memory-hygiene
仓库创建 2026年6月6日最近提交 21 天前SkillHot 收录 20 天前
▸ 精选理由
自动识别低价值、重复或冲突记忆,提升长期可靠性。
这个 Skill 做什么
判定与整理 RECALL 记忆质量并规划清理与路由策略。
在判断信息该存到本地 Recall(.recall/)、写进 repo 文档、放进技能/插件说明、记到 provider 配置还是只留在当前会话时用。还能发现并规划清理陈旧、重复、冲突或低价值的记忆,给出安全的非破坏性清理与路由策略。适合在大规模记忆变动前做质量策略评估;注意不要把秘密或凭证写入 RECALL,它是记忆质量的政策大脑。
▸ 展开 SKILL.md 英文原文
Use this skill when deciding whether candidate context belongs in Recall memory, repo docs, skill/plugin instructions, provider config, or current chat only; when planning memory cleanup; when detecting stale, duplicate, conflicting, low-value, source-backed, command, or weak-preference memories; or when applying safe non-destructive hygiene. Use proactively for memory quality policy before using manage-memory for direct ID-based mutation.
0
Stars
0
Forks
8
仓库内 Skill
+0
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/0langa/RECALL/main/plugins/recall/skills/memory-hygiene/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/0langa/RECALL/main/plugins/recall/skills/memory-hygiene/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Memory Hygiene Use this skill as RECALL's policy brain for memory quality. It routes candidate facts to the right durable surface, plans cleanup, and applies only safe non-destructive lifecycle changes. RECALL is local-only project memory. Work in the active project's `.recall/` store, or the legacy `.codex_memory/` store when present. Do not store or repeat secrets, credentials, tokens, private keys, passwords, or sensitive personal data. ## Boundary RECALL exposes seven public skills: - `save-insight`: create new durable memory. - `retrieve-memory`: targeted lookup. - `review-memory`: inspect/audit only. - `manage-memory`: direct lifecycle mutation when IDs/actions are already known
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有