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

# Prompt Engineering Playbook: A Trained Agent for One Ad Account

> The Prompt Engineering Playbook is a one-time $39 add-on that generates a custom agent skill, an account dossier, a prompt book, and agent instructions from your own ad account — then hands you the files to install in Claude, ChatGPT, Claude Code, Cowork, Cursor, or Codex.

The **Prompt Engineering Playbook** is a set of agent files generated from **one of your ad
accounts** — its campaign structure, spend history, and current state — and handed to you as a
download you install in your AI client.

It answers the question people ask after connecting Adspirer: *"the tools work, but how do I
actually get good at this?"* Instead of you learning prompt engineering, the playbook writes the
prompts, the instructions, and the account briefing for you.

<Info>
  **The single most important thing on this page: this is a one-time purchase, not a subscription.**
  You pay **\$39 once** for a given ad account and nothing recurs — no monthly charge, no renewal, no
  second bill. It is separate from your Adspirer plan, which continues to work exactly as before. The
  files are yours to keep, and rebuilding them later is free and unlimited.
</Info>

## What it is — and what it is not

Adspirer ships **13 free [Agent Skills](/docs/agent-skills/skills)** that teach any assistant how to run
ads in general: how to structure a Google Search campaign, what Meta needs before a launch, the
safety rules. Every plan gets those, at no cost.

The Prompt Engineering Playbook is the layer above that. It is not general advertising knowledge —
it is **your account**, written down.

|                                   | Free Agent Skills      | Prompt Engineering Playbook          |
| --------------------------------- | ---------------------- | ------------------------------------ |
| **Scope**                         | Advertising in general | **One specific ad account**          |
| **Knows your campaigns**          | No                     | **Yes** — read from the live account |
| **Knows your spend and currency** | No                     | **Yes**                              |
| **Cost**                          | Free on every plan     | **\$39 once, per ad account**        |
| **Who writes it**                 | Adspirer, for everyone | Generated for you, from your data    |

You want both. The free skills are the grammar; the playbook is the briefing.

## What you get

The download is a `.zip` laid out to the open [Agent Skills](https://agentskills.io) format, so the
same folder works across clients:

```
<platform>-expert-<your-account>/
├── SKILL.md                             # the operating doctrine, pinned to your account
├── references/
│   ├── account-profile.md               # the dossier — your account's state and priorities
│   └── working-with-adspirer.md         # how the agent should call Adspirer's tools
├── PROMPTBOOK.md                        # the prompt book, organized by level and workflow
├── AGENT_INSTRUCTIONS.md                # paste-ready instructions for Projects
└── AGENTS.md                            # same text, for clients that read agents.md
```

| File                                      | What it does                                                                                                                        | Where it goes                        |
| ----------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------ |
| **`SKILL.md`**                            | The agent's operating doctrine for this account. Loads automatically when you ask about this account — you never invoke it by name. | Uploaded or dropped in as a skill    |
| **`references/account-profile.md`**       | A written dossier of the account: what state it's in, what to prioritize, what cadence to work on.                                  | Read by the agent on demand          |
| **`references/working-with-adspirer.md`** | The tool-calling contract and guardrails: discovery loop, read-before-write, pause-don't-delete.                                    | Read by the agent on demand          |
| **`PROMPTBOOK.md`**                       | The starting prompts — organized by level and workflow, written against *your* campaigns.                                           | You read and copy these              |
| **`AGENT_INSTRUCTIONS.md`**               | The constitution, ready to paste into a project's custom-instructions field.                                                        | Claude / ChatGPT Projects            |
| **`AGENTS.md`**                           | Identical text in the [agents.md](https://agents.md/) standard, read automatically by folder-based clients.                         | Claude Code, Cursor, Codex, Windsurf |

<Note>
  `AGENT_INSTRUCTIONS.md` and `AGENTS.md` are the same content in two places on purpose. Chat clients
  have an instructions *field* you paste into; folder-based clients read an `AGENTS.md` file from the
  directory automatically. You use whichever one your client understands.
</Note>

