forge-diagnose

Diagnose runtime infrastructure issues across cloud and container environments.

69|8|Updated Mar 16, 2026

Search Tags:#devops #observability #cloud #infrastructure #reliability #diagnose #root-cause

Ready to run

npx skills add https://github.com/tonone-ai/tonone --skill forge-diagnose

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: forge-diagnose
Source: https://github.com/tonone-ai/tonone/tree/main/team/forge/skills/forge-diagnose
Command: npx skills add https://github.com/tonone-ai/tonone --skill forge-diagnose

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnoses runtime infrastructure issues across cloud and container environments to reduce MTTR and improve reliability.

Core Features & Use Cases

Symptom-driven diagnostics: identify latency, cold starts, timeouts, scaling bottlenecks, network failures, and resource exhaustion.
Diagnostic data gathering: detects cloud providers, IaC, deployed configurations to guide fixes.
Actionable remediation: suggests IaC-ready changes and runbooks to restore performance and stability.

Quick Start

Identify the current infra issues by scanning your cloud and container configs and report the top bottlenecks.

Frequently Asked Questions about forge-diagnose

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

FAQPage Schema

How do I diagnose cloud infrastructure latency and timeout issues?▼

To diagnose cloud infrastructure latency and timeouts, you scan deployed configurations and gather runtime diagnostics to identify bottlenecks. It detects cloud providers and IaC to guide targeted fixes for latency, cold starts, and network failures.

What is the best way to find the root cause of container scaling failures?▼

Finding the root cause of container scaling failures involves symptom-driven diagnostics that detect resource exhaustion and scaling bottlenecks. It scans your container environment configurations to pinpoint runtime constraints preventing proper scaling.

Does this diagnose infrastructure issues across multiple cloud providers?▼

Yes, it diagnoses infrastructure issues across multiple cloud providers by detecting deployed configurations and IaC during the diagnostic scan. This environment detection guides proposed remediation steps for your specific cloud and container setup.

How do I generate IaC-ready fixes for network failures and resource exhaustion?▼

You generate IaC-ready fixes for network failures and resource exhaustion by gathering diagnostic data from scanned configurations. It proposes actionable remediation changes and runbooks with verifiable steps to restore stability.

Can I use this for diagnosing cold starts in container environments?▼

Yes, you can use this for diagnosing cold starts in container environments. It applies symptom-driven diagnostics to identify cold start issues, scans your configurations, and suggests actionable remediation steps to resolve performance bottlenecks.