Skills

Skills are reusable functions that extend the capabilities of agents in Studio AI. They enable the execution of specific operations—such as calculations, database integrations, or business rules—that the model alone cannot perform efficiently, especially in tasks like math or structured actions.

A Skill is made up of Python code and can be used in automated flows to provide greater accuracy and control over the user experience.

---

Types of Skills in Skyone Studio

In Skyone Studio, Skills represent capability blocks that define how the AI agent will interact with users and process information. They can be divided into two main types: Embedded (Native) and Custom.

1. Embedded (Native) Skills

These are pre-configured models provided by Skyone Studio itself. They come ready to use and cannot be edited or deleted by users. Currently, Skyone Studio offers two embedded models:

• RAG Skill: Uses the Retrieval-Augmented Generation (RAG) technique, allowing the agent to fetch external information in real time to enhance the responses provided to users.

• SQL Skill: Enables the agent to interact directly with relational databases via SQL, answering questions and generating results based on structured queries.

These models are ideal for common use cases, ensuring robustness and best practices are built in. Learn more:

RAG (Retrieval-Augmented Generation)

RAG is an advanced artificial intelligence technique that combines information retrieval with text generation. Instead of relying solely on the knowledge acquired during the model’s training phase, RAG enables the AI to consult external sources in real time—such as vector databases or documents—to enrich and contextualize its responses.

Core Components and Competencies in RAG

• Understanding the RAG Concept: Knowing how AI models can retrieve external information in real time to supplement their generated responses.

• Semantic Search: Applying embeddings and vector representations to identify the most relevant documents for a given query.

• Vector Indexing: Using specialized tools such as FAISS, Weaviate, Pinecone, Milvus, among others, to efficiently store and search vectors.

• Integration with LLMs: Connecting retrieval mechanisms to language models (LLMs) like GPT, LLaMA, and others, ensuring the final output combines retrieved data with fluent text generation.

• RAG Pipeline Construction: Developing the complete workflow—query, retrieval, and response—ensuring that each step is integrated and functions efficiently.

• Document Embedding: Converting texts into vectors using models like all-MiniLM, nomic-embed, and others, to populate the vector database.

• RAG Frameworks: Utilizing frameworks such as LangChain, LlamaIndex, Haystack, and others to build, organize, and orchestrate RAG pipelines.

• RAG Evaluation: Measuring system effectiveness in terms of accuracy, response relevance, and latency (response time), ensuring quality and performance.

• Governance and Security: Ensuring RAG workflows comply with standards for confidentiality, data accuracy, and access control.

SQL (Structured Query Language)

When customizing an embedded Skill, the system creates an independent copy. This new version can be freely edited.

2. Custom Skills

These are created directly by users. There are two main ways to create them:

• From scratch: The user builds the entire logic and custom configuration to meet specific business needs.

• By duplicating an embedded Skill: The user copies a native model to use as a starting point, then makes adjustments and customizations as needed.

Custom Skills offer full flexibility, allowing the agent’s behavior to be tailored for unique and more complex use cases.

---

Create a New Skill

To create a custom Skill:

1. Go to the side menu and click on “Skills.”

2. Click on "New Skill".

1. On the editing screen, fill in the following fields:

• Module name: this is the primary identifier for the Skill.

• Skill access level: configure the skill's privacy by choosing between the following options:

  

  • Public: anyone can view and edit the skill settings.

  • Private: only selected users will be able to view details and edit the current skill.

    • Configure users: when the Private option is selected, this option becomes active. Choose the users who will have access to the skill and then click "Finish".

Unauthorized users can use the skill on Agents, but they cannot view technical details or edit it.

• Functions: write one or more functions in Python. Each function must receive parameters and return values clearly.

4.After filling in all fields and validating the code, click "Save module".

---

Import a Skill

To create a custom Skill using the Import option:

1. Access the side menu and click “Skills”.

2. Click "Import".

1. Choose the Python file (.py).

2. Make the desired edits and tests.

3. Click "Save module" to save the changes.

---

Edit a Skill

To edit a custom Skill:

1. Access the side menu and click “Skills”.

2. Select an existing Skill and click "Edit".

1. Make the desired edits and tests.

2. Click "Update module" to save the changes.

---

Test a Skill

To test a custom Skill:

1. Access the side menu and click “Skills”.

2. Hover over an existing Skill and click "Test".

1. Select the method.

2. In some cases, add a query.

3. Click "Test".

---

Export a Skill

To export a custom Skill:

1. Access the side menu and click “Skills”.

2. Hover over an existing Skill and click "More options".

3. Select the "Export" option.

---

Duplicar a Skill

To duplicate a custom Skill:

1. Access the side menu and click “Skills”.

2. Hover over an existing Skill and click "More options".

3. Select the "Duplicate" option.

---

Delete a Skill

To delete a custom Skill:

1. Access the side menu and click “Skills”.

2. Click on an existing Skill.

3. Click "Delete".

4. As a security measure, type the agent's name exactly as requested in the confirmation field.

5. Click "Delete" to finalize the process.

This deletion cannot be undone.