## How it's built

When you buy, Adspirer runs a five-stage build against the live account. It usually finishes in a
few minutes, and the page shows each stage as it completes:

<Steps>
  <Step title="Reading account structure">
    Pulls the campaigns, ad groups, budgets, and settings that exist right now.
  </Step>

  <Step title="Classifying the account's state">
    Works out what kind of account this is — scaling, stalled, newly built, seasonal.
  </Step>

  <Step title="Writing the account dossier">
    Writes `account-profile.md`: the state read, the priorities, the working cadence.
  </Step>

  <Step title="Writing your prompt book">
    Writes `PROMPTBOOK.md` against your actual campaigns and currency.
  </Step>

  <Step title="Assembling the skill package">
    Builds the folder, validates it against the Agent Skills spec, and packages the `.zip`.
  </Step>
</Steps>

If a build fails, the kit page shows it and offers a retry. A failed build costs you nothing extra.

## Price

|                                 | Price    | Billing                       | Covers             |
| ------------------------------- | -------- | ----------------------------- | ------------------ |
| **Prompt Engineering Playbook** | **\$39** | **One time — nothing recurs** | **One ad account** |

* Priced **per ad account**, because it is generated from that account's data. Two accounts means
  two playbooks.
* **Select every eligible account and 20% comes off the whole cart.** Tick them all in Expert Space
  — the cart bar has a **Select all** shortcut — and the bundle discount applies automatically at
  checkout. It needs **at least two** accounts, and it has to be *all* of the ones you can still
  buy; a partial selection pays full price per kit. The cart always shows the live discount before
  you pay.
* Buying several is a **single checkout and a single charge**, not one payment per account.
* **Annual plans include one playbook free.** If you're on an annual plan, claim it from Expert
  Space — there's no checkout step and no charge.
* The add-on also appears as an optional **"Add to your order"** on plan checkouts. Adding it there
  charges the \$39 immediately, on the same invoice as your plan — which is why the line item reads
  **"One-time Agent Setup — 1 Ad Account"**.

<Warning>
  \*\*Seeing $39 next to your plan charge does not mean your plan went up.** If you took the add-on
    during checkout, the $39 sits on the same invoice as your subscription, as a separate one-time line.
  Your recurring plan price is unchanged, and the \$39 will not appear on next month's invoice. Your
  [billing page](https://adspirer.ai/) shows the recurring amount on its own.
</Warning>

Because each playbook is generated on demand from your account, it's **non-refundable once the
build has completed and the files are available to download**. If a build failed, or you were
charged for an account you can't access, [contact support](/docs/knowledge-base/support) — that's a
different situation and we'll sort it out.

## How to get it

<Steps>
  <Step title="Open Expert Space">
    Go to [adspirer.ai/expert-space](https://adspirer.ai/expert-space). You'll see one card per
    connected ad account, grouped by platform.
  </Step>

  <Step title="Pick the account">
    Cards show what the playbook will be built from — campaign count, months of history, currency.
    Accounts that aren't active show **Inactive**; activate them in
    [Connections](https://adspirer.ai/connections) first.
  </Step>

  <Step title="Preview, then buy">
    **Preview Expert** shows sample prompts before you pay. Buy one account, or tick several and
    check out together.
  </Step>

  <Step title="Wait for the build">
    A few minutes. You can close the tab — the kit keeps building.
  </Step>

  <Step title="Download the .zip">
    From the kit page: **Download**. You can also copy `AGENT_INSTRUCTIONS.md` straight to your
    clipboard and read the prompt book in the browser.
  </Step>
</Steps>

<Tip>
  Lost the link? Everything you've bought is always at
  [adspirer.ai/expert-space](https://adspirer.ai/expert-space) — owned accounts show an **Open Kit**
  button. The purchase email also carries a direct link, but you never need it.
</Tip>

## Install it in your AI client

There are three install shapes. Which one you use depends on the client, not on the playbook.

