# Managed Deep Agents - Skills

## Executive summary

Skills allow managed deep agents to access specialized contexts and executable scripts dynamically, moving beyond static instructions. Skills are defined in a structured folder (`skills`) using `skill.md` files, which utilize 'progressive disclosure'—only basic information is given to the LLM initially. This system enables agents to perform complex tasks, such as asking follow-up questions or running Python scripts, and allows for centralized management of these skills via Context Hub without requiring code redeployment.

## Key takeaways

- Skills vs. Instructions: While instructions are always visible in the agent context, skills provide specialized, optional contexts that the agent can read or execute only when needed (progressive disclosure).
- Skill Definition Structure: Each skill resides in a dedicated folder under `skills/` and requires a `skill.md` file. This file must contain front matter fields: `name` (the skill name) and `description` (what is shown to the LLM).
- Executing Scripts: Skills can contain executable scripts (e.g., Python files like `hello.py`). The agent can identify, read, execute these scripts, and use their output as part of its response.

## Technical details

- Progressive Disclosure: Only the skill's name and description are automatically provided to the LLM initially. Detailed information is loaded only when the LLM chooses to read or utilize the skill further.
- Skill Implementation (Markdown): Skills are defined in `skill.md` files, requiring front matter fields for `name` and `description`. Example: Name='question asking', Description='Use this skill to ask follow-up questions when the user's initial question is vague.'
- Agent Interaction Flow: When an agent uses a skill, it first reads the relevant file (e.g., `skills/qa/skill.md`), which informs its behavior. If scripts are involved, the process includes listing files (`ls`) and executing commands (e.g., running Python).
- Context Hub Management: When deploying with MDA Dev, skills are pushed to Context Hub. This allows developers to modify skill content (e.g., changing text in `skill.md` or scripts) through the UI without redeploying the underlying code.

## Practical implications

- Skills provide a structured way to extend agent capabilities beyond simple system prompts.
- Using Context Hub allows for non-code updates (e.g., modifying skill descriptions or content) in deployed agents without requiring a full code redeployment cycle.
- The architecture supports both informational skills (Markdown reading) and functional skills (executable scripts).

## Topics

Agent Development, LLM Orchestration, Skill Engineering, Context Management, Python Scripting, LangChain, LangSmith, MDA Dev

Source: https://www.youtube.com/watch?v=Lhru0yMI2as