Blog views up 12%, 64 contacts from the blog
18,940 views in September (+12%) and 64 new contacts whose first page was a blog post (51 in August). The invoice template guide brought a third of them.
On the 1st: last month's HubSpot blog views, contacts whose first visit was a blog post, the top posts, and how new posts did.
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
18,940 views in September (+12%) and 64 new contacts whose first page was a blog post (51 in August). The invoice template guide brought a third of them.
Content teams on HubSpot can see views per post, and they can see new contacts, but rarely both on one page. The monthly blog review turns into a debate about whether traffic matters if it does not turn into leads.
This skill answers both halves. It pulls last month's views per post, counts the new contacts whose first page seen was on the blog, and lists the posts published last month with how they started. The ten minutes go to deciding what to write next instead of collecting numbers.
Call the analytics API GET /analytics/v2/reports/blog-posts/total?start=YYYYMMDD&end=YYYYMMDD for last month and the month before, sorted by views. Keep rawViews and entrances per post.
GET /cms/v3/blogs/posts?state=PUBLISHED&publishDate__gte=<first of month>&publishDate__lt=<first of this month> for each post's name, url and publishDate.
Search contacts created last month (POST /crm/v3/objects/contacts/search, createdate BETWEEN) with the properties hs_analytics_first_url and hs_analytics_source. Count those whose first URL is under your blog path, and which posts they first landed on.
Total views and blog contacts against the month before, the top 5 posts by views with their contacts, and the new posts with views so far. Mark posts that bring views but no contacts, and the reverse.
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/hubspot-blog-performance-report/install | shAsk Claude Code:
promptRun the hubspot-blog-performance-report skillOr paste the prompt instead of installing:
promptUsing HubSpot's APIs, report last month's blog performance against the month before. Get views and entrances per blog post (analytics API, blog-posts report), the posts published last month (CMS blog posts API), and the contacts created last month whose first page seen (hs_analytics_first_url) is on the blog, grouped by that post. Give me total views and blog contacts with the change, the top 5 posts by views with contacts each, how last month's new posts did, and one line on a post with traffic but no contacts.1st of the month at 9:00, from cron on any machine where Claude Code is signed in:
crontab0 9 1 * * claude -p "Run the hubspot-blog-performance-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.
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: hubspot-blog-performance-report
description: "On the 1st: last month's HubSpot blog views, contacts whose first visit was a blog post, the top posts, and how new posts did. Use when the user asks for this, or when it runs on a schedule."
---
# HubSpot blog performance report
On the 1st: last month's HubSpot blog views, contacts whose first visit was a blog post, the top posts, and how new posts did.
Content teams on HubSpot can see views per post, and they can see new contacts, but rarely both on one page. The monthly blog review turns into a debate about whether traffic matters if it does not turn into leads.
This skill answers both halves. It pulls last month's views per post, counts the new contacts whose first page seen was on the blog, and lists the posts published last month with how they started. The ten minutes go to deciding what to write next instead of collecting numbers.
## 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
- A HubSpot account with blog analytics (Content Hub or Marketing Hub), and a user or private app that can read contacts and CMS content.
- The HubSpot MCP server or connector, or a private app token in `HUBSPOT_ACCESS_TOKEN` with `crm.objects.contacts.read` and `content`.
If something is missing, say what and stop; do not invent numbers.
### Steps
1. **Pull views per post** (HubSpot): Call the analytics API `GET /analytics/v2/reports/blog-posts/total?start=YYYYMMDD&end=YYYYMMDD` for last month and the month before, sorted by views. Keep `rawViews` and `entrances` per post.
2. **List last month's new posts** (HubSpot): `GET /cms/v3/blogs/posts?state=PUBLISHED&publishDate__gte=<first of month>&publishDate__lt=<first of this month>` for each post's `name`, `url` and `publishDate`.
3. **Count contacts from the blog** (HubSpot): Search contacts created last month (`POST /crm/v3/objects/contacts/search`, `createdate` BETWEEN) with the properties `hs_analytics_first_url` and `hs_analytics_source`. Count those whose first URL is under your blog path, and which posts they first landed on.
4. **Compare and rank**: Total views and blog contacts against the month before, the top 5 posts by views with their contacts, and the new posts with views so far. Mark posts that bring views but no contacts, and the reverse.
