Technical Debt Assessment

The technical-debt-assessment skill enables AI agents to analyze codebases and documentation to identify areas requiring refactoring, outdated dependencies, or architectural inefficiencies. It generates structured reports highlighting specific risks and potential impacts on future development velocity.

When to use it

• Before starting a major feature sprint to ensure the existing foundation is stable enough for new work.
• During code reviews to flag legacy patterns that might slow down current team members.
• When planning a migration strategy to understand the scope of technical debt in a monolithic system.
• To prioritize maintenance tasks against upcoming release deadlines based on risk analysis.

Key capabilities

• Scans source code for anti-patterns and complexity indicators.
• Identifies deprecated libraries and unmaintained dependencies.
• Evaluates architectural decisions against current best practices.
• Quantifies the estimated effort required to resolve identified issues.

Example prompts

• "Analyze this repository's src directory and list the top five technical debt items that pose the highest risk to our upcoming authentication overhaul."
• "Review the project's dependency tree and generate a report on any packages with critical security vulnerabilities or zero stars on GitHub."
• "Assess the current database schema for normalization issues and suggest specific refactoring steps to improve query performance."

Tips & gotchas

Ensure the AI agent has read access to all relevant repositories and documentation before running an assessment, as context gaps lead to incomplete findings. While the skill identifies problems effectively, it cannot execute the refactoring itself; human engineers must validate and implement the suggested fixes.