kiro-debug

Investigate implementation failures to identify root causes and produce fix plans.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/manatago/gion --skill kiro-debug-manatago
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kiro-debug
Source: https://github.com/manatago/gion/tree/main/.claude/skills/kiro-debug
Command: npx skills add https://github.com/manatago/gion --skill kiro-debug-manatago

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps engineers and reviewers resolve blockers by guiding a root-cause-first investigation when builds, tests, validations, or reviewer feedback repeatedly fail and guess-first fixes are producing no convergence.

Core Features & Use Cases

  • Evidence-driven triage: Systematically gather error text, stack traces, failing commands, and git diffs to avoid premature patching.
  • Repository and runtime inspection: Check package manifests, build and runtime configs, dependency versions, and changed files to locate environmental or configuration gaps.
  • Targeted research and classification: Use focused web searches and documentation to classify the failure (e.g., MISSING_DEPENDENCY, RUNTIME_MISMATCH) and produce a minimal, verifiable fix plan.

Quick Start

Use kiro-debug with an exact failure summary, error output, git diff, and task brief to produce a concise root-cause report with a fix plan and verification steps.

Frequently Asked Questions about kiro-debug

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

FAQPage Schema
How do I find the root cause of a failing build or test?

To find the root cause of a failing build, systematically gather error text, stack traces, and git diffs. This evidence-driven triage approach inspects repository configurations and runtime environments to prevent premature patching.

What is the best way to debug code when fixes are not converging?

The best way to debug non-converging fixes is to halt guess-first patching and perform repository inspection. Check package manifests, build configs, and dependency versions to identify environmental gaps causing the repeated failures.

Why does my integration fail after reviewer feedback, and how do I classify the issue?

Integration failures after reviewer feedback often stem from runtime mismatches or missing dependencies. Classify the issue by combining targeted web research with documentation to categorize the failure and produce a verifiable fix plan.

Can I use repository inspection to triage incident response blockers?

Yes, you can use repository inspection to triage incident response blockers by examining changed files and dependency versions. This process isolates configuration gaps and generates a minimal repo-fix plan with verification commands.

Do I need exact error output and git diff to investigate implementation failures?

Yes, providing exact failure summaries, error output, git diff, and task briefs is required. This evidence-driven triage ensures the investigation classifies the root cause accurately and produces concise verification steps.