首页/AI 技能平台与生态/convex-improve-convex-plugin
C

convex-improve-convex-plugin

by @convexv
4.7(120)

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。

agent-feedbacksession-transcriptpost-mortemconsentskill-improvementGitHub
安装方式
npx skills add https://github.com/convex/agent-skills --skill convex-improve-convex-plugin
compare_arrows

Before / After 效果对比

1 组
使用前

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。

使用后

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。

SKILL.md

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.

用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价

统计数据

安装量45.4K
评分4.7 / 5.0
版本
更新日期2026年11月21日
对比案例1 组

用户评分

4.7(120)
5
37%
4
43%
3
13%
2
5%
1
2%

为此 Skill 评分

0.0

兼容平台

🤖claude-code

时间线

创建2026年10月17日
最后更新2026年11月21日
🎁 Agent 知识卡片
调研问卷