跳到技能内容
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
词映 AI导航
工具库Skills 技能
我的收藏
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
Skills directory/spurbey/agent-memory-orchestrator/amo-semantic-checkpoint

Codex AMO Semantic Checkpoint from Git and Test Evidence

Extract a small set of repository facts from a defined work window. Record anchors and evidence in structured JSON.

中文

Install in Codex

Codex with an agent-memory-orchestrator checkout, a defined checkpoint range, and local commits and tests.

  1. Copy the entire pinned `.codex/skills/amo-semantic-checkpoint/` directory to `.agents/skills/amo-semantic-checkpoint/` in the target checkout.
  2. Open Codex in that checkout and invoke `$amo-semantic-checkpoint` with the example task and desired output.

Example task

Invoke `$amo-semantic-checkpoint` with two fictional commits. Capture one fact about a cache output shape and one about its regression test.

What to check

The checkpoint contains verifiable anchors, evidence, and confidence for review.

Original SKILL.md on GitHub · Updated 2026-11-13

Frequently asked question

Can I include ideas for the next session as facts?

Keep facts within the defined window and its evidence. Track future ideas in planning notes.

Browse Codex skills in the Chinese directory
词映 AI 导航Skills 技能
工具分类全部工具已本地化技能选型指南AI 快讯