| Shape      | What you do                                                         | Clients                                                         |
| ---------- | ------------------------------------------------------------------- | --------------------------------------------------------------- |
| **Upload** | Upload the skill folder into the client's Skills UI                 | Claude, Claude Cowork, ChatGPT *(Business/Enterprise/Edu only)* |
| **Paste**  | Paste `AGENT_INSTRUCTIONS.md` into the project's instructions field | ChatGPT *(Free, Plus, Pro)*                                     |
| **Folder** | Drop the unzipped folder into your working directory                | Claude Code, Cursor, Codex, Windsurf, OpenClaw, Antigravity     |

<Note>
  The playbook assumes Adspirer is already connected in that client. It teaches the agent how to work
  *your account*, not how to authenticate — connect first via [ChatGPT](/docs/ai-clients/chatgpt),
  [Claude](/docs/ai-clients/claude), [Cowork](/docs/ai-clients/claude-cowork),
  [Claude Code](/docs/ai-clients/claude-code), or [Codex](/docs/ai-clients/codex).
</Note>

### Claude (web and desktop)

<Steps>
  <Step title="Unzip the download">
    You'll get a folder named for your account, e.g. `google-ads-expert-acme-retail`.
  </Step>

  <Step title="Open Customize → Skills">
    Go to [Customize → Skills](https://claude.ai/customize/connectors) in Claude and open the
    **Skills** tab.
  </Step>

  <Step title="Upload the skill">
    Click **Upload skill** and provide the folder. Claude reads `SKILL.md` and the `references/`
    files together.
  </Step>

  <Step title="Add the instructions to a Project (optional but recommended)">
    Create a Project for this account and paste `AGENT_INSTRUCTIONS.md` into its instructions field.
    The skill carries the expertise; the project instructions keep every chat scoped to this one
    account.
  </Step>
</Steps>

Ask a normal question — *"how did we do last week?"* — and the skill loads on its own. You do not
name it. See the [Claude setup guide](/docs/ai-clients/claude) for connector details.

### Claude Cowork

Cowork supports skills the same way, from the **Customize** panel.

<Steps>
  <Step title="Open Customize">
    Click **Customize** in the left sidebar. You'll see **Skills**, **Connectors**, and
    **Browse Plugins**.
  </Step>

  <Step title="Add the playbook under Skills">
    Add the unzipped folder as a skill. It sits alongside the two skills the Adspirer plugin
    installs — the free ones cover advertising in general, the playbook covers this account.
  </Step>

  <Step title="Use a brand folder">
    Open the brand folder for this account and drop `AGENTS.md` in it. Cowork picks it up as
    standing context for everything you do in that folder.
  </Step>
</Steps>

See the [Cowork setup guide](/docs/ai-clients/claude-cowork) for the plugin install.

### ChatGPT

Which path you take depends on your **ChatGPT plan**, because ChatGPT's Skills feature is not on
every tier.

<Warning>
  **ChatGPT Skills are available on Business, Enterprise, Healthcare, and Edu — not on Free, Plus, or
  Pro.** If you're on Plus or Pro (the tiers the [Adspirer ChatGPT app](/docs/ai-clients/chatgpt) requires),
  use the **Project instructions** path below. It gives you the same behavior without the Skills
  feature. On Enterprise and Edu, skills may also be switched off until a workspace admin enables them.
</Warning>

**Plus and Pro — paste into Project instructions**

<Steps>
  <Step title="Create a Project for this ad account">
    One project per ad account keeps the agent from mixing them up.
  </Step>

  <Step title="Paste the agent instructions">
    Copy `AGENT_INSTRUCTIONS.md` — the kit page has a one-click **Copy** button — and paste it into
    the project's custom-instructions field.
  </Step>

  <Step title="Upload the rest as project files">
    Add `PROMPTBOOK.md` and `references/account-profile.md` to the project's files so ChatGPT can
    read the dossier and the prompts on demand.
  </Step>
</Steps>

**Business, Enterprise, Healthcare, Edu — upload it as a skill**

<Steps>
  <Step title="Open Skills">
    Go to **Skills** in ChatGPT and choose **Create → Upload from your computer**.
  </Step>

