Issue Triage

Automate GitHub issue triage with verdicts, deduplication, and label management.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill issue-triage-atrium-hermes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Issue Triage
Source: https://github.com/Atrium-Hermes/atrium-lighthouse/tree/main/skills/issue-triage
Command: npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill issue-triage-atrium-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Triage and prioritize new GitHub issues automatically by producing a decision-ready verdict and a concrete next action, reducing manual review time.

Core Features & Use Cases

  • Verdict-based triage: ACCEPT, NEEDS-INFO, DUPLICATE, or DECLINE to guide maintainer actions.
  • Deduplication and labeling: detects duplicates across issues, applies schema-safe labels, and posts concise triage comments.
  • Memory-aware workflow: tracks previously triaged issues to avoid re-processing and maintains per-repo budgets.

Quick Start

Run the triage workflow for your watched repos to automatically classify and respond to new issues.

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 new issues across multiple repositories?

Automating GitHub issue triage involves classifying new issues with verdicts like ACCEPT or NEEDS-INFO, applying schema-safe labels, detecting duplicates, and posting comments to guide maintainer actions without manual review.

What is the best way to prevent duplicate GitHub issues from being processed twice?

Preventing duplicate GitHub issues requires a memory-aware triage workflow that tracks previously triaged issues and performs deduplication across watched repositories to avoid re-processing and mislabeling.

Can I automatically apply labels to new GitHub issues without mislabeling them?

Automatically applying labels to GitHub issues requires schema-safe label handling that validates labels against repository schemas before applying them, preventing invalid or duplicate labels from being assigned during triage.

Does automated issue triage work with per-repo budgets to limit processing volume?

Automated issue triage supports per-repo budgets to control processing volume across watched repositories, ensuring that triage workflows maintain memory of processed issues and respect configurable rate limits per repository.

How do I classify GitHub issues into decision-ready categories for maintainers?

Classifying GitHub issues into decision-ready categories involves emitting concise verdicts such as ACCEPT, NEEDS-INFO, DUPLICATE, or DECLINE alongside a concrete next action comment to accelerate maintainer triage workflows.

What are the limitations of automated GitHub issue classification for large repositories?

Automated GitHub issue classification operates within per-repo budgets and relies on memory of triaged issues to prevent re-processing, meaning throughput is intentionally constrained to maintain label safety and avoid duplicate triage comments.