills and tools work together: a code review skill tells the agent what to look for, while tools let it read the code and leave comments.
Benefits of Skills
Specialization Without Bloat
Keep the base system prompt lean. Load specialized knowledge only when needed, preserving context window for the actual task.
Consistency
Define a process once, apply it consistently every time. No more variations in how tasks are approached.
Shareability
Skills are just foldersâshare them across projects, teams, or publicly. Build once, use everywhere.
Iteration
Improve skills independently of the agent. Update the code review skill without touching the rest of your agent setup.
Example: Code Review Skill
--- name: code-reviewer description: Performs thorough code reviews following team standards triggers: - "review this code" - "check for bugs" - "code review" --- # Code Reviewer Skill When reviewing code, analyze for correctness, performance, security, and maintainability. ## Checklist - [ ] Check for common security vulnerabilities - [ ] Verify error handling is comprehensive - [ ] Look for performance anti-patterns - [ ] Ensure code follows style guidelines
Best Practices
Keep Skills Focused
One skill, one purpose. If a skill is doing too many things, split it up. Focused skills are easier to maintain and compose.
Include Examples
Show, don't just tell. Include input/output examples that demonstrate exactly what good execution looks like.
Version Your Skills
Track changes to skills over time. When behavior changes unexpectedly, you can trace it back to a skill update.
Key Takeaways
- 1Skills are reusable instruction packages that give agents specialized expertise on demand
- 2Unlike tools (which execute actions), skills provide knowledge and methodology
- 3Well-designed skills improve consistency and reduce system prompt bloat
- 4The skill framework enables modular agent developmentâbuild once, share everywhere