菜单
Drop the Second Brain's task ledger — one task's, or all of them. A ledger is derived state (goal, compaction notes, advisories, suppressions), so deleting one is always safe; a running task rebuilds from its next observations.
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/shofer-dev/shofer --skill second-brain-forget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。
正在显示 SKILL.md
基于 SOC 职业分类
| name | second-brain-forget |
| description | Drop the Second Brain's task ledger — one task's, or all of them. A ledger is derived state (goal, compaction notes, advisories, suppressions), so deleting one is always safe; a running task rebuilds from its next observations. |
Call the plugin request forget (plugin second-brain, params { taskId? } —
omit taskId to drop EVERY ledger). Confirm with the user before the drop-all
variant; per-task deletion needs no confirmation, it is always safe.
What is lost: the task-scoped judgment (goal, notes distilled from window compactions, delivered advisories and their outcomes, suppressed advice keys, budget spend). What is NOT lost: nothing else — the Second Brain holds no workspace-scoped state by design.