How do I install the Improve Convex Plugin skill?

Run npx skillmds@latest add get-convex/improve-convex-plugin in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Improve Convex Plugin safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Improve Convex Plugin?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Improve Convex Plugin free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Improve Convex Plugin?

get-convex (@get-convex) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Improve Convex Plugin by get-convex

Name: Improve Convex Plugin
Rating: 4.5 (4 reviews)
Author: get-convex

Improve Convex Plugin

Send THIS Codex session's transcript to the Convex quickstart backend for an AI post-mortem that improves the whole system (runbook, bootstrap, skills). TRIGGER when the user runs $improve-convex-plugin, or after a quickstart build says 'send feedback', 'report how that went', or 'help improve the quickstart'.

get-convex 7ddbc40 1.6 KB Updated Sep 10, 2026

File contents

Send session for review ($improve-convex-plugin)

Ships the current Codex session transcript to anteater's /review endpoint, which runs an AI post-mortem and returns concrete findings to improve the runbook / bootstrap / skills. The user's text after $improve-convex-plugin is an optional note about how the run went (pass it as --idea).

Run it (QB_HARNESS=codex tells the helper to read the Codex transcript):

curl -fsSL "https://basic-anteater-667.convex.site/send-transcript" \
  | QB_HARNESS=codex bash -s -- --idea "<the user's note, or the app idea>"

Read the output:

REVIEW_DONE status=done → summarize for the user: overall outcome + summary, then the top findings by severity (each: title → target → suggestedFix), then the wins. Keep it about the system, never paste back secrets (the helper already redacts).
REVIEW_PENDING → it was submitted; the review is still running. Tell the user it's queued (the printed /review/<id> can be re-checked).
REVIEW_NO_TRANSCRIPT / REVIEW_TRANSCRIPT_TOO_SMALL → no Codex transcript found; tell the user.
REVIEW_UPLOAD_FAILED → the endpoint was unreachable (network/sandbox) — report it.

Frequently asked questions