Publishing Cadence Reader

What this does

Publishing frequency is a public, dated, hard to fake statement about whether a company is investing in content, and it is one of the cleanest qualifiers for anyone selling content services or tooling. This skill measures the real cadence from the site, spots the gap where a program stopped, and reads acceleration and decline as separate signals.

Requirements

Check these before you run the skill. Nothing outside this table is needed.

Requirement	Needed	Used for	What it costs you
Apify account and API token (APIFY_TOKEN)	Required	Runs the live data actors	A free Apify account works. Each run bills your own Apify account at the actor's Store price: blog-publishing-frequency 0.004 USD per domain.
Node.js 18 or newer	Required	The MCP tool calls	Free. It starts the Mamba Labs MCP server with npx.

Missing a required item? Stop before the live steps and tell the user which item is missing and what it is for. Do not run the step without it and do not present an empty result as an answer. Keys are read from the environment at run time and are never written into a file, a prompt or the output.

When to use it

• how often do they publish
• content investment signal
• benchmark competitor publishing
• qualify a content buyer
• did their blog stop

Inputs

• domains: the companies to measure
• window: the period to measure over

Shared context this skill reads

Before doing anything else, read whichever of these exist at the project root and use them instead of asking the user to repeat themselves:

• ICP.md

If none exist, do the work from what the user gives you, then offer to write the missing file so the next skill in the pack starts warmer.

Tool connection

Cadence is measured from the site's own dated pages rather than from a feed, which catches sites whose feed is truncated or stale.

This skill calls live data through the Mamba Labs MCP server, which runs the actors on Apify with your own Apify token (https://console.apify.com/account/integrations).

• Installed as a plugin: the server is already wired, and the plugin asks for the token once.
• Installed by hand: copy .mcp.json from this folder into your project root and set APIFY_TOKEN in your environment, or run:

claude mcp add mamba-gtm-suite -e APIFY_TOKEN=<your token> -- npx -y @mambalabsdev/mcp-gtm-suite@1.12.0

Actor	MCP tool	Used for	Store page
Publication Cadence Tracker	track_publication_cadence	publishing volume and cadence by domain over a window	https://apify.com/mambalabs/blog-publishing-frequency

Runnable example input, matched to the live tool schema:

track_publication_cadence:

{
  "domains": [
    "example.com"
  ],
  "max_pages_to_date": 400
}

Cost line. Before any live call, state how many calls you plan and which actors they bill. After the run, report the calls made, the calls that failed, and the Apify usage where the tool reports it. Each actor bills the user's own Apify account at its Store price.

No token, no live data. If no Apify token is available, say so and stop the live steps. Never fill a live section from memory and present it as live.

Method

1. Measure over at least twelve months. A three month window cannot distinguish a seasonal gap from a program that stopped.
2. Report cadence as posts per month over time, not as a total. The shape is the signal and the total hides it.
3. Identify the inflection: the month the rate changed, up or down, and check it against public events such as a funding round or a leadership change.
4. Treat a stopped program and a never started program as different signals with different messages.
5. Check whether output is coming from one author or many, where the data allows, since a single author program is fragile and a multiple author program is a budget.
6. Do not read undated pages as absence. A site with no visible dates is unmeasured, not inactive.
7. Check the output with scripts/check-output.py before you return it.

Approval stop

This skill does not send email or write to a CRM. If the user asks it to, stop first: show what would be sent or written and wait for an explicit yes.

Output

The posts per month series, the inflection point with a date, the classification as accelerating, steady, declining or stopped, the author concentration where available, and the angle for that classification.

Check the output before you return it

Save the output to a file and run python3 scripts/check-output.py <file>. The contract it checks is scripts/output-contract.json.

• Exit 0, COMPLETE: return the output.
• Exit 2, INCOMPLETE: do not present the output as finished. Fill what you can, run the check again, and if parts stay missing, return the output under the heading Incomplete with every reason the check printed.

Quality bar

• The window is at least twelve months
• Cadence is reported as a series, not a total
• Undated pages are reported as unmeasured, not as absence
• Stopped and never started are distinguished

Related skills

• first-party-data-post
• tech-stack-signal-reader
• gtm-signal-aggregator

Ships in the seo-content-engine, signal-based-selling packs.