## Route B: the browser
### What you need
- Signed in to HubSpot with a user that can view blog content and analytics (Marketing Hub or Content Hub) and view contacts.
If something is missing, say what and stop; do not invent numbers.
### Steps
Start at https://app.hubspot.com/. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.
1. **Open the blog analytics**: Open HubSpot, pick the account if more than one is listed, then go to **Content > Blog** and open the **Analyze** tab. Set the date range to last month. Read total `Views` and the per-post table sorted by views; if the table caps its rows, use **Export** and read the file.
2. **Repeat for the month before**: Change the date range to the month before and read total views again, plus the top 5 posts for comparison.
3. **List the new posts**: On the **Manage** tab, filter by **Publish date** to last month and note each post's name, URL and publish date.
4. **Count contacts who started on the blog**: Open **Contacts**, add **Advanced filters** `Create date` **is between** the first and last day of last month and `First page seen` **contains** your blog path (`/blog/`), and read the count. Add the `First page seen` column to see which posts they landed on.
5. **Compare and rank**: Total views and blog contacts against the month before, the top 5 posts with their contacts, the new posts with views so far, and the posts with traffic but no contacts.
Note: The Analyze tab shows the same views the analytics API returns, so the browser route is the better one for accounts whose plan returns nothing from the API. Contact counts by first page seen depend on the HubSpot tracking code being on the blog.
## The report
- **Blog views** and **contacts first seen on the blog**, against last month.
- **Top 5 posts** by views, with entrances and contacts each.
- **New posts** from last month and how they started.
- **Mismatches**: posts with traffic and no contacts, and small posts that convert.
## 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": "hubspot-blog-performance-report/<date of this run, e.g. 2026-10-16>",
"item_key": "hubspot-blog-performance-report",
"project": "Acme",
"source": "HubSpot blog performance report skill",
"kind": "update",
"title": "Blog views up 12%, 64 contacts from the blog",
"summary": "**18,940 views** in September (+12%) and **64 new contacts** whose first page was a blog post (51 in August). The invoice template guide brought a third of them.",
"widget": [
{
"type": "Table",
"props": {
"columns": [
"Post",
"Views",
"Entrances",
"Contacts"
],
"align": [
"left",
"right",
"right",
"right"
],
"rows": [
[
"Free invoice templates for freelancers",
4210,
3880,
22
],
[
"How to write a late payment reminder",
2960,
2710,
9
],
[
"Net 30 payment terms explained",
2440,
2190,
4
],
[
"Invoice vs receipt: the difference",
1980,
1830,
0
],
[
"Getting paid in 2 currencies (new)",
870,
640,
6
]
]
}
},
{
"type": "Callout",
"props": {
"text": "\"Invoice vs receipt\" brings 1,980 views and no contacts. It has no call to action; add the template download.",
"tone": "info"
}
}
]
}
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: 1st of the month at 9:00 (`0 9 1 * *`). From cron, with the agent signed in on that machine:
```bash
0 9 1 * * claude -p "Run the hubspot-blog-performance-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/hubspot-blog-performance-report#schedule
Source: https://briefkin.dev/skills/hubspot-blog-performance-report
A HubSpot account with blog analytics (Content Hub or Marketing Hub), and a user or private app that can read contacts and CMS content.
The HubSpot MCP server or connector, or a private app token in HUBSPOT_ACCESS_TOKEN with crm.objects.contacts.read and content.
https://mcp.hubspot.com. HubSpot also offers a Claude connector built on the same server; you sign in with your HubSpot user and it sees what that user can see (docs).crm.objects.deals.read, crm.objects.contacts.read, crm.objects.companies.read, crm.objects.owners.read), and store its token in HUBSPOT_ACCESS_TOKEN.The MCP server and connector can create and update records, so for unattended reports a private app with only .read scopes is the safer credential.
Blog analytics through the API depends on your HubSpot plan, and the report is part of HubSpot's older analytics API. If it returns an error or no rows, export the blog's page performance from HubSpot as a CSV each month and point the skill at the file. The contact counts still come from the CRM API.
It means their first recorded visit was a blog post. Many converted later on a landing page. That is the fairest single number for a blog's pull, but read it as "started here", not "signed up here".
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 HubSpot pages themselves: the agent opens app.hubspot.com 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.