From personal-skills
Architecture smell scan when the user explicitly asks for refactor targets, deep-module candidates, or an architecture review. HTML report in OS temp; stop after report unless the user picks a candidate.
How this skill is triggered — by the user, by Claude, or both
Slash command
/personal-skills:improve-codebase-architectureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Surface architectural friction and deepening opportunities — shallow modules worth refactoring for testability and navigability.
Surface architectural friction and deepening opportunities — shallow modules worth refactoring for testability and navigability.
User must request this scan explicitly. Do not publish issues unless asked.
Use codebase-design vocabulary (module, interface, depth, seam, adapter, leverage, locality) in every suggestion.
Read the repo glossary and architecture spine named in root or nested AGENTS.md (for ABB: docs/ubiquitous-language.md, docs/system-map.md). Respect docs/DECISIONS.md or docs/adr/ — surface ADR conflicts only when friction warrants reopening.
Read domain glossary and decision notes for the touched area. Walk the codebase and note friction:
Apply the deletion test on suspected shallow modules.
Write a self-contained HTML file to OS temp: <tmpdir>/architecture-review-<timestamp>.html. Open it for the user and give the absolute path.
Each candidate card: Files, Problem, Solution, Benefits, Before/After diagram, Recommendation strength (Strong | Worth exploring | Speculative).
End with Top recommendation.
Use domain vocabulary from the repo glossary and architecture terms from codebase-design.
See HTML-REPORT.md for scaffold and styling.
Do not propose interfaces yet. Ask which candidate to explore.
Use grill-me or repo alignment skill when capture is next. Propose glossary or decision-note updates only when the user asks. Use codebase-design DESIGN-IT-TWICE.md for interface alternatives.
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
npx claudepluginhub allmight97/agents --plugin personal-skills