> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ewake.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Skills

> Write team playbooks that ewake applies automatically when it encounters a matching situation.

<Info>
  **What you'll get:** Skills let your team encode institutional knowledge, "when you see X, investigate like this", and have ewake apply it automatically, without you repeating the instructions every time.
</Info>

***

## What it does

Skills are playbooks written by your team that guide ewake's behaviour in specific situations. When an investigation starts, ewake scans your active skills and automatically injects the relevant ones into its context.

The result: ewake responds the way your team would, based on the guidance you've already written, more consistent answers, less repetition.

***

## Anatomy of a skill

Each skill has three fields:

| Field           | Role                                                                                                                                                                          |
| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Title**       | A short name that identifies what the skill covers                                                                                                                            |
| **Description** | Used by ewake to decide whether this skill applies to the current mission.                                                                                                    |
| **Body**        | The actual guidance, injected into the agent's context verbatim when the skill is selected. Write it as you would a runbook: what to check, what to look for, how to respond. |

## Statuses

A skill moves through the following statuses:

| Status       | Meaning                                                           |
| ------------ | ----------------------------------------------------------------- |
| **Draft**    | Being written or waiting for review. Not used by ewake.           |
| **Active**   | Ewake retrieves and injects this skill when it matches a mission. |
| **Disabled** | Temporarily excluded without being deleted.                       |
| **Archived** | Retired. No longer used.                                          |

<Warning>
  Only **active** skills are used by ewake. A skill in draft, disabled, or archived status is never injected, even if it matches the mission.
</Warning>

***

## Versioning

Every time you save changes to a skill, a new version is created. Ewake only uses the version that has been **selected**.

You can view the full version history and **restore** any previous version if needed. Restoring a version promotes it to current without deleting the history.

***

## AI-generated skills

Ewake can suggest new skills or propose updates to existing ones based on patterns it observes. These arrive with status **draft** and include a per-field explanation of what the AI changed and why, so you can review the suggestion before activating it.

<Note>
  AI-generated skills are never activated without a human review.
</Note>

***

## How to create a skill

<Steps>
  <Step title="Go to Skills">
    In your ewake dashboard, navigate to the **Skills** section.
  </Step>

  <Step title="Create a new skill">
    Click **New skill**.
  </Step>

  <Step title="Write the title">
    Choose a title that clearly describes the situation this skill covers.

    **Examples:**

    * `Database connection pool exhaustion`
    * `High 5xx rate on payments-api`
    * `Post-deploy latency spike triage`
  </Step>

  <Step title="Write the description">
    Describe when this skill applies. This is what ewake uses to match the skill to a mission.

    You can click **Suggest** to have ewake generate a description from the title and body.

    **Example:**

    ```
    Apply when investigating a sudden increase in latency or errors on a service that follows a recent deployment.
    ```
  </Step>

  <Step title="Write the body">
    Write the guidance ewake should follow. Treat it as a runbook: concrete steps, specific things to check, how to interpret results.

    **Example:**

    ```
    1. Check the deployment timeline, identify what changed in the 30 minutes before the alert.
    2. Compare error rates and p99 latency before and after the deploy using Datadog.
    3. Look for database query regressions or connection pool exhaustion in the logs.
    4. If the deploy is the likely cause, identify the commit diff and surface it as evidence.
    5. Suggest a rollback only if error rate exceeds 10% and no quick fix is identifiable.
    ```
  </Step>

  <Step title="Save and activate" />
</Steps>

***

## Tips for writing effective skills

**Be specific.** A skill scoped to "database connection pool exhaustion on checkout-api" is more useful than one titled "database issues". Specific skills get retrieved more precisely and contain more actionable guidance.

**Write the body as instructions to the agent.** Use numbered steps, concrete thresholds, and named services. Avoid vague directives like "investigate carefully".

**Use the description as a trigger condition.** The description should answer: *in what situation should ewake apply this?* Think of it as the `if` clause.

**Start in draft, activate when ready.** There is no cost to keeping a skill in draft while you refine it. Activate only when you are confident the guidance is correct.

***

Need help? Contact [support@ewake.ai](/support).