Org learning: correction mining → proposed skill, directive and routine diffs

未关闭
#166 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
35/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
typescript

调研方向

The issue describes weekly correction mining from the Ledger and approval-gated Inbox proposals, but names no implementation files or tests. Start by reading the related roadmap items and issues #117, #132, #133 and #138, then locate the Ledger, Inbox and agent-instruction versioning entry points. Done means three similar rejections produce a proposal with linked evidence, and approval versions the agent instructions.

由索引模型根据 Issue 内容生成。

描述

area:agents area:memory needs-triage p2 type:feature

Part of #117 · beat-Paperclip spec id E14

  • Priority: p2
  • Labels: type:feature, area:memory, area:agents
  • Relates to: #117 (#132, #133), #138
  • Scope: Paperclip's roadmap ⚪ items "Automatic Organizational Learning" and "Self-Organization" are unstarted. Weekly, Muster clusters human corrections, rejected diffs and repeated review notes from the Ledger. It proposes instruction, skill, routine or reporting-line diffs as Inbox items with evidence links. Nothing applies without approval.
  • Acceptance: Given 3 similar review rejections, a proposal appears with the 3 receipts linked. Approving it versions the agent instructions.

Source: Paperclip issue/discussion research (docs, GitHub issues, live instance).

主要语言
TypeScript
星标
3
派生
0
平均合并
17 小时 33 分钟
30 天内合并 PR
163

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

musterhq/muster-code 的其他 Issue

查看 musterhq/muster-code 的全部 Issue

相似的 Issue

更多 TypeScript Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。