Audit beginner Works with: Any AI

GitHub Issue Backlog and Stale Item Audit

Table output Has example

• 🐙 GitHub

Find old issues, duplicates and missing information.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Audit the issue backlog. Export of open issues with title, labels, created date, last activity, comments and assignee: [ISSUE_EXPORT]. Our rules for staleness: [STALENESS_RULES].

Show age bands with counts and percentages and the arithmetic, for example 140 open issues of which 56 have had no activity for 90 days is 40 percent. Also count issues with no labels, no response, probable duplicates by title similarity (list the first ten pairs with the matching words and a confidence), and issues that are questions rather than bugs. Do not close issues on age alone; ask whether the problem still exists. Never close security reports or accepted roadmap items.

Recommend closing, merging, labelling or asking for information per group. Write three kind messages that invite reopening: a request for current information, a duplicate closure that links to the original, and a stale closure. Estimate about three minutes per issue for a two-hour clean-up and total it. Return a table and a plan.

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.

Invented export of 140 open issues. Age: under 30 days 36 (25.7 percent), 30 to 90 days 28 (20 percent), 90 to 180 days 24 (17.1 percent), over 180 days 52 (37.1 percent). No labels: 31. No response: 19. Probable duplicates: 11 pairs. Questions rather than bugs: 14.
Plan (2 hours): close the 11 duplicates with a link, redirect the 14 questions to discussions, ask for current information on the 52 oldest issues and close those with no reply after 14 days. Messages are friendly and invite reopening.

• github