triage

Applies type, effort, priority, and area labels to GitHub issues.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/ChatGPT-KB/Archon-mirror --skill triage-chatgpt-kb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triage
Source: https://github.com/ChatGPT-KB/Archon-mirror/tree/main/.claude/skills/triage
Command: npx skills add https://github.com/ChatGPT-KB/Archon-mirror --skill triage-chatgpt-kb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.

Core Features & Use Cases

  • Isolated context via context: fork to keep triage work separate from the main chat
  • Delegates to a specialized triage agent with label validation hooks
  • Restricted tool access to GitHub and read-only codebase for safety

Quick Start

Use the skill to triage a specific issue by number, e.g., /triage 42.

Frequently Asked Questions about triage

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

FAQPage Schema
How do I automatically triage GitHub issues and apply labels for priority and effort?

You can automatically triage GitHub issues by running a specialized agent in an isolated forked context that applies type, effort, priority, and area labels with validation guardrails. This prevents polluting your main conversation with issue details.

What is the best way to keep issue triage details from cluttering my main chat context?

Keeping issue triage details separate is handled by running the triage agent in an isolated forked context. This ensures the main conversation stays clean while the agent processes issue details and applies taxonomy labels.

How do I add guardrails to validate GitHub labels before an agent applies them?

Adding guardrails to validate GitHub labels is achieved through a specialized prompt hook that enforces taxonomy before changes are applied. The triage agent operates with restricted tool access to ensure label safety.

Can I use a restricted tool environment to safely triage open issues in a repository?

Yes, you can safely triage open issues in a repository using a restricted tool environment. The triage agent accesses only GitHub and read-only codebase tools, ensuring controlled and safe label application.

How do I triage a specific GitHub issue by its number?

To triage a specific GitHub issue by its number, invoke the skill with the issue number as an argument. The agent will then analyze the issue in an isolated context and apply the appropriate taxonomy labels.