Issue Triage

Triage GitHub issues into verdicts and next actions with gh queries.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill issue-triage-anajuliabit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Issue Triage
Source: https://github.com/anajuliabit/aeon/tree/main/skills/issue-triage
Command: npx skills add https://github.com/anajuliabit/aeon --skill issue-triage-anajuliabit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates slow, repetitive maintainer triage by automatically classifying each new GitHub issue into a clear verdict and a concrete next action.

Core Features & Use Cases

  • Decision-ready verdicts: Produces one of ACCEPT, NEEDS-INFO, DUPLICATE, or DECLINE with an appropriate comment and labels.
  • Duplicate detection first: Detects likely duplicates using title/body overlap and identifying-string matches, and closes only when high-confidence.
  • Schema-safe labeling: Fetches and caches repo label definitions, creates missing labels with sensible defaults, and avoids re-triaging issues already labeled or recorded in memory.
  • Maintainer-friendly outcomes: Suggests reviewer context when possible via CODEOWNERS or recent authors and supports a run budget per repo.

Quick Start

Ask an AI agent to run Issue Triage for a specific repository by setting var to "owner/repo", or leave var empty to triage all watched repos defined in memory/watched-repos.md.

Frequently Asked Questions about Issue Triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate GitHub issue triage for my repository?

To automate issue triage, this Skill classifies new GitHub issues into verdicts like ACCEPT, NEEDS-INFO, or DUPLICATE, then posts a comment and applies appropriate labels to reduce manual maintainer workload.

How does duplicate detection work for GitHub issues?

Duplicate detection works by comparing title and body overlap plus identifying-string matches against a memory file of triaged issues, closing duplicates only when high-confidence matches are found.

Can I automatically label new GitHub issues without creating conflicts?

Yes, you can automatically label issues safely because the Skill fetches and caches existing repo label definitions, creates missing labels with sensible defaults, and avoids re-triaging issues already labeled or recorded in memory.

What is the best way to manage issue intake across multiple watched repos?

The best way to manage intake across multiple watched repos is reading targets from a watched-repos memory file, applying classification and duplicate detection per repo while respecting a configured run budget.

How do I stop slow, repetitive maintainer workflows for recurring repository issue intake?

You stop repetitive maintainer workflows by running automated issue triage that emits decision-ready verdicts and concrete next actions, suggesting reviewer context via CODEOWNERS or recent authors to streamline intake.