> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/core-concepts/skills-and-tools.md).
# Skills & Tools
What an agent can actually do.
A reasoning model can produce text. An **agent** can act — send the email, write the record, query the ledger, read the document. Skills are what turn one into the other.
A skill is a single action the agent can take. The set of skills attached to an agent is its complete vocabulary of actions, and the planner chooses from exactly that set. Nothing else is available to it, whatever the instructions say.
{% hint style="info" %}
**The list is the planner's universe.** A skill that isn't attached cannot be used. A skill that is attached but whose description doesn't match the requests users actually send won't get picked. Auditing that list is the highest-value thing you can do when an agent isn't behaving as expected — see [Skills & Capabilities](/ai-workbench-qore/console/agent-builder/build/skills-and-capabilities.md).
{% endhint %}
## Where skills come from
Seven kinds of skill, all landing in the same list. [Adding a skill to the agent](/ai-workbench-qore/console/agent-builder/build/adding-a-skill-to-the-agent.md#understanding-skills) compares them side by side.
**Built-in.** Every agent has the same built-in skills, in two groups in its **Skills** panel. **General** covers reasoning, web search, knowledge search, code execution, files, and messages. **Document** covers extracting, classifying, summarizing, and generating documents. Enable or disable each one from the **Pre-attached Skills** tab of Add Skill. See [General skills](/ai-workbench-qore/platform-resources/skill-library/general-skills.md) and [Document skills](/ai-workbench-qore/platform-resources/skill-library/document-skills.md). An agent with a governed graph attached queries it with the **Knowledge Graph Search** skill; see [Knowledge & Context](/ai-workbench-qore/core-concepts/knowledge-and-context.md).
**The Skill Library.** Skills that you add and configure for your own systems and logic, such as **API Call**, **JavaScript Code**, **Python Code**, **MCP Server**, and **Web Crawler**. See the [Skill Library](/ai-workbench-qore/platform-resources/skill-library.md) reference.
**Connectors.** Connecting an integration or an MCP server registers its skills into the agent automatically. Two catalogs:
| Catalog | Holds | Reach for it when |
| -------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| [Apps & Services](/ai-workbench-qore/console/agent-builder/build/apps-and-services.md) | Pre-built connectors to recognized SaaS products — Stripe, Resend, Twilio | The action involves a product with a logo and a stable customer-facing API |
| [MCP Tools](/ai-workbench-qore/console/agent-builder/build/mcp-tools.md) | Model Context Protocol servers — market data, scraping, search, knowledge retrieval | The action involves a data API or a generic tool |
The catalogs overlap, so the same service can appear in both.
**Control Center → Govern →** [**Connectors**](/ai-workbench-qore/control-center/govern/connectors.md) lists what the account has made available, in three tabs: **Integrations**, **MCP Servers**, and **Platform Skills**. It is the outer limit every agent inherits: an agent can't use a connector the account hasn't made available, whatever its own configuration requests.
**Custom skills.** Your own procedures and know-how, written in a `SKILL.md` file and uploaded to the agent. See [Custom skills](/ai-workbench-qore/platform-resources/skill-library/custom-skills.md). To reach a service that isn't in either catalog, add an [API Call](/ai-workbench-qore/platform-resources/skill-library/api-call.md) skill instead.
**Flows.** A multi-step process you built in Flows, added to the agent as one skill. Use a flow when the steps are fixed and should always run in the same order. See [Flows](/ai-workbench-qore/console/flows.md).
**Other agents.** Another agent in the project, added as a sub-agent. Use one when a different agent is better suited to part of the job. See [Adding a skill to the agent](/ai-workbench-qore/console/agent-builder/build/adding-a-skill-to-the-agent.md#add-another-agent-as-a-skill).
## Skills versus protocols
A skill is *an action*. A protocol is *a way of reaching things*. MCP is a protocol: connecting one MCP server can register several skills at once. That's why MCP appears both here and in [Protocols](/ai-workbench-qore/core-concepts/protocols.md) — it's the mechanism by which a class of skills arrives.
## Turning skills off
Every attached skill is a choice the planner can make. A disabled skill is one the agent can't use.
Built-in skills can be disabled one at a time, without affecting the ones that remain. Open [Skills & Capabilities](/ai-workbench-qore/console/agent-builder/build/skills-and-capabilities.md) to see every skill on the agent. To require a person's approval before selected skills run, use Tool Execution Approval; see [Guardrails & Validation](/ai-workbench-qore/core-concepts/guardrails-and-validation.md).
## Where this is configured
* [Skills & Capabilities](/ai-workbench-qore/console/agent-builder/build/skills-and-capabilities.md) — the full list, and the planner's universe
* [Adding a skill to the agent](/ai-workbench-qore/console/agent-builder/build/adding-a-skill-to-the-agent.md) — the flow for attaching one
* [Apps & Services](/ai-workbench-qore/console/agent-builder/build/apps-and-services.md) — SaaS connectors, per agent
* [MCP Tools](/ai-workbench-qore/console/agent-builder/build/mcp-tools.md) — MCP servers, per agent
* [Skill Library](/ai-workbench-qore/platform-resources/skill-library.md) — the built-in skills, and the skills you configure
***
{% columns %}
{% column width="83.33333333333334%" %}
Maintained by Abhishek Paul
AI-assisted, human-approved
{% endcolumn %}
{% column width="16.666666666666664%" %}
{% endcolumn %}
{% endcolumns %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.uptiq.ai/ai-workbench-qore/core-concepts/skills-and-tools.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
