Every Monday: the domains that entered or left the top 10 on your 25 highest-click keywords, and how many of your clicks those keywords carry.
Reads
You get
The card on the right is a sample. Yours shows your own numbers and updates in place every run.
What lands on your board
2 new domains entered the top 10 for 6 of your 25 money keywords this week; rival.com took position 2 on "acme pricing". Those 6 keywords brought you 1,860 clicks in the last 28 days.
A new competitor rarely announces itself. It shows up at position 6 on a keyword that pays your bills, climbs for a few weeks, and you notice when clicks are already down. Rank trackers follow your own position; they don't tell you who just arrived beside you.
Every Monday the agent takes the 25 queries that bring you the most clicks in Search Console, fetches their live Google results through DataForSEO, and compares each top 10 with last week's. SEO leads, marketers and founders see which domains entered or left, on which keywords, and how many of your clicks ride on those keywords.
Call searchanalytics.query for the last 28 full days with dimensions: ["query"] and your country filter, sort by clicks and take the top 25, or use the fixed list from the settings. Save the list in serp-watch.json and refresh it only on the first Monday of the month, so the week-to-week comparison covers the same keywords.
Send one POST /v3/serp/google/organic/task_post with 25 tasks (up to 100 fit in one call), each with the keyword in lowercase, location_code and language_code for your market, depth: 10 and tag set to the keyword. Poll GET /v3/serp/google/organic/tasks_ready and fetch each with GET /v3/serp/google/organic/task_get/advanced/<id>; fetching is free for 30 days.
From each result keep items with type: "organic" and rank_group 1 to 10, and normalize domain (lowercase, strip www.). Compare the set of domains per keyword with last week's in serp-watch.json: domains in this week's set only have entered, last week's only have left. Ignore your own domain, and note your rank_group (or "not in top 10").
Join the changed keywords back to the Search Console rows on the query string and add up the clicks they brought in the last 28 days. A domain new on several keywords is a competitor; one new on a single keyword is often a one-off article. Also read the previous card with GET https://briefkin.dev/v1/cards/insight-dataforseo-new-serp-competitors to say whether a new domain was already flagged last week.
Post the keywords that changed with the domains in and out, their positions, your position and the clicks at stake. Write this week's top 10s to serp-watch.json for next Monday.
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.
Pick your agent, where the data comes from and how to schedule it; the commands below follow.
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/dataforseo-new-serp-competitors/install | shAsk Claude Code:
promptRun the dataforseo-new-serp-competitors skillOr paste the prompt instead of installing:
promptTake the 25 queries that brought my site the most clicks in Google Search Console over the last 28 full days (United States). Fetch the Google top 10 for each through DataForSEO's SERP API on the Standard queue: one task_post with 25 tasks (location_code 2840, language_code en, depth 10, tag = keyword), then tasks_ready and task_get/advanced. Keep organic results ranked 1 to 10, lowercase the domains and strip www. Compare each keyword's set of domains with last week's saved in serp-watch.json: list domains that entered (with position) and that left, and my own position. Add up my last-28-day clicks on the keywords that changed. Save this week's top 10s to serp-watch.json. Tell me how many keywords changed, the new domains and how many keywords each entered, and the competitor to look at first.Mondays at 8:00, from cron on any machine where Claude Code is signed in:
crontab0 8 * * 1 claude -p "Run the dataforseo-new-serp-competitors 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.
Connect Briefkin once with curl -fsSL https://briefkin.dev/install | sh and every run lands on your board as a report card. How setup works
SKILL.md---
name: dataforseo-new-serp-competitors
description: "Every Monday: the domains that entered or left the top 10 on your 25 highest-click keywords, and how many of your clicks those keywords carry. Use when the user asks for this, or when it runs on a schedule."
---
# New competitors on your money keywords: DataForSEO SERP API and Search Console
Every Monday: the domains that entered or left the top 10 on your 25 highest-click keywords, and how many of your clicks those keywords carry.
A new competitor rarely announces itself. It shows up at position 6 on a keyword that pays your bills, climbs for a few weeks, and you notice when clicks are already down. Rank trackers follow your own position; they don't tell you who just arrived beside you.
