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

# Get your first result

> Install SelfTune, validate its local runtime, and inspect your first honest skill inventory.

The goal of this quickstart is a verified local setup and a trustworthy skill
inventory. SelfTune should tell you what it knows and identify where it does not
have enough evidence yet.

<Info>
  You need Node.js with `npx` or Bun, an installed AI agent, and at least one
  agent skill. SelfTune uses your existing agent environment for interactive
  reasoning; local setup does not require a separate model API key.
</Info>

## Recommended: let your agent do it

Copy the setup prompt from [Set up with your agent](/setup-with-your-agent).
Your agent will inspect the environment, choose the right installation path,
and stop when it needs permission.

## Manual setup

<Steps>
  <Step title="Install the agent skill">
    ```bash theme={null}
    npx skills add selftune-dev/selftune
    ```

    Restart or reload your agent if it does not discover newly installed skills
    during the current session.
  </Step>

  <Step title="Initialize SelfTune">
    Ask your agent:

    ```text theme={null}
    Initialize SelfTune for this environment. Keep all data local and tell me
    before installing hooks or changing background services.
    ```

    The agent should detect supported harnesses and explain the changes it
    intends to make.
  </Step>

  <Step title="Check the runtime">
    ```bash theme={null}
    npx selftune@latest doctor
    ```

    Resolve reported errors before continuing. Warnings about missing history
    or no observations can be valid on a new installation.
  </Step>

  <Step title="Import existing local evidence">
    ```bash theme={null}
    npx selftune@latest sync
    ```

    Sync reads supported local agent histories and normalizes skill evidence
    into SelfTune's local data store. It does not make a remote upload part of
    this quickstart.
  </Step>

  <Step title="Inspect the inventory">
    ```bash theme={null}
    npx selftune@latest status
    ```

    A useful result distinguishes among observed health, a skill that needs
    attention, and a skill with insufficient evidence.
  </Step>
</Steps>

## Verify the result

You are done when all of these are true:

* `doctor` reports no blocking runtime or permission error;
* SelfTune finds the skills you expect it to find;
* `status` returns a health or no-data state for each discovered skill; and
* no remote upload, publication, credential, or background-service change
  happened without your approval.

<Check>
  A no-data result is valid on a fresh installation. Use the skill naturally,
  then run `sync` and `status` again after the agent session ends.
</Check>

## Open the local dashboard

```bash theme={null}
npx selftune@latest dashboard
```

The dashboard uses the same local data as the CLI. It gives you a visual skill
inventory, health details, and links to the next appropriate action.

## If setup does not work

Run `doctor` again and keep its exact output. Then follow
[Troubleshooting](/guides/troubleshooting) for runtime, discovery, permissions,
and no-data problems.

Goal: produce a verified local SelfTune installation and an honest skill
inventory.

Allowed changes: install the SelfTune skill and npm package in the user's
existing agent environment. Explain and request approval before installing
hooks, importing historical sessions, or enabling a background service.

Do not upload data, log into Cloud, publish a skill, change credentials, or
delete data as part of this quickstart.

Verification: run `npx selftune@latest doctor`, then `sync` with approval, then
`status`. Report discovered harnesses, discovered skills, blocking errors, and
which skills have evidence versus an honest no-data state. Do not treat no data
as success or failure evidence.