菜单
Use when a loop or long-running task must persist factual state, decisions, evidence, blockers, or next actions outside model context
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/cvsz/zaff --skill persistent-memory命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when executing approved implementation or operational plan steps that mutate files, services, repositories, or external state
Use when an agent loop, long-running task, or multi-agent workflow needs explicit budget, context, retry, or escalation control
Use when requirements must become a finite executable plan with acceptance criteria, validation, rollback notes, and stop conditions
正在显示 SKILL.md
| name | persistent-memory |
| description | Use when a loop or long-running task must persist factual state, decisions, evidence, blockers, or next actions outside model context |
Maintain durable factual project memory across loop runs.
At each stage transition, persist current state, decisions, attempts, results, blockers, and next action. Compact superseded information. Never store secrets or private reasoning.
Durable state record and concise memory update.
