Skip to main content

​
Overview

Agent Skills are reusable packages of instructions and bundled files (scripts, templates, references) that give your agents specialized capabilities. Skills use progressive disclosure — agents see only a skill’s name and description at startup, then load the full instructions on-demand when a matching task comes up. This keeps system prompts lean while letting agents handle complex, specialized workflows when needed.

​
Key Features

​
Progressive Disclosure

  • Agents start with just skill names and descriptions — no prompt bloat
  • Full instructions load on-demand via the load_skill tool
  • Only the skills relevant to the current task are loaded

​
Bundled Files

  • Package scripts, templates, references, and assets alongside your instructions
  • Files are pre-loaded into the Python sandbox at /home/user/skills/{skill-name}/
  • Your SKILL.md instructions tell the agent exactly how to use each bundled file

​
SKILL.md Format

Skills follow the open Agent Skills format — a SKILL.md file with YAML frontmatter for metadata and markdown body for instructions: 
---
name: PDF Report Generator
description: Generate formatted PDF reports from structured data
---

## Instructions

When asked to generate a PDF report:

1. Collect the data from the user
2. Run `scripts/generate_report.py` with the data as JSON input
3. Return the generated PDF to the user

## Available Scripts

- `scripts/generate_report.py` — Takes JSON input, produces formatted PDF

​
Getting Started

​
Creating a Skill

  1. Navigate to Control Hub → Skills
  2. Click “Create Skill”
  3. Paste or write your SKILL.md content with frontmatter
  4. The skill name and description are automatically parsed from the frontmatter

​
Adding Bundled Files

  1. Open your skill from the Skills list
  2. Use the “Upload Files” button to add scripts, templates, or reference materials
  3. Files appear in the bundled files list with size and type information
  4. Reference these files in your SKILL.md instructions by their file path

​
Assigning Skills to Agents

  1. Go to Control Hub → edit your agent
  2. In the Skills section, select which skills this agent can access
  3. The load_skill tool is automatically enabled when skills are assigned
  4. Save the agent configuration

​
How It Works

​
At Chat Time

  1. The agent’s system prompt includes an <available_skills> section listing skill names and descriptions
  2. When the agent recognizes a task that matches a skill, it calls the load_skill tool
  3. The tool returns the full SKILL.md instructions plus a listing of bundled files
  4. The agent follows the instructions, using bundled scripts via execute_python as needed

​
Sandbox Integration

When an agent has skills assigned, all bundled files are automatically pre-loaded into the Python sandbox: 
/home/user/skills/
└── pdf-report-generator/
    ├── SKILL.md
    └── scripts/
        └── generate_report.py
The skill directory name is a slugified version of the skill name (e.g., “PDF Report Generator” → pdf-report-generator).

​
Use Cases

​
Document Generation

  • Bundle Python scripts that generate PDFs, Excel files, or PowerPoint presentations
  • SKILL.md provides step-by-step instructions for when and how to use each script
  • Agent collects data from the user, runs the script, and returns the generated file

​
Data Processing Pipelines

  • Package data transformation scripts with reference schemas
  • Agent loads the skill when asked to process specific data formats
  • Scripts handle the heavy lifting while the agent manages the workflow

​
Specialized Analysis

  • Bundle domain-specific analysis scripts with reference materials
  • Include lookup tables, configuration files, or API documentation
  • Agent uses the skill’s instructions to perform complex analysis tasks

​
Template-Based Workflows

  • Include templates (Excel, markdown, etc.) as bundled files
  • SKILL.md describes how to fill in each template
  • Agent follows the recipe to produce consistent, formatted output

​
Best Practices

​
Writing SKILL.md

  1. Be specific: Tell the agent exactly when to use this skill and what steps to follow
  2. Reference files by path: Use relative paths like scripts/setup.py that match the sandbox structure
  3. Include examples: Show sample inputs and expected outputs
  4. Keep it focused: One skill per workflow — don’t combine unrelated tasks

​
Organizing Bundled Files

  1. Use descriptive names: generate_report.py is better than script.py
  2. Use subdirectories: Organize with scripts/, templates/, references/ as needed
  3. Keep it lean: Only include files the agent actually needs (max 20 files per skill)
  4. Document dependencies: Note any Python packages your scripts require

​
Skill Design

  1. Single responsibility: Each skill should handle one type of task well
  2. Self-contained: Include everything the agent needs — don’t assume external context
  3. Test the workflow: Try the full flow (load skill → follow instructions → run scripts) before deploying
  4. Version via SKILL.md updates: Update the instructions when your workflow changes

​
API Integration

Skills can be managed programmatically through the Aster Agents API. Create skills, upload bundled files, and assign them to agents via API calls. For detailed API documentation, see the API Reference section.
Agent Skills let you package complex, repeatable workflows into reusable components. Write the instructions once, bundle the scripts, and any agent with the skill assigned can execute the full workflow on demand.