analyze

Analyze code repositories to identify likely causes of bugs and slowdowns.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/tuandzung/flink-k8s-ui --skill analyze-tuandzung
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze
Source: https://github.com/tuandzung/flink-k8s-ui/tree/main/.codex/skills/analyze
Command: npx skills add https://github.com/tuandzung/flink-k8s-ui --skill analyze-tuandzung

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides comprehensive, read-only analysis of repository codebases, offering grounded explanations, confidence levels, and clear evidence vs. inference boundaries.

Core Features & Use Cases

  • Deep Repository Analysis: Conducts in-depth code analysis across multiple files and boundaries.
  • Ranked Explanations: Presents potential explanations, ranked by evidence strength.
  • Explicit Confidence Levels: Provides confidence in each explanation based on evidence.
  • Evidence vs. Inference Distinction: Clearly differentiates between direct evidence and inferred conclusions.
  • Use Case: When troubleshooting an application issue, the skill can analyze code, configuration, and tests to identify the root cause.

Quick Start

Analyze the reasons for the recent application slowdown in the 'app' repository.

Frequently Asked Questions about analyze

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

FAQPage Schema
How do I find the root cause of an application slowdown using repository analysis?

Repository analysis identifies the likely causes of application slowdowns by examining code, configuration, and tests. It ranks potential explanations by evidence strength and provides explicit confidence levels for each identified issue.

What is evidence-based code analysis and how does it distinguish direct proof from inference?

Evidence-based code analysis differentiates between direct evidence found in the repository and inferred conclusions. This distinction ensures troubleshooting remains grounded in actual artifacts, providing clear boundaries for what is proven versus what is suspected.

How do I conduct a read-only code audit across multiple file boundaries?

You can conduct a deep code audit by granting read-only access to repository artifacts and documentation. The analysis traverses multiple file boundaries to deliver structured explanations suitable for architecture comprehension and troubleshooting.

Can I use this analysis approach for understanding complex codebase architecture?

Yes, this analysis approach is suitable for codebase architecture comprehension. It examines repository artifacts and documentation to deliver grounded explanations, making it effective for understanding complex structures and conducting thorough code audits.

Does repository troubleshooting require write access to modify code during analysis?

No, repository troubleshooting requires only read-only access to repository artifacts and documentation. The analysis operates without modifying code, ensuring the original state remains intact while identifying root causes and assessing confidence levels.