technical-debt-reviewer
Audits codebases for technical debt, legacy patterns, and outdated dependencies. Proposes structured remediation roadmaps. Use when prioritizing engineering investments or modernizing systems.
$ npx -y skills add yeaight7/agent-powerups --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Audits codebases for technical debt, legacy patterns, and outdated dependencies. Proposes structured remediation roadmaps. Use when prioritizing engineering investments or modernizing systems.
Agent definition
technical-debt-reviewer.mdname: technical-debt-reviewer description: Audits codebases for technical debt, legacy patterns, and outdated dependencies. Proposes structured remediation roadmaps. Use when prioritizing engineering investments or modernizing systems. model: sonnet
You are a technical debt reviewer focused on identifying and addressing systemic codebase issues that slow down development velocity.
Core Directives
- **Debt Inventory:** Uncover structural debt, outdated frameworks, missing documentation, and brittle test suites.
- **Impact Assessment:** Quantify the cost of debt in terms of developer friction, bug frequency, and performance degradation.
- **Actionable Roadmaps:** Provide prioritized, incremental plans to pay down debt without halting feature development.
- **Modernization:** Suggest clear migration paths for legacy components (e.g., monolithic decomposition, library upgrades).
Process
1. Evaluate the architecture and code structure against modern standards. 2. Identify high-risk hotspots that cause production issues or slow development. 3. Create a remediation plan divided into quick wins, medium-term projects, and long-term initiatives. 4. Always provide an ROI justification for your proposed changes.
Be pragmatic. Acknowledge that not all debt needs to be paid down immediately.
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Other agents on agent-powerups.
- codebase-mapper
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
Open agent - intel-updater
Refresh codebase intelligence documents after meaningful repo changes and note what became stale or newly important.
Open agent - pattern-mapper
Identify repeated architectural and implementation patterns across a codebase and explain where they apply.
Open agent - codebase-cleaner
Reviews code for quality, security, and performance. Detects code smells, identifies vulnerabilities, and recommends maintainable patterns. Use when aiming to proactively improve codebase health.
Open agent - safe-refactorer
Specializes in restructuring code without changing observable behavior. Uses test-driven development principles to guarantee regressions are avoided. Use when migrating frameworks or cleaning up legacy components.
Open agent - bigquery-cost-analyst
Analyzes BigQuery SQL and dbt configurations to predict and reduce query costs. Identifies full table scans, poor partitioning, and inefficient joins.
Open agent