triage-issues

Categorize bugs and enhancements using a structured state machine for issue triage.

4|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/leocosta/octopus --skill triage-issues-leocosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triage-issues
Source: https://github.com/leocosta/octopus/tree/main/skills/triage-issues
Command: npx skills add https://github.com/leocosta/octopus --skill triage-issues-leocosta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Move issues through a disciplined state machine to reduce triage time and preserve context, ensuring AI-assisted triage remains transparent and auditable.

Core Features & Use Cases

  • Move issues through states: needs-triage, needs-info, ready-for-agent, ready-for-human, and wontfix with clear exit criteria.
  • Read context: pull issue body, comments, related ADRs, and .out-of-scope entries to determine next steps.
  • Preserve grilling notes: retain established information when escalating to agents and humans.
  • Output actionable hand-offs: provide concise acceptance criteria and relevant files for agents.

Quick Start

Provide the issue body and related comments to the triage-issues skill and ask it to assign a recommended category and starting state.

Frequently Asked Questions about triage-issues

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

FAQPage Schema
How do I automate GitHub issue triage with a state machine?

Automated GitHub issue triage applies a structured state machine to categorize bugs and enhancements, moving them through states like needs-triage, needs-info, and ready-for-agent with clear exit criteria and rationale.

What is the best way to preserve context when escalating GitHub issues to AI agents?

Preserve context during issue escalation by retaining grilling notes in the needs-info state, ensuring AI-assisted triage remains transparent and auditable while providing concise acceptance criteria for agents.

Can I use this state machine triage for both GitHub issues and pull requests?

Yes, the state machine triage works on both issues and pull requests in repositories, reading issue bodies, comments, related ADRs, and out-of-scope notes to determine next steps across AFK and human-in-the-loop scenarios.

How do I categorize incoming GitHub bugs versus enhancements automatically?

Categorize incoming bugs and enhancements automatically by pulling issue context and applying enforced state transitions, which outputs ready-to-apply labels with clear rationale for each categorized issue.

What are the limitations of using a state machine for issue triage?

State machine issue triage requires providing the issue body and related comments to determine categories and states, and relies on templates and out-of-scope notes to accurately enforce transitions and determine wontfix outcomes.