From devflow
Code quality checks applied while writing or editing code. Catches missing error handling, null safety issues, test gaps, naming problems, and language-specific anti-patterns. Use this skill whenever writing new code, editing existing code, generating implementations, fixing bugs, writing tests, or refactoring — even if the user doesn't explicitly ask for a review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/devflow:code-qualityThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When writing or editing code, check for these issues inline. Do not run
When writing or editing code, check for these issues inline. Do not run a separate review pass — apply these during generation.
Read .claude/devflow.yaml → languages.primary. Apply extra checks:
TypeScript/JavaScript:
any type without justificationawait or return the promisekey props in listsconsole.log in production pathsPython:
except: — catch specific exceptionsGo:
_ = err)defer cleanupRust:
.unwrap() only with a comment explaining why it's safe? where possibleDo NOT list issues separately. Fix them as you write. If you spot a problem in existing code adjacent to your changes, mention it but don't fix it unless asked — avoid scope creep.
npx claudepluginhub jdepotter/devflow --plugin devflowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.