Stale Pull Requests and Issues Backlog Triage
Classify open pull requests and issues into close, revive, split or escalate, so your GitHub backlog becomes a short honest list.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.
My repository [REPO_NAME] has a backlog of open pull requests and issues that nobody looks at. I will paste a list with number, title, author, labels, created date, last activity date and comment count: [BACKLOG_LIST]. Today's date is [TODAY]. Our rule of thumb for stale is [STALE_RULE]. Current goals for the next quarter: [QUARTER_GOALS]. Classify each item as: Close with thanks, Ask for an update, Revive and assign, Split into smaller pieces, Escalate to a maintainer, or Keep as is. Show a table with the columns Number, Title, Age in days, Days since activity, Class and Reason, calculating the ages explicitly. Then give counts per class and the percentage of the backlog that is stale. Provide a friendly comment template for each of two cases: a stale pull request and a stale issue, each under 60 words, which tells the author what happens next and when. Use only the pasted information. Do not guess whether a bug is still present. Any item tied to security, data loss or a paying customer goes to Escalate regardless of age. Do not close or comment automatically; I will review your table first. Bot and label automation options depend on our GitHub plan and setup, so mark them [VERIFY]. Keep the tone kind, because contributors are often volunteers.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.