Catalog

​

Overview

Catalog is a shared library that includes published agents and skills from the ELITEA community. Agents are pre-configured AI assistants designed for specific tasks, while Skills are reusable instruction sets that can be attached to agents and reused across workflows. Catalog vs. Agents The following table compares the Catalog and Agents menus.

---

​

Open ELITEA Catalog

Catalog is located in the ELITEA sidebar:

1. Open ELITEA and ensure you are logged in.
2. In the sidebar, locate Catalog.
3. Select Catalog to open it.

---

​

Catalog Tabs

Catalog includes two tabs:

• Agents — community-published agents that you can inspect and start in chat.
• Skills — community-published reusable skills that can be discovered from the same shared library surface.

---

​

Agents in Catalog

Published agents are displayed as cards in a responsive grid layout, grouped by their assigned categories. Each card provides key agent information:

• Agent display name.
• Profile image of the agent creator.
• Number of likes the agent has received.

From the agent card, you can:

• Select the card to open the agent full information.
• Like or unlike the agent.

---

​

View Agent Details

When you select any agent card, a dialog opens that displays all the information about the agent:

• Creator: Details about who created the agent.
• Name: Full name of the agent.
• Description: Detailed explanation of the agent purpose and capabilities.
• Show instructions: Select to open a read-only dialog displaying the agent full instructions and configuration details. You can read and copy the instructions but cannot modify them.
• Conversation starters: Pre-defined prompts to help users get started.
• Welcome message: The greeting users see when starting a conversation.
• Start chat: Primary action to begin using the agent.

---

​

Start a Conversation with an Agent

You can start a conversation with an agent in two ways:

1. Select Start chat to create a new conversation and display conversation starters.
2. Select a Conversation Starter to create a new conversation and pre-fill the starter text in the chat input field.

After you start a conversation:

1. You are automatically redirected to the Chat menu.
2. A new conversation is created for this agent.
3. The agent is added to the Participants list.
4. The agent is set as the active participant.
5. Pre-defined prompts appear to guide your interaction (or if you selected a starter, it is pre-filled in the input field).
6. You can immediately start sending messages.

Once the conversation is created, you can:

• Use conversation starters: Select any starter to send that prompt immediately.
• Enter a custom message: Enter your own message in the input box.
• Modify the model settings: Adjust the LLM model and model parameters.

---

​

Skills in Catalog

Published skills are available in Catalog through the Skills tab. Use the Skills tab to:

• Search for published skills using the Search for skills field.
• Browse reusable skills from the ELITEA community.
• Open skill details from the catalog surface.

Skills are catalog items intended for reuse in agent configurations rather than direct standalone chat execution.

​

View Skill Details

When you select a skill card, a details view opens from the Catalog surface. The skill details view can include:

• Creator: Details about who created the skill.
• Name: Full name of the skill.
• Description: Explanation of the skill purpose and intended usage.
• Instructions / Content: Read-only view of the skill content so you can review what it provides before using it.

Use this view to inspect whether the skill matches your use case before attaching it to an agent.

​

Attach a Skill to an Agent

Skills from Catalog are intended to be reused in agent configurations. To attach a published skill to an agent:

1. Open the skill in the Skills tab and review its details.
2. In the skill details view, select Add to Agent.
3. Select one or more of your agents from the list.
4. Choose one of the available actions:
   • Add & Test — attaches the skill to the selected agent and redirects you to the Chat menu with a conversation opened for that agent.
   • Add — attaches the skill to the selected agent without opening Chat.

After attaching the skill, the selected agent uses that skill according to its configured behavior and version.

---

​

Browse & Search Catalog Items

Catalog provides a Search field at the top of the page for both tabs. You can search by the item name and description. The search results update in real time as you enter text. Clear the search field to reset the search. Filter by Category Category filters are available for both Agents and Skills and are located in the right panel of Catalog. These filters help you browse catalog items by their assigned categories. The following table describes each category. To filter catalog items by category:

1. Select the category button. You can apply multiple filters simultaneously.
2. The active category is highlighted.
3. The visible cards update automatically based on the selected filters.

---

​

Modification Restrictions

Catalog items are read-only. This applies to both published agents and published skills.

• A published agent remains read-only, but certain conversation-level overrides are allowed for your current session when you start a chat with it.
• A published skill is a snapshot of the skill at the time it was published. You can review its details and attach it to one or more of your agents, but you cannot edit the published skill directly from Catalog.

What You Can Modify For published agents used in chat, you can modify:

• Variable values: Provide or modify values for variables defined in the agent.
• LLM model: Change which AI model the agent uses. Icons near the model name indicate its supported capabilities:

  Capability	What it means
  Image analysis	The model can analyze and interpret images alongside text input
  Reasoning	The model uses extended reasoning steps; exposes Reasoning Effort in Model settings instead of Creativity

• Model settings:

  Parameter	Shown when	Description
  Creativity	Standard models	A 5-level discrete slider (Low → Mid-Low → Medium → Mid-High → High) controlling response randomness. Lower values produce focused, deterministic outputs; higher values produce more diverse, creative responses.
  Reasoning Effort	Reasoning-capable models (replaces Creativity)	A 3-level slider: Low (fast, surface-level), Medium (balanced), High (deep step-by-step analysis, slower).
  Max completion tokens	Always	Limits the maximum length of AI responses. Toggle between Auto (model-managed) and Custom (enter a specific token count, default 4096).
  Steps limit	Always (in conversation context)	Maximum number of tool-call steps before the execution loop ends (default 25).

How to Modify Agent Conversation Overrides

1. With the agent active in a conversation, select the Settings icon at the bottom of the chat.
2. The Model settings dialog opens — adjust the parameters as needed.
3. Select Apply to save your changes, or Cancel to discard them.
4. Use Reset to defaults in the dialog to restore the published agent original conversation settings.
5. Changes apply only to this conversation — they do not affect the published agent.

What You Cannot Modify These published catalog properties are read-only to preserve the original design and functionality. For published agents:

• Agent name.
• Instructions (core behavior and task guidelines are locked).
• Welcome message.
• Conversation starters.
• Toolkits (toolkits are locked as part of the published agent).
• Variable definitions (you cannot add or remove variables, but you can modify their values).

For published skills:

• Skill name.
• Description.
• Instructions / content.
• Published version content shown in Catalog.

---

​

Agent Powers & Limitations

When using published agents from Catalog, keep the following considerations in mind.

---

​

Troubleshooting

---

​

Best Practices

---

​

Guides & References

---