/
/
Get a two-minute digest of a GitHub repository's week
For team leads who want commits, issues and CI health summarized without reading raw logs, by asking their AI assistant.
On this page
Connector
Connect GitHub, pick your AI tool and paste the prompt.
The problem
A repository's week takes an hour of clicking
A team lead wants to know what happened in a GitHub repository this week, but that means reading commits, issues and CI results separately. The summary takes an hour or, more often, does not happen.
Without PopdockAI
- Read the commit log for the week
- Scan issues opened and closed
- Check workflow results one by one
- Skip the summary when time is short
With PopdockAI
- Commits, issues and workflow runs are read for your period
- Commits are counted by author and grouped into themes
- Workflows under 80 percent success are called out
- A two minute digest with the date range, and nothing is touched
The prompt
Use this prompt
Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.
**Objective:** Summarise the activity in `{repository}` over the last `{lookback-days}` days (default 7) as a digest a team lead can read in two minutes.
**Step 1: Commits**
Call `github-get-commit` with company `{repository}`, commit-date.from set to today minus the lookback, and max-records 200. Count commits per author-name and group the messages into themes (features, fixes, dependency updates, refactors). If exactly 200 come back, say the count is a lower bound.
**Step 2: Issues**
Call `github-get-issue` with company `{repository}` and created-date.from set to the start of the window to find issues opened in it. Then call `github-get-issue` with status `closed` and updated-date.from set to the start of the window, and keep only those whose closed-date falls inside the window.
**Step 3: CI health**
Call `github-get-workflow-run` with company `{repository}` and created-date.from set to the start of the window. Count runs by conclusion per workflow name and compute a success rate for each.
**Step 4: Report**
* Headline numbers: commits, contributors, issues opened, issues closed, workflow success rate.
* Top themes of the work, three to five bullets, drawn from commit messages.
* Notable issues opened and closed (issue-number and title, at most five each).
* Workflows with a success rate below 80 percent.
**Rules & Guidelines:**
* This prompt is read-only. Do NOT call `github-add-issue`, `github-update-issue`, `github-add-issue-assignee`, `github-add-issue-label`, `github-add-issue-comment`, `github-update-issue-comment`, `github-lock-issue`, `github-unlock-issue`, `github-add-milestone`, `github-update-milestone`, `github-rerun-workflow-run`, `github-cancel-workflow-run`, `github-enable-workflow` or `github-disable-workflow`.
* State the exact date range you used at the top of the digest.
**Validation:**
* If a section returns nothing, say "No activity" for that section rather than omitting it.
* If every section is empty, check the repository name with the user.Who it's for
One answer, three teams that use it
Team leads
Know what the team shipped
Headline numbers and top themes tell you what happened without reading logs.
Summarise activity in fabrikam/app for the last 14 days.
Engineering managers
Watch CI health
Workflow success rates with weak ones called out show where the pipeline needs work.
How healthy was CI in contoso/api this week, and what were the main themes?
Product managers
Follow progress without GitHub skills
A plain digest of commits, issues and CI lets you follow along in two minutes.
What happened in northwind/web this sprint, in plain words?
How it works
What PopdockAI does when you ask
You name the repository and a period, and your AI assistant turns the raw activity into a short digest. Empty sections are shown as no activity.
01
Ask
You name the repository and a lookback period.
02
Read
It reads commits, issues opened and closed, and workflow runs.
03
Group
It counts commits by author, groups them into themes and works out CI success rates.
04
Report
You get headline numbers, themes, notable issues and CI health.
What PopdockAI provides
The tools behind the answer
Ready made tools for GitHub and one secure connection to your AI tool. No code, no exports.
github-get-commit
github-get-issue
github-get-workflow-run
This report is built from Get data tools only. PopdockAI applies the row, field and parameter rules your admin sets, and every query is written to the audit trail.
The outcome
A two minute picture of the week
Related use cases
More ways to put this data to work
Check a GitHub deploy for Ghost Inspector regressions
Ask your AI to check a GitHub deploy for regressions and it compares Ghost Inspector results before and after the run, details each regression and lists the commits shipped.
Learn More
Report a failed GitHub workflow as an issue
Ask your AI to report a failed GitHub workflow and it confirms the failure, gathers the streak and suspect commit, and comments on an existing issue or opens one after you confirm.
Learn More
Diagnose failed GitHub workflow runs
Ask your AI to diagnose failed GitHub workflow runs and it finds the last success and breaking commit for each workflow and branch, labelling flaky and fixed ones.
Learn More
Cancel stuck GitHub workflow runs
Ask your AI to find stuck GitHub Actions runs and it lists old queued or running ones, flags superseded runs and deploys, and cancels only the runs you approve.
Learn More
Check a GitHub deploy for new Bugsnag errors
Ask your AI to check a GitHub deploy for new Bugsnag errors and it matches the run's commit to Bugsnag releases and lists errors first seen after each, with a verdict.
Learn More
One prompt template with infinite possibilities.
Your AI assistant adapts its approach, tone, and capabilities to match each unique context while you maintain a single, manageable workflow.
Join forward-thinking companies that are transforming their operations with intelligent, secure AI automation.