Get a weekly Google Search Console keyword report from your AI agent

Every Monday: clicks, impressions and position for your top queries, what moved since last week, and the pages to work on first.

Runs
Mondays at 9:00
Posts
Stat tile

What lands on your board

example.comOrganic clicks4,812+6% vs previous period, bettervs last report
Impressions182k+9.0% vs previous period
Avg position11.4-6.0% vs previous period, better
CTR2.6%+4.0% vs previous period, better
↑ invoice template↑ free invoice maker↓ invoice software
An example with made-up numbers. Your agent posts your real ones.

What it does

For anyone who owns a site's organic traffic and opens Search Console every Monday to see what moved. The agent pulls the last 7 days of query data, lines it up against the 7 days before, and writes down only what changed: the queries that gained or lost clicks, the ones whose position slipped, and the new ones.

You stop scrolling the Performance report and start the week with five lines you can act on.

How it works

  1. 1Pull this week's queries

    Call searchanalytics.query for the property with dimensions: ["query"], the last 7 full days (Search Console lags about 2 days) and rowLimit: 250. Keep clicks, impressions, CTR and position.

  2. 2Pull the week before

    Run the same query for the 7 days before that, so every query has a this-week and a last-week row.

  3. 3

    3Find what moved

    Join the two weeks on the query. Flag gains and drops in clicks of 20% or more (with at least 10 clicks), position changes of 2 or more places, and queries that are new this week with at least 50 impressions.

  4. 4

    4Write the report

    Total clicks and the change, then up to 5 winners, 5 losers and 5 new queries, each with clicks, position and the page that ranks for it.

  5. Post it to the board

    With BRIEFKIN_TOKEN set, the agent sends the result as one card that updates in place every run. Without it, you get the report in the chat.

What you get

  • Clicks this week and the change against last week.
  • Winners: up to 5 queries with the biggest gains in clicks.
  • Losers: up to 5 queries that dropped, with their old and new position.
  • New queries that started showing up this week.
  • One line on what to do first, for example "Refresh /pricing: it lost 3 positions for 'invoice software'".

Install and run it

Pick your agent, where the data comes from and how to schedule it; the commands below follow.

Agent
Data
Schedule
  1. Install the skill

    One command. It puts the SKILL.md in ~/.claude/skills and in ~/.agents/skills, which Codex, Cursor, Gemini CLI, Copilot CLI and OpenCode read too.

    shellcurl -fsSL https://briefkin.dev/skills/google-search-console-weekly-keyword-report/install | sh
  2. Run it

    Ask Claude Code:

    promptRun the google-search-console-weekly-keyword-report skill

    Or paste the prompt instead of installing:

    promptUsing the Google Search Console API for my site, compare the last 7 full days with the 7 days before (dimension: query, up to 250 rows). Give me total clicks and the change, then up to 5 queries that gained the most clicks, 5 that lost the most (with old and new position) and up to 5 new queries with at least 50 impressions. For each, name the page that ranks. End with the one page I should work on first and why.
  3. Put it on a schedule

    Mondays at 9:00, from cron on any machine where Claude Code is signed in:

    crontab0 9 * * 1 claude -p "Run the google-search-console-weekly-keyword-report skill"

    Add it with crontab -e. A laptop asleep at that time runs it when it wakes if you use launchd or Task Scheduler instead; GitHub Actions works for the API route.

  4. Send it to your board

    Connect Briefkin once with curl -fsSL https://briefkin.dev/install | sh and every run lands on your board as a stat tile. How setup works

View the SKILL.mdRaw file
SKILL.md---
name: google-search-console-weekly-keyword-report
description: "Every Monday: clicks, impressions and position for your top queries, what moved since last week, and the pages to work on first. Use when the user asks for this, or when it runs on a schedule."
---

# Search Console weekly keyword report

Every Monday: clicks, impressions and position for your top queries, what moved since last week, and the pages to work on first.

For anyone who owns a site's organic traffic and opens Search Console every Monday to see what moved. The agent pulls the last 7 days of query data, lines it up against the 7 days before, and writes down only what changed: the queries that gained or lost clicks, the ones whose position slipped, and the new ones.

You stop scrolling the Performance report and start the week with five lines you can act on.

## Two ways to get the data

Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.

