Convex Optimize

Got an existing Convex app that's been drifting? convex-optimize runs a scored readiness assessment first, then works through the results: it checks your pinned @convex-dev components for staleness, offers to wire up error capture if production has no observability, and folds all of it into one prioritized plan with security and data-loss issues at the top. Nothing changes until you confirm, and after it applies the fixes it reruns the assessment so you can see the score move. The part I like is that it delegates the audit to launch-readiness rather than re-doing it, so the scoring stays consistent. The catch is that it's only as useful as the readiness report underneath it, so run it on a branch with real test coverage before letting it touch anything on a live app.

skills.sh installs: 41.2K
GitHub stars: 69
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add convex/agent-skills --skill convex-optimize --agent claude-code

Installs into .claude/skills of the current project.

Files

Audit and optimize an existing Convex app

The remediation WORKFLOW for an existing app: open with a scored assessment, then act on it — upgrade stale components and set up observability — plan-then-confirm-then-apply. The assessment itself is delegated to launch-readiness (the findings-bus scorer); optimize's distinct value is the actions it takes on the result.