Convex Launch Readiness

Before you ship a Convex app, this skill runs the authz, reviewer, advisor, and insights audits together and collapses their output into one scored readiness report. Findings are deduped by function or table identity, so a missing index flagged from the code and its read-limit symptom flagged from the live deployment count once, not twice. The score is auditable: it starts at 100, subtracts per confirmed finding by severity, and prints the formula, while unconfirmed "plausible" findings are listed but don't move the number. It also tells you which passes were skipped, which matters because a code-only run yields a code-only score. It doesn't fix anything itself; it hands you an ordered punch list and dispatches to the fixer skills on request. My take: the skipped-pass labeling is the part I'd trust most, since a green number on a half-run audit is the usual way launch checks fail.

skills.sh installs: 41K
GitHub stars: 69
last updated: Oct 26, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Launch-readiness report

Readiness is not one check — it's the union of the checks, deduped, ranked, and scored. This capability is pure composition over the findings bus (specs/finding.schema.json): it runs each audit capability, normalizes their outputs into one report (specs/finding-report.schema.json), computes an auditable score, and — because every finding names a fixCapability — hands the user a prioritized, actionable punch list instead of four separate reports. It fixes nothing itself; it decides WHAT to fix and in what order, then dispatches to the fixers.