debug-agent

Diagnose pipeline failures from logs, work items, or issue URLs.

298|70|Updated Nov 4, 2020
One-click install
npx skills add https://github.com/microsoft/powerplatform-build-tools --skill debug-agent-microsoft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug-agent
Source: https://github.com/microsoft/powerplatform-build-tools/tree/main/.claude/skills/debug-agent
Command: npx skills add https://github.com/microsoft/powerplatform-build-tools --skill debug-agent-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose pipeline failures and customer issues end-to-end by ingesting a log path, error text, ADO work item ID, or GitHub issue URL.

Core Features & Use Cases

  • Ingests inputs from logs, work items, or issue URLs to determine failure context.
  • Identifies ownership, triages PPBT-owned tasks, and surfaces a precise triage package for the correct team.
  • Works autonomously across the PPBT workflow, pausing to request missing logs or evidence as needed.

Quick Start

Invoke as: /debug-agent <log-file-path | error-text | issue-url | ado-id>.

Frequently Asked Questions about debug-agent

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

FAQPage Schema
How do I diagnose a pipeline failure from a log file or error text?

To diagnose a pipeline failure, you can ingest a log file path, error text, ADO work item ID, or GitHub issue URL. The system determines failure ownership, resolves PPBT-owned tasks, or generates a precise triage package for the correct team.

Can I triage a GitHub issue or ADO work item automatically?

Yes, you can triage a GitHub issue or ADO work item automatically by providing its URL or ID. The system analyzes the input to identify ownership and produces a triage package routing the failure to the correct team.

What is the best way to determine ownership of a customer issue end-to-end?

Determining ownership of a customer issue end-to-end involves ingesting the error text or logs to classify the failure layer. The system identifies the correct team, resolves the issue if PPBT-owned, or surfaces a precise triage package.

Does the debug agent work when missing logs are needed to classify the failure layer?

Yes, the debug agent works autonomously across the PPBT workflow and can pause to request missing logs or evidence when needed to accurately classify the failure layer before determining ownership.

What inputs do I need to start diagnosing pipeline failures?

To start diagnosing pipeline failures, you need one of the following inputs: a log file path, error text, ADO work item ID, or GitHub issue URL. The system loads context from these inputs to begin the end-to-end diagnosis.