Every Monday the agent takes the 25 queries that bring you the most clicks in Search Console, fetches their live Google results through DataForSEO, and compares each top 10 with last week's. SEO leads, marketers and founders see which domains entered or left, on which keywords, and how many of your clicks ride on those keywords.
## 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 and the market you track (country, plus DataForSEO `location_code` and `language_code`, for example `2840` and `en`).
- DataForSEO API login and password, or the DataForSEO MCP server. A run is 25 Standard-queue SERPs a week, about $0.015 at list price; try the task flow on `https://sandbox.dataforseo.com/v3/` first.
- A folder the agent can keep `serp-watch.json` in between runs; the first run only records a baseline.
If something is missing, say what and stop; do not invent numbers.
### Steps
1. **Fix the 25 money keywords** (Google Search Console): Call `searchanalytics.query` for the last 28 full days with `dimensions: ["query"]` and your country filter, sort by clicks and take the top 25, or use the fixed list from the settings. Save the list in `serp-watch.json` and refresh it only on the first Monday of the month, so the week-to-week comparison covers the same keywords.
2. **Queue 25 SERPs on the Standard queue** (DataForSEO): Send one `POST /v3/serp/google/organic/task_post` with 25 tasks (up to 100 fit in one call), each with the keyword in lowercase, `location_code` and `language_code` for your market, `depth: 10` and `tag` set to the keyword. Poll `GET /v3/serp/google/organic/tasks_ready` and fetch each with `GET /v3/serp/google/organic/task_get/advanced/<id>`; fetching is free for 30 days.
3. **Compare each top 10 with last week**: From each result keep items with `type: "organic"` and `rank_group` 1 to 10, and normalize `domain` (lowercase, strip `www.`). Compare the set of domains per keyword with last week's in `serp-watch.json`: domains in this week's set only have entered, last week's only have left. Ignore your own domain, and note your `rank_group` (or "not in top 10").
4. **Weigh the change by your clicks** (Google Search Console): Join the changed keywords back to the Search Console rows on the query string and add up the clicks they brought in the last 28 days. A domain new on several keywords is a competitor; one new on a single keyword is often a one-off article. Also read the previous card with `GET https://briefkin.dev/v1/cards/insight-dataforseo-new-serp-competitors` to say whether a new domain was already flagged last week.
5. **Post and save**: Post the keywords that changed with the domains in and out, their positions, your position and the clicks at stake. Write this week's top 10s to `serp-watch.json` for next Monday.
## Route B: the browser
### What you need
- Signed in to Google with access to the Search Console property, and to the DataForSEO dashboard with a funded balance. The agent needs a file it can read and write for last week's lists.
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. **Pick the money keywords**: Pick the property, set Date to `Last 28 days` and your country, and sort the Queries table by Clicks. Note the top 25 queries with their clicks, or use your fixed list.
2. **Fetch the top 10s in DataForSEO**: Open `https://app.dataforseo.com/`, go to API Playground, choose SERP API > Google > Organic > Live Advanced, set your location and language and depth `10`, and run each of the 25 keywords once. Note the organic results ranked 1 to 10 by domain.
3. **Compare with last week**: Compare each keyword's domains with last week's list in the saved file: new domains have entered, missing ones have left. Leave out your own domain and note your position.
4. **Report and save**: List the changed keywords with domains in and out, your position and your clicks from Search Console, and save this week's lists for next Monday.
Note: The Playground runs Live requests (about three times the Standard queue price) one at a time, so 25 keywords take a while and cost more than the API route. Searching Google by hand is free but shows results personalized to your browser and location, so it is not comparable week to week.
## The report
- **Keywords that changed**: how many of the 25 have a new domain in the top 10.
- **New domains**, with the keywords they entered and their positions.
- **Domains that left** the top 10.
- **Clicks at stake**: last 28 days of your clicks on the changed keywords.
- The competitor to look at first.