  <Step title="Upload the playbook folder">
    ChatGPT scans the upload before it becomes available — most are ready straight after the scan.
    The playbook follows the open Agent Skills standard, so it's the same folder you'd install
    anywhere else.
  </Step>

  <Step title="Still worth making a Project">
    Paste `AGENT_INSTRUCTIONS.md` into a project for this account too. The skill carries the
    expertise; the project keeps every chat scoped to one ad account.
  </Step>
</Steps>

See [Skills in ChatGPT](https://help.openai.com/en/articles/20001066-skills-in-chatgpt),
[ChatGPT custom instructions](https://help.openai.com/en/articles/8096356-chatgpt-custom-instructions),
and the [ChatGPT setup guide](/docs/ai-clients/chatgpt).

### Claude Code, Cursor, Codex, Windsurf, OpenClaw, Antigravity

Folder-based clients read the files off disk. Unzip the playbook into the directory you work in:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
unzip google-ads-expert-acme-retail.zip
# the folder contains SKILL.md, references/, PROMPTBOOK.md, AGENT_INSTRUCTIONS.md, AGENTS.md
```

* **`AGENTS.md`** is read automatically by clients that follow the [agents.md](https://agents.md/)
  standard — Claude Code, Cursor, Codex, Windsurf, Antigravity. Keep it at the root of the folder
  you work in.
* **`SKILL.md`** is picked up as a skill by clients with a skills directory. See
  [Claude Code skills](https://code.claude.com/docs/en/skills),
  [Cursor skills](https://cursor.com/docs/context/skills),
  [Codex skills](https://learn.chatgpt.com/docs/customization/overview), and
  [OpenClaw skills](https://docs.openclaw.ai/tools/skills).

**Claude Code** has two skill locations — pick by whether this account is one project or all of them:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
# personal — available in every project you open
mkdir -p ~/.claude/skills
cp -r google-ads-expert-acme-retail ~/.claude/skills/

# or project-scoped — just this repo/folder
mkdir -p .claude/skills
cp -r google-ads-expert-acme-retail .claude/skills/
```

Claude Code watches these directories, so it picks the skill up **without a restart**. Claude loads
it when a task matches, or you can invoke it directly as `/google-ads-expert-acme-retail`. Drop
`AGENTS.md` at the root of the folder you work in as well — that's the always-on layer.

**Codex uses both, in two different places.** `AGENTS.md` carries project rules and lives at the
repo root; skills are reusable workflows and live in a skills directory. Put the playbook in both:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
# repo-scoped — checked in, shared with your team
mkdir -p .agents/skills
cp -r google-ads-expert-acme-retail .agents/skills/
cp google-ads-expert-acme-retail/AGENTS.md ./AGENTS.md

