From tech-debt-audit
Full codebase technical debt audit using 11 parallel specialized agents. Identifies dependency issues, code smells, architecture problems, test gaps, error handling flaws, performance bottlenecks, security vulnerabilities, documentation gaps, type safety issues, API inconsistencies, and over-engineering. Groups findings into actionable GitHub issues. Use when the user asks to audit the codebase, find tech debt, assess code quality, check for technical debt, or run a codebase health check.
npx claudepluginhub stilero/claude-plugins --plugin tech-debt-auditThis skill uses the workspace's default tool permissions.
This skill runs a comprehensive technical debt audit by spawning 11 specialized agents in parallel, each examining the codebase from a different angle.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
This skill runs a comprehensive technical debt audit by spawning 11 specialized agents in parallel, each examining the codebase from a different angle.
| Agent | Focus | Model |
|---|---|---|
| dependency-auditor | Outdated deps, CVEs, unused packages | haiku |
| code-quality-analyzer | Code smells, complexity, duplication, dead code | sonnet |
| architecture-reviewer | Circular deps, layer violations, pattern inconsistencies | sonnet |
| test-coverage-analyzer | Untested modules, test quality, integration gaps | sonnet |
| error-handling-auditor | Swallowed errors, missing error handling, resilience | sonnet |
| performance-analyzer | N+1 queries, missing indexes, unbounded queries | sonnet |
| security-scanner | Secrets, injection, validation, auth gaps | sonnet |
| documentation-auditor | Missing API docs, stale docs, missing ADRs | haiku |
| type-safety-auditor | any usage, unsafe assertions, strict mode gaps | sonnet |
| api-design-reviewer | Endpoint naming, pagination, error consistency | sonnet |
| complexity-reviewer | Over-engineering, unnecessary abstractions, YAGNI | sonnet |
When multiple agents flag the same area or pattern, severity is bumped one level:
Related findings are merged into single actionable issues:
any type → one issueRun /tech-debt-audit to start a full codebase audit. The command handles everything automatically — context gathering, agent spawning, aggregation, and reporting.