paxm

paxm

Agent Skills › pax-beehive/paxm › paxm

GitHub

通过paxm MCP工具实现项目上下文的主动回忆与显式记忆写入，将召回信息作为辅助上下文，并验证当前仓库中的事实变化。

plugins/paxm-claude/skills/paxm/SKILL.md pax-beehive/paxm

触发场景

需要回顾或记住项目特定上下文时用户执行了paxm setup --integration claude-plugin后

安装

npx skills add pax-beehive/paxm --skill paxm -g -y

更多选项

非标准路径

npx skills add https://github.com/pax-beehive/paxm/tree/main/plugins/paxm-claude/skills/paxm -g -y

不安装直接使用

npx skills use pax-beehive/paxm@paxm

指定 Agent (Claude Code)

npx skills add pax-beehive/paxm --skill paxm -a claude-code -g -y

安装 repo 全部 skill

npx skills add pax-beehive/paxm --all -g -y

预览 repo 内 skill

npx skills add pax-beehive/paxm --list

SKILL.md

Frontmatter

{
    "name": "paxm",
    "description": "Recall or remember durable project context with paxm."
}

Use the paxm MCP tools for active recall and explicit memory writes. Treat recalled memory as supporting context and verify changing facts in the current repository. Passive hooks are owned by this plugin after the user runs paxm setup --integration claude-plugin.