Skip to content
Get packs

Convex App Optimizer

Audit an existing Convex app, then plan and apply upgrades and observability fixes after your confirmation.

Source Download skill
Repository
openclaw/clawhub
Stars
9,546
Licence
MIT
Files
1 file

What it does

When installed, the agent follows a fixed workflow for an existing Convex app (a backend platform for web apps). It first detects the project, then runs a scored assessment by delegating to a separate launch-readiness skill, checks whether the Convex components the app depends on are out of date, and offers to set up production error monitoring if it is missing. It presents one prioritized plan with security and data-loss issues first, and only changes files after you explicitly confirm. After applying fixes, it re-runs the assessment and shows how the score changed.

Great for

  • Developers who inherited or maintain a Convex app and want a prioritized cleanup plan
  • Teams preparing a Convex app for launch who want upgrades and error monitoring handled in one pass

Skip it if

  • Apps you cannot afford to change: the skill can modify files after confirmation, so it is risky for live production code without review and a backup or version control. Reason: it is designed to act on code.
  • Projects that are not Convex: the workflow depends on Convex conventions such as the convex/ directory and @convex-dev components, so it will not help elsewhere.
  • Anyone expecting a standalone audit: the assessment itself is delegated to launch-readiness and sentinel and check-updates are referenced but not included in this skill's files, so those parts may not work unless those skills are also installed.

Try asking

  • “Audit and optimize my existing Convex app before we launch”
  • “Check whether my @convex-dev components are out of date and plan upgrades”
  • “Set up production error monitoring for my Convex project and show me the plan first”
  • “Re-run the readiness assessment after the fixes and show the score change”
Step-by-step guide: how to use Convex App OptimizerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    convex-optimize.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip convex-optimize.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip convex-optimize.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review the plan before confirming, and make sure your project is under version control so changes can be reverted.
  • Install the referenced companion skills (launch-readiness, check-updates, sentinel) or the workflow will not complete as described.
  • Run it on a development branch first, then compare the before and after scores before applying to production.

What's inside

  • SKILL.md

Redistributed unmodified from openclaw/clawhub under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.