> For the complete documentation index, see [llms.txt](https://docs.karini.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.karini.ai/prompt-management/skills/custom-skills.md).

# Custom skills

Custom skills are organization-specific capabilities that extend an agent platform beyond its built-in native skills by allowing teams to create, customize, version, and manage reusable domain-specific functionality. Custom skills can include specialized logic, scripts, documentation, and supporting assets that agents discover and use as needed. They help organizations capture institutional knowledge, standardize complex or compliance-sensitive workflows, and provide agents with a reusable self-service capability layer, reducing the need to repeatedly supply detailed procedural instructions in individual conversations.

#### Key Characteristics

* **Organization-Scoped**: Custom skills belong to a specific organization and are isolated from other tenants
* **Version-Controlled**: Skills support draft and versioned releases for staged deployment and rollback
* **Filesystem-Backed**: Skills are stored on shared EFS (Elastic File System) for durability and multi-instance access
* **Modular Structure**: Standardized directory layout with SKILL.md, scripts/, assets/, references/, and examples/
* **Runtime Inheritance**: SubAgents automatically inherit parent agent skills plus their own extended skill sets

#### When to Use Custom Skills

Use Custom Skills to encode information or instructions that are specific to your organization, such as:

* Proprietary knowledge
* Internal procedures and workflows
* Regulatory or compliance guidelines
* Domain-specific terminology
* Organization-specific standards or instructions
* Knowledge that is not covered by available Native Skills

#### Add Custom Skills in Prompt Playground

Follow the steps below to add the skills in the Prompt Playground.

1. Navigate to the **Prompt Playground**.
2. Select the prompt (Agent/Deep agent  to which you want to add a Skill.
3. Open the **Skills** tab.
4. In the Skills panel, select **Add new → Custom**.
5. The right panel opens the **Custom Skill** form.

   1. Provide the following required information:
      1. **Name** *(Required)* : Enter a unique and descriptive name for the Skill.
      2. **Description** *(Required)* : Provide a brief summary explaining what the Skill does and when it should be used.
      3. **Template** *(Required)* : Add the Skill content in Markdown format, either manually or by uploading a `.md` file.
   2. Choose an Input Method:  You can create the Skill using one of the following methods:
   3. **Upload File:** Upload a Markdown (`.md`) file from your local machine.The contents of the uploaded file are used as the Skill template.

   <figure><img src="https://415930246-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7ZrVuiAUMyuYVvrK5KaB%2Fuploads%2F3bJBslPXa6Ceg2gqg1Ir%2Fimage.png?alt=media&amp;token=d64cb9f9-9ffb-4ff5-a661-60a5e0711da7" alt=""><figcaption></figcaption></figure>

&#x20;        d. **Manual Input :**&#x45;nter the Skill content directly in the editor.

<figure><img src="https://415930246-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7ZrVuiAUMyuYVvrK5KaB%2Fuploads%2FqwscPJUvASesFoSfGuQ9%2Fimage.png?alt=media&amp;token=b87362fd-7635-447d-986b-3bd06cd1c453" alt=""><figcaption></figcaption></figure>

Lastly Select **Save** and the Custom Skill is created and automatically added to the selected prompt, where it can be used during prompt execution.

#### Execution of skills in Deep Agent Prompt

Skills are **loaded and executed on demand** instead of running continuously in the background. This keeps the agent’s workflow efficient and controlled.

1. **Skill instructions are loaded when required.**\
   The agent reads the relevant `SKILL.md` file only when a particular skill is needed for the task.
2. **Skills run inside the sandbox.**\
   The required operations are performed in a controlled sandbox environment where files and tasks can be safely processed.
3. **The agent waits for the result.**\
   After executing a skill, the agent waits for the output and uses the result before moving to the next step.
4. **Skills are not background tasks.**\
   Skills do not continue running independently. They are executed as part of the active workflow and complete before the agent proceeds.

Overall, skills work as **on-demand capabilities** that are loaded, executed, and completed only when necessary.

The following points describe the skill inheritance behavior for Sub Agents.

* **Sub Agents automatically inherit all skills configured on their parent Deep Agent**, ensuring that parent-level capabilities are consistently available to each Sub Agent.
* Skills configured directly on a Sub Agent are additive, meaning the effective skill set is the union of the parent Deep Agent’s skills and the Sub Agent’s own skills.

#### Execution of skills in Agent Prompt

Agent prompts are designed for **simple, single-step, and stateless execution**. Skills provide the instructions the agent should follow, but skills themselves cannot execute code. If the skill includes executable logic, the Agent node must have a **Code Interpreter** configured.

* **Code Interpreter is required** for Python code, shell commands, automation scripts, data processing, computations, or any other executable logic.
* **Without Code Interpreter**, the agent can only read, interpret, and explain the code or instructions defined in the skill.
* **With Code Interpreter**, the agent can execute the required code, process the output, and return the computed result.
* Skills are loaded **per request**, with no retained skill context across requests.
* Agent execution is **single-turn and stateless**, unless conversation context is explicitly provided at the recipe level.
* This setup is best suited for **quick lookup, simple transformations, calculations, and straightforward skill-based tasks**.