## 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": "dataforseo-new-serp-competitors/<date of this run, e.g. 2026-10-16>",
"item_key": "dataforseo-new-serp-competitors",
"project": "example.com",
"source": "New competitors on your money keywords: DataForSEO SERP API and Search Console skill",
"kind": "update",
"title": "2 new domains entered the top 10 on 6 money keywords",
"summary": "**2 new domains** entered the top 10 for **6 of your 25** money keywords this week; **rival.com** took position 2 on \"acme pricing\". Those 6 keywords brought you **1,860 clicks** in the last 28 days.",
"widget": [
{
"type": "Table",
"props": {
"columns": [
"Keyword",
"Entered (pos)",
"Left",
"You",
"Your clicks 28d"
],
"align": [
"left",
"left",
"left",
"right",
"right"
],
"rows": [
[
"acme pricing",
"rival.com (2)",
"oldtool.com",
1,
610
],
[
"invoice software",
"rival.com (7)",
"",
9,
240
],
[
"invoice app",
"quotepilot.io (6)",
"",
4,
380
],
[
"recurring invoices",
"rival.com (9), quotepilot.io (10)",
"oldtool.com",
5,
290
],
[
"invoice template pdf",
"quotepilot.io (8)",
"",
6,
210
],
[
"billing software small business",
"rival.com (5)",
"",
7,
130
]
]
}
},
{
"type": "Badges",
"props": {
"items": [
{
"label": "rival.com: 4 keywords",
"tone": "bad"
},
{
"label": "quotepilot.io: 3 keywords",
"tone": "warn"
},
{
"label": "oldtool.com left 2",
"tone": "neutral"
},
{
"label": "19 keywords unchanged",
"tone": "ok"
}
]
}
},
{
"type": "Callout",
"props": {
"text": "Look at rival.com first: new on 4 keywords at once, including your own brand query. Its /vs/acme page is the one ranking on \"acme pricing\".",
"tone": "warn"
}
}
]
}
JSON
```
Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.
## Run it on a schedule
Suggested: Mondays at 8:00 (`0 8 * * 1`). From cron, with the agent signed in on that machine:
```bash
0 8 * * 1 claude -p "Run the dataforseo-new-serp-competitors 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/dataforseo-new-serp-competitors#schedule
Source: https://briefkin.dev/skills/dataforseo-new-serp-competitors
Read access to the Search Console property and the market you track (country, plus DataForSEO location_code and language_code, for example 2840 and en).
DataForSEO API login and password, or the DataForSEO MCP server. A run is 25 Standard-queue SERPs a week, about $0.015 at list price; try the task flow on https://sandbox.dataforseo.com/v3/ first.
A folder the agent can keep serp-watch.json in between runs; the first run only records a baseline.
npx dataforseo-mcp-server and set DATAFORSEO_USERNAME and DATAFORSEO_PASSWORD to your API login and API password (Dashboard > API Access); add http to the command for clients that want a local HTTP server. A hosted server runs at https://mcp.dataforseo.com/mcp for clients that can send a Basic authorization header. You can turn off the modules a skill doesn't use to keep the tool list short (setup guide).DATAFORSEO_LOGIN and DATAFORSEO_PASSWORD and call the endpoints with curl -u "$DATAFORSEO_LOGIN:$DATAFORSEO_PASSWORD". The free sandbox at https://sandbox.dataforseo.com/v3/ returns sample data at no cost, which is the place to test a skill before it spends money.The API password can spend your balance but cannot sign in to the dashboard or change billing. Set a low balance alert in the dashboard, and give each skill a fixed keyword list and depth so a run costs the same every time.
GOOGLE_APPLICATION_CREDENTIALS at the key and set GSC_SITE_URL to sc-domain:example.com or https://www.example.com/.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.
The SERP API returns one live result page for one location at the time of the request. Search Console averages your position over every impression in 28 days, across devices and cities. The card shows the live position because it is the same snapshot the competitors come from; a gap of one or two places is normal.
Twenty-five SERPs a week. The Standard queue costs less than Live (at list price about $0.0006 a SERP against $0.002) and returns within minutes, which is fine for a Monday report. Keep depth at 10: you are billed per page of 10 results, so a deeper crawl multiplies the cost without telling you more about the top 10.
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 report card, so you can glance at it instead of asking again.
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.
Yes. Switch the data source to "Your browser" and the steps change to the DataForSEO and 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.
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.