# or global — available in every repo, just for you
mkdir -p ~/.agents/skills
cp -r google-ads-expert-acme-retail ~/.agents/skills/
```

Run `/skills` in Codex to confirm it loaded. Codex discovers skills by their `SKILL.md`
frontmatter and loads the full file only when a task matches, so you don't invoke it by name —
though you can with `$<skill-name>` if you want to force it.

<Tip>
  The same folder works in Claude Code and OpenClaw unchanged — one Agent Skills bundle, several
  clients. Only the directory it goes in differs.
</Tip>

Managing several accounts from one machine? Keep one folder per account and open the one you're
working on — see [set up your project](/docs/guides/set-up-your-project) for the project-per-account and
project-per-channel patterns.

## Set up the project, then run the prompts

Installing the files is half of it. The playbook pays off when it lives inside a **project** — a
persistent workspace scoped to that one ad account — so every chat starts already knowing the
account. The pattern is the same in all three chat clients: **create a project → paste the agent
instructions → add the dossier as knowledge → work through the prompt book.**

<Tabs>
  <Tab title="Claude">
    <Steps>
      <Step title="Create the project">
        Go to [claude.ai/projects](https://claude.ai/projects) and click **+ New Project**. Name it
        for the ad account — *"Acme Retail — Google Ads"* — so you never wonder which account a
        chat is about.

        Projects are available on every plan, including free (free is capped at 5 projects).
      </Step>

      <Step title="Paste the agent instructions">
        On the right-hand side of the project, click **Set project instructions**. Paste the whole
        of `AGENT_INSTRUCTIONS.md` — the kit page has a one-click **Copy** button — then click
        **Save instructions**.

        This is the constitution: it pins the account ID, the currency, read-before-write, and
        create-paused. Every chat in the project inherits it.
      </Step>

      <Step title="Add the dossier as project knowledge">
        Still on the right, click **+** and upload `references/account-profile.md` and
        `PROMPTBOOK.md`. Claude uses them as context in every chat in the project.
      </Step>

      <Step title="Upload the skill (optional, but better)">
        Separately, upload the skill folder under
        [Customize → Skills](https://claude.ai/customize/connectors). Instructions are the rules,
        the skill is the expertise — keeping them in their own layers is what stops one from
        drowning out the other.
      </Step>

      <Step title="Run a prompt">
        Open a new chat **inside the project** and paste the first prompt from `PROMPTBOOK.md`.
        Work down the levels rather than cherry-picking — they're ordered so the agent builds
        context before it proposes changes.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Cowork">
    Cowork projects are **desktop-only and stored locally**, which suits the playbook well — the
    folder you downloaded can *be* the project.

    <Steps>
      <Step title="Create the project">
        Click **+** next to **Projects** in the left navigation. You get three options: start from
        scratch, import an existing Claude project, or **use an existing folder on your computer**.

        Pointing it at the unzipped playbook folder is the fastest route — the files are already
        laid out the way a project wants them.
      </Step>

      <Step title="Paste the agent instructions">
        Open the project's **Instructions** section — *"Add tone, formatting, or rules to help
        guide how Claude works on all tasks in the project"* — and paste `AGENT_INSTRUCTIONS.md`
        into it.
      </Step>

      <Step title="Add the account dossier to Context">
        Use the project's **Context** area to add the local playbook folder (or link the Claude
        chat project you already set up). That's where `account-profile.md` and `PROMPTBOOK.md`
        belong — data, not rules.
      </Step>

      <Step title="Add the skill">
        In **Customize → Skills**, add the playbook folder as a skill so it sits alongside the two
        skills the Adspirer plugin installs.
      </Step>

      <Step title="Run a prompt, then schedule one">
        Work through `PROMPTBOOK.md` in the project. Once a prompt is proving itself by hand, move
        it to the **Scheduled** panel — see [scheduled tasks](/docs/guides/scheduled-tasks) and
        [Cowork for Ad Ops](/docs/guides/claude-cowork-ad-ops) for the unattended safety model.
      </Step>
    </Steps>
  </Tab>

  <Tab title="ChatGPT">
    <Steps>
      <Step title="Create the project">
        Create a Project for this ad account. One project per account — the agent should never have
        two accounts in scope at once.
      </Step>

      <Step title="Paste the agent instructions">
        Paste `AGENT_INSTRUCTIONS.md` into the project's custom-instructions field.

        On Business, Enterprise, Healthcare, or Edu you can *also* upload the skill under
        **Skills → Create → Upload from your computer**. On Free, Plus, and Pro the instructions
