modules/programs/agents/shared/skills/cleanup/SKILL.md
Audit codebase for tech debt and improvements
npx skillsauth add MichaelVessia/nixos-config cleanupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Audit the codebase for technical debt, code smells, and improvement opportunities.
Identify tech stack from package.json, tsconfig.json, etc.
Search for debt markers:
# Comments
rg -n "TODO|FIXME|HACK|XXX|BUG|WARN" -t ts -t js src/
# Linter disables
rg -n "eslint-disable|biome-ignore|prettier-ignore|oxlint-ignore" -t ts -t js src/
Search for type safety violations (high priority):
# TypeScript directive escapes
rg -n "@ts-ignore|@ts-expect-error|@ts-nocheck" -t ts src/
# Type assertions (as Type) - should use type guards or proper typing
rg -n " as [A-Z]| as any| as unknown" -t ts src/
# Non-null assertions (!) - should use proper null checks
rg -n "!\.|!\[|!;|!\)|!," -t ts src/
# Explicit any types - should use proper types or unknown
rg -n ": any|<any>|any\[\]" -t ts src/
Check for common issues:
console.log left in code (not in dev/debug files)Framework-specific checks:
Pattern violations:
Create a report organized by category:
For each item include:
Ask if you should:
bd create)development
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.
development
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
development
Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
testing
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.