> ## Documentation Index
> Fetch the complete documentation index at: https://e328d4e-productmetrics.manicule.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://e328d4e-productmetrics.manicule.dev/docs/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://e328d4e-productmetrics.manicule.dev/docs/api/mcp.
> Every agent surface: https://e328d4e-productmetrics.manicule.dev/docs/.well-known/llms-manifest.json

# Product Metrics agent skills (/docs/agent-skills/overview)

<!-- agent-signals: reading_time_min: 3 · est_tokens: 1122 · updated: 2026-11-16 -->
Related: [Install Product Metrics skills](/docs/agent-skills/install.md), [set-up-tracking skill](/docs/agent-skills/set-up-tracking.md), [connect-google-ads skill](/docs/agent-skills/connect-google-ads.md), [check-tracking skill](/docs/agent-skills/check-tracking.md), [bid-on-profit skill](/docs/agent-skills/bid-on-profit.md), [analyse-google-ads skill](/docs/agent-skills/analyse-google-ads.md)

> Skills teach a coding agent or AI assistant the real steps to set up, check and use Product Metrics.

**A skill is a `SKILL.md` file of task instructions an agent loads when your request matches it.** The Product Metrics skills tell the agent which `productmetrics` commands or MCP tools to call, in which order, what to hand to you in a browser, and how to check the result.

Skills are instructions, not code. They don't run anything on their own and don't hold credentials: the agent still signs in through the [`productmetrics` CLI](/docs/cli/overview) or the [MCP server](/docs/mcp/overview), and you approve browser steps yourself.

## Install

From the project where your agent works (needs Node.js 22.20 or later):

```bash
npx skills add https://www.productmetrics.io/docs
```

The CLI lists the skills and the agents it found, and asks which to install. Flags for each agent are on [Install skills](/docs/agent-skills/install).

## Skills, CLI and MCP

| Path                                        | Use it for                                        |
| ------------------------------------------- | ------------------------------------------------- |
| **Skills**                                  | Teach the agent the real steps for a task         |
| **[CLI](/docs/cli/overview)** (`productmetrics`) | Setup and checks from a terminal or coding agent  |
| **[MCP](/docs/mcp/overview)**                    | Analysis and setup from Claude, ChatGPT or Cursor |

## Available skills

Each skill works through the CLI or the MCP server. `analyse-google-ads` needs the MCP analysis tools for its reports.

| Skill                                                    | Use it to                                                                                              |
| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
| [`set-up-tracking`](/docs/agent-skills/set-up-tracking)       | Go from nothing to tracking active: workspace, store, Google Ads, Meta, consent, costs, first purchase |
| [`connect-google-ads`](/docs/agent-skills/connect-google-ads) | Connect Google Ads and Merchant Center, or fix a broken connection                                     |
| [`check-tracking`](/docs/agent-skills/check-tracking)         | Check every part of tracking and find a test order (read only)                                         |
| [`bid-on-profit`](/docs/agent-skills/bid-on-profit)           | Set up and check POAS or ROAS bidding in Google Ads and Meta                                           |
| [`analyse-google-ads`](/docs/agent-skills/analyse-google-ads) | Answer "how are my campaigns doing" and "why did ROAS drop" with real figures (read only)              |

## How agents find them

The skills are published with these docs. An agent (or the `skills` CLI) reads the discovery index:

```bash
curl -s \
  https://www.productmetrics.io/docs/.well-known/agent-skills/index.json
```

You should see a `skills` list with one entry per skill. Each entry's `url` serves the skill file.



Response:

```json
{
  "skills": [
    {
      "name": "set-up-tracking",
      "type": "skill-md",
      "description": "Set up Product Metrics server-side conversion tracking end to end ...",
      "url": "https://www.productmetrics.io/docs/.well-known/agent-skills/set-up-tracking/SKILL.md",
      "digest": "sha256:..."
    }
  ]
}
```

Once installed, the agent sees each skill's name and description, and loads the full instructions only when your request matches one: "set up Product Metrics for my Shopify store" loads `set-up-tracking`.

## What every skill does the same way

* **Discovers, never guesses.** Ids come from earlier results; commands are checked with `productmetrics <command> --help --json` or the MCP `search` tool first.
* **Hands browser steps to you.** When a command exits with code 4 (`next_action.type: "browser"`), the agent gives you the URL and waits.
* **Keeps secrets out of the chat.** It never asks for passwords or tokens. The exceptions are credentials the API needs from you (a Lightspeed API key and secret, a Meta Conversions API token): it passes them on and never repeats them.
* **Writes for store owners.** Plain answers, with the exact app labels for the steps you take yourself.

## Where next

* [Install skills](/docs/agent-skills/install)
* [Agents, skills and MCP](/docs/overview/agents-skills-and-mcp)
* [CLI for agents](/docs/cli/for-agents)
* [MCP tools](/docs/mcp/tools)
