---
id: gh-convex-improve-convex-plugin
name: "convex-improve-convex-plugin"
url: https://skills.yangsir.net/skill/gh-convex-improve-convex-plugin
author: convex
domain: ai-skill-platform-ecosystem
tags: ["agent-feedback", "session-transcript", "post-mortem", "consent", "skill-improvement"]
install_count: 45400
rating: 4.70 (120 reviews)
github: https://github.com/convex/agent-skills/tree/main/skills/convex-improve-convex-plugin
---

# convex-improve-convex-plugin

> 此技能把当前编码会话的记录发送到 AI 复盘接口，自动生成结构化发现：指令歧义、智能体卡顿、工具故障与成功亮点，并全部指向 runbook、bootstrap 脚本与技能本身。适合在用户明确同意后，用真实开发过程沉淀系统改进建议，形成持续迭代的闭环；上传前自动脱敏密钥，不做终端用户数据反馈。

**Stats**: 45,400 installs · 4.7/5 (120 reviews)

## Before / After 对比

### 会话复盘从手工整理到自动生成

**Before**:

开发者遇到问题后只能凭记忆手动整理会话，逐条回想到底哪条指令含糊、智能体在哪里卡住，往往要花几十分钟，还容易漏掉关键细节，最终维护方拿到的反馈零散且难以复现。

**After**:

此技能自动抓取当前会话记录并生成结构化发现，按标题、目标与修复建议归档，指令歧义、卡顿模式、工具故障和亮点一目了然，维护方拿到的反馈完整且可直接落地。

| Metric | Before | After | Change |
|---|---|---|---|
| 反馈整理耗时 | 45分钟 | 5分钟 | -89% |
| 可执行改进项 | 2条 | 9条 | +350% |

## Readme

<!-- 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.


---
*Source: https://skills.yangsir.net/skill/gh-convex-improve-convex-plugin*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-convex-improve-convex-plugin/markdown*