        field is the whole mechanism — see the plan note above.
      </Step>

      <Step title="Upload the dossier and prompt book as project files">
        Add `references/account-profile.md` and `PROMPTBOOK.md` to the project's files so ChatGPT
        can read them on demand.
      </Step>

      <Step title="Run a prompt">
        Start a chat in the project and paste the first prompt from `PROMPTBOOK.md`.
      </Step>
    </Steps>
  </Tab>
</Tabs>

<Tip>
  **The split that makes this work:** instructions are *rules*, the dossier is *data*. Paste
  `AGENT_INSTRUCTIONS.md` into the instructions field and upload `account-profile.md` as knowledge —
  never the other way round. [Set up your project](/docs/guides/set-up-your-project) explains why, and
  covers memory, connectors, and scheduling around it.
</Tip>

## Keeping it current

Ad accounts change. The playbook is a dated snapshot, and the agent is explicitly told that live
data wins over anything written in the dossier.

When the account has moved on, hit **Refresh** on the kit page. Adspirer rebuilds against current
data and gives you a new version to download.

<Check>
  **Refreshes are free and unlimited.** Rebuilding is included in the original \$39 — there is no
  charge for a new version, ever.
</Check>

## FAQ

<AccordionGroup>
  <Accordion title="Is this a subscription? Will I be charged $39 every month?">
    No. It is a single one-time charge for one ad account, and nothing recurs. If you took it as an
    add-on during plan checkout, it appears on the same invoice as your subscription as a separate
    one-time line called **"One-time Agent Setup — 1 Ad Account"** — that is why the total looked
    higher that month. Your recurring plan price is unchanged and the \$39 will not appear again.
  </Accordion>

  <Accordion title="Does it cover all my ad accounts?">
    No — one playbook covers one ad account, because it is generated from that account's own
    campaigns and history. If you run Google Ads and Meta for the same brand, those are two
    accounts and two playbooks. Buying several is one checkout and one charge, and **selecting
    every eligible account takes 20% off the whole cart** — minimum two accounts, and it must be
    all of the ones you can still buy.
  </Accordion>

  <Accordion title="Where do I download it?">
    [adspirer.ai/expert-space](https://adspirer.ai/expert-space) — accounts you own show **Open
    Kit**, and the kit page has the **Download** button, a one-click copy for the agent
    instructions, and the prompt book in a reader. The purchase email also links straight to it.
  </Accordion>

  <Accordion title="Do I keep it if I cancel or downgrade my Adspirer plan?">
    The downloaded files are yours — they're on your machine. What changes is that the tools the
    playbook drives run on your Adspirer plan, so the agent needs an active plan with quota to
    actually do the work.
  </Accordion>

  <Accordion title="Can I get a refund?">
    Each playbook is generated on demand from your account, so it is non-refundable once the build
    has completed and the files are available to download. If the build failed, or you were charged
    for an account you can't access, that's different — [contact support](/docs/knowledge-base/support).
  </Accordion>

  <Accordion title="Does it set up the Adspirer connector for me?">
    No. Connecting Adspirer to your AI client is free and covered in the
    [client setup guides](/docs/ai-clients/claude). The playbook starts after that: it teaches the agent
    how to work *your* account well.
  </Accordion>

  <Accordion title="I'm on an annual plan — do I still pay?">
    Annual plans include one playbook free. Claim it from
    [Expert Space](https://adspirer.ai/expert-space); there's no checkout and no charge. Additional
    accounts beyond the free one are \$39 each.
  </Accordion>

  <Accordion title="What if my account data changes?">
    Hit **Refresh** on the kit page for a rebuild against current data. Refreshes are free and
    unlimited. The agent is also instructed to always read live campaign data rather than trusting
    the dossier's snapshot, so a slightly stale playbook still behaves correctly.
  </Accordion>

  <Accordion title="Which AI clients does it work in?">
    All of them. The files follow the open Agent Skills and agents.md standards — Claude, Claude
    Cowork, ChatGPT, Claude Code, Cursor, Codex, Windsurf, OpenClaw, and Antigravity. Only the
    install shape differs: upload, paste, or drop the folder in.
  </Accordion>
</AccordionGroup>

## Related documentation

<CardGroup cols={2}>
  <Card title="Agent Skills" icon="book" href="/docs/agent-skills/skills">
    The 13 free skills every plan gets. The playbook builds on top of these.
  </Card>

  <Card title="Set Up Your Project" icon="folder-tree" href="/docs/guides/set-up-your-project">
    Where the playbook's instructions and context belong in a project.
  </Card>

  <Card title="Pricing" icon="tag" href="/docs/knowledge-base/pricing">
    Plans, tool calls, and where the one-time add-on sits.
  </Card>

  <Card title="Support" icon="life-ring" href="/docs/knowledge-base/support">
    Billing questions, failed builds, and anything else.
  </Card>
</CardGroup>