Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones — informed by the project's domain language and its binding decision records, then grill through whichever one the human picks. Use when an area has become hard to change or hard to test, or when the user asks to improve architecture, consolidate tightly-coupled modules, or make a codebase more navigable.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is improve-codebase-architecture in agranado2k/google-books-clojure
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow has the agent explore the local repository, including its commit history, comments, fixtures, and vendored files (SKILL.md Step 1), which may contain text from outside contributors or third-party sources. The agent does not search or fetch external content, so this is low rather than medium.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.