# Weekly Context7 docs usage report in Sheets and Slack

> See which AI coding assistants are reading your published documentation each week, with a running history in Sheets and a Monday summary in Slack.

- Workflow type: code
- Services: Context7, Google Sheets, Slack
- Categories: Engineering, Marketing
- Published: 2026-08-04

## What it does

- Every Monday morning, pulls the last seven days of usage for each library your team publishes to Context7.
- Records one row per library per week in a Google Sheet, so you build a clean history of request volume over time.
- Breaks down which AI coding assistants are reading your docs, including Cursor, Claude Code and Windsurf, alongside the topics and countries the requests came from.
- Posts a summary to your developer relations Slack channel with this week's totals, the change against last week, and the topics developers asked about most.

## What you'll need

- A Context7 account that belongs to the teamspace or team project that owns your libraries. This is the important one: usage figures are only available to the team that publishes the documentation, so this report is for teams who publish their own libraries to Context7, not for people who only read the public catalog.
- The list of libraries your team publishes, so the report knows what to track.
- A Google account and a spreadsheet with a tab set aside for the weekly history.
- A Slack workspace and a channel where your developer relations team wants the summary posted.

## Prompt

Every Monday at 9am, run a scheduled workflow that reports on how AI coding assistants consumed the documentation we publish to Context7 over the previous 7 days. This is a fixed report with fixed fields and fixed destinations, so build it as a deterministic workflow with no reasoning step.

Keep the list of library IDs we own as a configurable input at the top of the workflow so we can add or remove libraries without rebuilding it. For each library in that list, call Get Library Usage Metrics in Context7 with the days parameter set to 7. From each response, pull the request counters, the MCP client breakdown, the topic distribution and the country distribution. Note that this operation requires our Context7 API key to belong to a member of the teamspace or team project that owns the library, so it only works for libraries we publish ourselves.

Before writing anything new, use Get Values in Google Sheets to read the existing rows on the tracking tab and find the most recent prior row for each library. Use that row's total request count to compute the week over week change, as both an absolute difference and a percentage. If there is no prior row for a library, treat this run as the baseline and record the change as not applicable rather than as zero.

Then use Append Values in Google Sheets to append one row per library per week to the tracking tab. Each row should carry: the week start date, the week end date, the library ID, total requests for the window, the absolute and percentage change versus the prior week, the per client request counts for the MCP clients returned (Cursor, Claude Code, Windsurf and any others), the top topics with their request counts, and the top countries with their request counts. Serialize the client, topic and country breakdowns into single cells as compact name equals count lists so the row stays one row wide and the column layout never shifts between weeks. Always append a row for every tracked library, even when a library returned no traffic, recording zeros so the history has no gaps.

Finally, use Send a Message in Slack to post the weekly summary to our developer relations channel. The message should lead with the reporting window and the combined request total across all libraries with its week over week change, then list each library on its own line with its total and its change versus last week, then show the aggregate client breakdown so we can see which coding assistants are hitting our docs hardest, and close with the most requested topics across all libraries. Sort libraries by request volume descending and mark clear risers and fallers so the trend is readable at a glance.

If Context7 returns an error for one library, skip that library, still report the others, and note the failure at the end of the Slack message rather than aborting the whole run.

## How to customize

- Change the day and time it runs, and the length of the reporting window if you would rather see fourteen or thirty days.
- Add or remove libraries from the tracked list as your team publishes more documentation.
- Point the summary at a different Slack channel, or post to several at once.
- Adjust how many top topics and clients are included in the Slack message.

## Example output

Context7 docs usage, week of 28 Jul to 3 Aug

Total requests across 3 libraries: 14,208 (up 12% from 12,684)

/acme/acme-sdk: 9,431 requests (up 18% from 7,993)
/acme/acme-cli: 3,902 requests (up 4% from 3,752)
/websites/acme_docs: 875 requests (down 7% from 939)

Top clients: Cursor 6,110 | Claude Code 4,388 | Windsurf 2,201 | Other 1,509

Top topics: authentication, webhooks setup, rate limits, migrating to v3, error handling

## FAQ

### Which AI coding tools will I see in the report?

Whichever ones are actually requesting your documentation. Context7 reports the client behind each request, so you typically see tools like Cursor, Claude Code and Windsurf broken out separately, along with anything else that pulls your docs.

### Does this work for any library, or only my own?

Only libraries your team owns. Usage figures are restricted to the team that publishes the documentation, so your Context7 account has to be a member of the teamspace or team project that owns the library. It will not report on libraries published by other people.

### What happens on the very first run, when there is no previous week to compare against?

The first run simply records the baseline row for each library and notes in the Slack message that there is no prior week yet. From the second week onward you get a proper week over week comparison.

### What if one of my libraries had no traffic that week?

It still gets a row, recorded as zero. Keeping the history continuous means your charts and comparisons do not develop gaps, and a sudden drop to zero is itself worth seeing.

### Can I run this more often than weekly?

Yes. The schedule and the reporting window are both settings, so you can switch to a daily or monthly rhythm. Just keep the window matched to the schedule so the history rows do not overlap or leave gaps.

Use this prompt in General Input: https://www.generalinput.com/prompts/weekly-context7-docs-usage-report-in-sheets-and-slack