AutoGineer
Generated banner for Convex Improve Convex Plugin
Generated logo for Convex Improve Convex Plugin

Convex Improve Convex Plugin

ConvexOfficialPublished by Convex

  • Skill
  • Workflow
  • Software development
  • Apache-2.0
  • Medium risk
Download ZIP

From the author

Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system. Run only when the user explicitly asks.
— the description by Convex

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill facilitates a feedback loop for the Convex quickstart system by sending session transcripts to an AI-driven review endpoint. It is designed to identify patterns of agent failure, ambiguous instructions, and tooling issues to improve future development experiences. The process is strictly opt-in, requiring explicit user consent before any data is transmitted, and includes automated redaction of sensitive information.

What it does

  • Triggers a transcript submission process for AI-based post-mortem analysis.
  • Handles user consent requirements for data sharing.
  • Identifies system-level issues such as agent-stuck patterns and tooling failures.
  • Summarizes high-severity findings including suggested fixes and system wins.
  • Redacts secrets and tokens from transcripts before transmission.

When to use it

  • When you want to contribute to the improvement of the Convex quickstart system.
  • After completing a coding session where you encountered agent-related friction or tooling issues.
  • When you wish to provide structured feedback on the effectiveness of the current development workflow.

Advantages

  • Directly contributes to the refinement of agent workflows and system documentation.
  • Ensures privacy through mandatory opt-in consent and automated secret redaction.
  • Provides actionable insights based on real-world coding session data.
  • Focuses on system-level improvements rather than end-user data.

Usage examples

“Can you send this session's transcript to the Convex team for a post-mortem?”
The agent initiates the transcript submission process, checks for consent, and provides a summary of the system findings once the review is complete.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/convex/convex-improve-convex-plugin/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip convex-improve-convex-plugin.zip -d .agents/skills

Documentation by Convex

<!-- GENERATED from convex-agents content/capabilities/improve-convex-plugin.json — do not edit by hand. -->

improve-convex-plugin

Sends the current coding session transcript to the anteater POST /review endpoint for an AI post-mortem. The review returns structured findings (ambiguous instructions, agent-stuck patterns, tooling failures, wins) targeted at the runbook, bootstrap script, skills, and components — not end-user data. Sharing is opt-in: the anteater-served helper asks once (Always / Just this once / Never) and remembers the choice.

Workflow

  1. Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".

  2. If it prints CONSENT_REQUIRED (exit 4), the user has not chosen yet — ask them to share Always, Just this once, or Never, then re-run appending --consent always|once|never. Do not send until they answer.

  3. Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=... (accepted), REVIEW_DONE status=done (findings ready).

  4. Summarize the highest-severity findings for the user: title → target → suggestedFix, then wins. Keep the summary about the system, not the user's data.

Rules

  • Never send a transcript until the user has explicitly chosen to share (the helper prints CONSENT_REQUIRED and exits until they do).

  • REVIEW_NO_TRANSCRIPT means no Claude/Codex .jsonl was found — tell the user.

  • Never paste raw secrets back — the script redacts keys/tokens before upload; keep the summary system-focused.

  • This is a system-improvement loop, not end-user feature feedback.

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

What our scanner noticed· Medium risk

  • Downloads piped into a shell

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Convex
Publisher
Convex (Official)
Source
convex/agent-skills · skills/convex-improve-convex-plugin · commit f60629d
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Convex or Convex.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download convex-improve-convex-plugin.zip