## Route A: API or MCP server

### What you need

- Read access to the Search Console property (`sc-domain:example.com` or a URL-prefix property).
- A way for the agent to call the Search Console API: a Search Console MCP server, or a service account added as a user on the property with `GOOGLE_APPLICATION_CREDENTIALS` set.

If something is missing, say what and stop; do not invent numbers.

### Steps

1. **Pull this week's queries** (Google Search Console): Call `searchanalytics.query` for the property with `dimensions: ["query"]`, the last 7 full days (Search Console lags about 2 days) and `rowLimit: 250`. Keep clicks, impressions, CTR and position.
2. **Pull the week before** (Google Search Console): Run the same query for the 7 days before that, so every query has a this-week and a last-week row.
3. **Find what moved**: Join the two weeks on the query. Flag gains and drops in clicks of 20% or more (with at least 10 clicks), position changes of 2 or more places, and queries that are new this week with at least 50 impressions.
4. **Write the report**: Total clicks and the change, then up to 5 winners, 5 losers and 5 new queries, each with clicks, position and the page that ranks for it.

## Route B: the browser

### What you need

- Signed in to Google in this browser with an account that has at least Restricted access to the Search Console property.

If something is missing, say what and stop; do not invent numbers.

### Steps

Start at https://search.google.com/search-console/performance/search-analytics. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.

1. **Open the Performance report**: The URL opens the property picker when the account has several properties; choose the site, then Performance > Search results. Leave Search type on `Web`.
2. **Compare the two weeks**: Click the Date filter, open the Compare tab, choose `Compare last 7 days week over week` and click Apply. Turn on all four tiles above the chart (Total clicks, Total impressions, Average CTR, Average position) so the table shows them for both periods with a Difference column.
3. **Read winners, losers and newcomers**: On the Queries tab, sort by the Clicks difference for the gains, then the other way for the drops. Keep gains and drops of 20% or more with at least 10 clicks, position changes of 2 or more, and rows with no clicks or impressions in the earlier week and at least 50 impressions now.
4. **Find the ranking page**: For each query you keep, click its row (this adds a Query filter), switch to the Pages tab and note the first page, then remove the filter with the x. Up to 15 queries is a few minutes of clicking.
5. **Export when the table is full**: The table and its exports stop at 1,000 rows per tab. For a site with more queries, use Export > Download CSV, keep the same thresholds and finish the comparison in a spreadsheet.

Note: The UI caps each table and export at 1,000 rows, so large sites get their top queries only; the API returns up to 25,000 rows per call. Both routes carry the same 2-day data lag. The comparison is the same one the report draws, so for a quick look the browser route is the faster one.

## The report

- **Clicks this week** and the change against last week.
- **Winners**: up to 5 queries with the biggest gains in clicks.
- **Losers**: up to 5 queries that dropped, with their old and new position.
- **New queries** that started showing up this week.
- One line on what to do first, for example "Refresh /pricing: it lost 3 positions for 'invoice software'".

## Post it to Briefkin

When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.

```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
  -H "authorization: Bearer $BRIEFKIN_TOKEN" \
  -H "content-type: application/json" \
  -d @- <<'JSON'
{
  "v": 1,
  "event_id": "google-search-console-weekly-keyword-report/<date of this run, e.g. 2026-10-16>",
  "item_key": "google-search-console-weekly-keyword-report",
  "project": "example.com",
  "source": "Search Console weekly keyword report skill",
  "kind": "metric",
  "title": "Organic clicks this week",
  "metric": {
    "label": "Organic clicks",
    "value": 4812,
    "better": "higher",
    "period_start": "<start of the period, ISO 8601>",
    "period_end": "<end of the period, ISO 8601>"
  },
  "glance": [
    {
      "type": "Grid",
      "props": {
        "columns": 3
      },
      "children": [
        {
          "type": "Stat",
          "props": {
            "label": "Impressions",
            "value": "182k",
            "delta": 9
          }
        },
        {
          "type": "Stat",
          "props": {
            "label": "Avg position",
            "value": 11.4,
            "delta": -6,
            "better": "lower"
          }
        },
        {
          "type": "Stat",
          "props": {
            "label": "CTR",
            "value": 2.6,
            "unit": "%",
            "delta": 4
          }
        }
      ]
    },
    {
      "type": "Badges",
      "props": {
        "items": [
          {
            "label": "↑ invoice template",
            "tone": "ok"
          },
          {
            "label": "↑ free invoice maker",
            "tone": "ok"
          },
          {
            "label": "↓ invoice software",
            "tone": "bad"
          }
        ]
      }
    }
  ],
  "widget": [
    {
      "type": "Table",
      "props": {
        "columns": [
          "Query",
          "Clicks",
          "Change",
          "Position"
        ],
        "align": [
          "left",
          "right",
          "right",
          "right"
        ],
        "rows": [
          [
            "invoice template",
            1204,
            "+18%",
            3.1
          ],
          [
            "free invoice maker",
            860,
            "+31%",
            4.6
          ],
          [
            "invoice generator",
            512,
            "+4%",
            6.2
          ],
          [
            "invoice software",
            288,
            "-22%",
            9.8
          ],
          [
            "receipt template",
            141,
            "new",
            12.4
          ]
        ]
      }
    },
    {
      "type": "Callout",
      "props": {
        "text": "Refresh /pricing: it slipped from 6.4 to 9.8 for \"invoice software\".",
        "tone": "warn"
      }
    }
  ],
  "size": "md"
}
JSON
```

Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.

Set `period_start` and `period_end` to the window the number covers: the tile names it from them ("Last 7 days", "Today", "This month"). For a count right now (open items, a balance), send `"period_label": ""` so no period shows; for another name, send it as `period_label` (at most 24 characters).

## Run it on a schedule

Suggested: Mondays at 9:00 (`0 9 * * 1`). From cron, with the agent signed in on that machine:

```bash
0 9 * * 1 claude -p "Run the google-search-console-weekly-keyword-report skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```

Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/google-search-console-weekly-keyword-report#schedule

Source: https://briefkin.dev/skills/google-search-console-weekly-keyword-report

What your agent needs

  • Read access to the Search Console property (sc-domain:example.com or a URL-prefix property).

  • A way for the agent to call the Search Console API: a Search Console MCP server, or a service account added as a user on the property with GOOGLE_APPLICATION_CREDENTIALS set.

Connecting Google Search Console

  1. MCP server. Google doesn't publish one for Search Console. Community MCP servers exist; check which scopes one asks for before you sign in.
  2. API with a service account. Enable the Google Search Console API in a Google Cloud project, create a service account, and add its email under Settings > Users and permissions on the property. Point GOOGLE_APPLICATION_CREDENTIALS at the key and set GSC_SITE_URL to sc-domain:example.com or https://www.example.com/.
  3. OAuth as yourself. When you can't add users to the property, a desktop OAuth client with the webmasters.readonly scope and a stored refresh token works for scheduled runs.

Ask for webmasters.readonly and add the service account as a Restricted user; the reports only read.

Questions

Why does the report stop two days ago?

Search Console data is final about two days after the fact. The skill uses the last 7 full days it has, so this week and last week are always compared like for like.

Can it report on one folder or country?

Yes. Add a filter to both queries, for example page contains /blog/ or country equals usa, and say so in the prompt. Keep a separate item_key per filter so each gets its own card.

Do I need Briefkin to use the Search Console weekly keyword report skill?

No. The skill runs with your own agent and gives you the report in the chat. With a Briefkin token set, each run also posts it to your board as a stat tile, so you can glance at it instead of asking again.

Which agents can run it?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Windsurf and Amp all read SKILL.md files. The install command puts it in ~/.claude/skills and ~/.agents/skills, where they look. ChatGPT, the Claude app and Grok take the prompt instead. Pick your agent under "Install and run it" and the commands change to match.

Can it work without an API or MCP server, from my browser?

Yes. Switch the data source to "Your browser" and the steps change to the Google Search Console pages themselves: the agent opens search.google.com/search-console/performance/search-analytics in a browser you are signed in to and reads the numbers off the page. Claude Code, Codex, Cursor, Claude app and ChatGPT can drive a browser out of the box; Gemini CLI, Copilot CLI and OpenCode need a Playwright or Chrome DevTools MCP server first. It is slower than the API and needs you signed in, so it suits a report you run by hand or from a scheduler on your own computer.

Watch organic clicks on your board, run after run

Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.

Free during the open beta. No card.