aped-triage

Classify and route incoming issues through a structured triage state machine.

2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yabafre/aped-claude --skill aped-triage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aped-triage
Source: https://github.com/yabafre/aped-claude/tree/main/src/templates/skills/aped-triage
Command: npx skills add https://github.com/yabafre/aped-claude --skill aped-triage

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents inconsistent issue handling by forcing structured intake, evidence-backed classification, and scope-verified routing before any fix, deferment, or closure.

Core Features & Use Cases

  • Evidence-first triage: Captures title, reporter, reproduction steps, evidence, and affected artefact, asking the user when any required field is missing.
  • Scope verification gate: Reads current phase and active epic artefacts from state files, deciding out-of-scope versus in-scope without assumptions.
  • Deterministic routing outputs: Emits a triage decision artefact for downstream skills and records deferred items into an out-of-scope knowledge base.

Quick Start

When a user says "triage this issue" and includes the issue title, reproduction (or why it’s not applicable), and any error logs or screenshots, tell me to run aped-triage and produce triage-decision.md plus any out-of-scope record if needed.

Frequently Asked Questions about aped-triage

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

FAQPage Schema
How do I triage issues with evidence and route them based on sprint scope?

Issue triage with evidence requires capturing reproduction steps and affected artefacts, then verifying sprint and epic scope before routing. A structured triage state machine classifies each issue and emits a decision artefact for downstream skills.

What is the best way to classify incoming bug reports and feature requests in a project backlog?

Classifying bug reports and feature requests requires evidence-first intake, reading pipeline phase and active epic file sets from state outputs, and applying scope verification to decide in-scope versus out-of-scope routing deterministically.

How do I handle out-of-scope issues during product backlog triage?

Out-of-scope issues identified during triage are recorded into an out-of-scope knowledge base artefact, deferring them from the active sprint while preserving the classification decision and evidence for future pipeline phases.

Can I triage regressions and duplicates without manually checking active epic files?

Triage for regressions and duplicates respects sprint and epic scope by automatically reading pipeline phase and active epic file sets from state outputs, enforcing missing-field prompts to ensure complete evidence before classification.

What happens if a bug report is missing reproduction steps or evidence during priority routing?

Missing reproduction steps or evidence trigger missing-field prompts that ask the user for required fields before classification proceeds, ensuring no issue is routed downstream without complete evidence and affected artefact details.