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

# Guided onboarding

> Run /onboard and your agent takes you from nothing to a trustworthy first evaluation on Calibrate

The `/onboard` skill guides you through setting up your first Calibrate
evaluation step by step. It's an **orchestrator** — each phase delegates to a
feature skill and produces a real Calibrate object, so you finish with a working
evaluation, not a tutorial.

## Quick start

<Steps>
  <Step title="Install the skills">
    ```bash theme={null}
    npx skills add dalmia/calibrate-skills
    ```

    See [Agent skills](/docs/agents/skills) for the full pack.
  </Step>

  <Step title="Open your AI coding agent">
    Claude Code, Cursor, Codex, Windsurf, or any Agent Skills–compatible agent.
  </Step>

  <Step title="Run the onboarding skill">
    ```
    /onboard
    ```

    The skill handles everything from there — including installing the CLI and
    authenticating if you haven't already.
  </Step>
</Steps>

The onboarding is **resumable and adaptive**: progress is saved to
`.calibrate/onboard.md`, so a later session picks up at the first incomplete
phase, and the skill compresses or skips phases you've already answered.

## What it creates

By the end you have a real, inspectable evaluation on Calibrate:

| Resource         | What it is                                                                    |
| ---------------- | ----------------------------------------------------------------------------- |
| Agent            | Your system under test, connected and verified against its endpoint           |
| Tests            | Test cases turning your goal into falsifiable `tool_call` / `response` checks |
| Evaluator        | An LLM or audio judge, if any case scores response quality                    |
| Run              | The first evaluation run, with pass/fail and judge reasoning                  |
| Calibrated judge | The judge tuned against human labels, so you can trust the scores             |
| Benchmark        | Optional model comparison across the linked tests                             |

## The workflow

`/onboard` walks these phases in order for a first-time user, and lets an expert
compress or skip any they've already answered.

<Steps>
  <Step title="Setup">
    Confirms the CLI is installed and authenticated (`calibrate whoami`, else
    `calibrate login`) and scaffolds the resumable state file.
  </Step>

  <Step title="Connect the agent">
    Asks what the agent does, who uses it, and where it fails today, then
    delegates to `/connect-agent` to register and verify the connection.
  </Step>

  <Step title="Build the tests">
    Turns your goal into a falsifiable hypothesis, then delegates to
    `/build-test-suite` (or `/import-dataset` if you already have a dataset) to
    author and upload test cases.
  </Step>

  <Step title="Design the evaluators">
    Only if a case judges response quality — delegates to `/design-evaluator` to
    create a judge. Skipped entirely when every case is a deterministic
    `tool_call`.
  </Step>

  <Step title="Run">
    Delegates to `/run-tests` to link the tests, run them, poll for results, and
    present **failures first**.
  </Step>

  <Step title="Calibrate the judge">
    Offered, not forced — when you care whether the scores are trustworthy,
    `/calibrate-evaluator` measures human ↔ judge agreement and tunes the judge
    until it matches humans. This is the step that makes it *Calibrate*, not just
    a test runner.
  </Step>

  <Step title="Scale and wire into CI">
    Delegates to `/benchmark-models` to compare models, and — when you mention
    PRs, releases, or shipping — proposes wiring
    `calibrate agent-tests run` into CI in agent mode.
  </Step>
</Steps>

## Evaluation is a loop

After the first run, `/onboard` expects one of: expand the test set when a defect
surfaces, tune the hypothesis when the bar is too loose or strict, add a model,
or tune the judge when agreement is too low. Each pass appends to the state file
so prior baselines stay inspectable — stop when you've shipped or wired it into
CI.

## Next steps

<CardGroup cols={2}>
  <Card title="Browse the skills" icon="graduation-cap" href="/docs/agents/skills">
    See every skill `/onboard` orchestrates, and invoke them on their own.
  </Card>

  <Card title="Connect the MCP server" icon="plug" href="/docs/mcp/overview">
    Give your agent native Calibrate tools alongside the skills.
  </Card>
</CardGroup>