Export Cleanup Auditor

The problem

Public API surfaces grow organically until you no longer know what is safe to delete. Stale exports and orphaned modules bloat your package size and increase the maintenance burden of your next major version.

What it does

• Identifies the package boundary using package.json, pyproject.toml, or go.mod.
• Scans the entire repository using ripgrep to map internal versus external usage of every export.
• Categorizes code into Dead, Internal-only, Public & used, or Public but undocumented.
• Generates a structured cleanup plan with risk assessments for SemVer compliance.
• Verifies that deletions won't break the build or existing test suites.

Why this beats prompting it yourself

Manual grepping is error-prone and misses edge cases like string-based dynamic imports or type-only references. This skill automates the cross-referencing logic and applies a systematic risk-grading framework that ensures you don't accidentally ship a breaking change in a minor release.

Use cases

• Pre-release audits to slim down a library before a major SemVer bump.
• Identifying "internal-only" utilities that were accidentally exposed to the public API.
• Finding dead code left over from refactors that eslint or pyright missed.
• Mapping undocumented public functions that need tests or deprecation notices.

Known limitations

Not for performance profiling or style linting. Best results require running on a clean branch without work-in-progress code.