convex-improve-convex-plugin

该 Skill 通过 curl 管道执行 anteater 服务提供的脚本，把当前编码会话转录提交到 POST /review 端点做 AI 复盘，返回结构化发现（指令歧义、代理卡住模式、工具失败、成功经验），面向 runbook、引导脚本、Skill 与组件而非终端用户数据。分享为显式选择制：脚本先询问并记住选择，未选择前不发送。

convex

热度 0.00

最近更新 2026-10-18 16:51:30

分类：自动化依赖：代码执行 / 第三方 API应用场景：自动化脚本 / 工作流 / 摘要总结 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add convex/agent-skills/convex-improve-convex-plugin

Metadata

name: convex-improve-convex-plugin
description: 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.

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

Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".
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.
Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=... (accepted), REVIEW_DONE status=done (findings ready).
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.