← 返回 Skills 市场
nicshliu

OpenClaw: memory freshness

作者 NICSHLIU · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
92
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-memory-freshness
功能描述
为 OpenClaw 4.2 记忆搜索结果添加新鲜度警告。当记忆搜索结果返回时自动注入时间戳警告,提示模型验证旧记忆。当用户提到记忆过时、记忆不准确、记忆过期、或要求添加记忆新鲜度提醒时触发。
安全使用建议
This skill is coherent with its goal, but be aware of what it asks you to do: 1) It recommends editing your global OpenClaw system prompt (~/.openclaw/openclaw.json) — that change affects all agents, so back up the file before editing and review the new prompt for unintended instructions. 2) It suggests adding timestamps to memory files and running local commands (grep/rg) to verify memory contents; those verification steps will cause the agent or you to read local files referenced by memories—ensure you are comfortable with that access and that the referenced paths are safe to inspect. 3) The instructions assume grep or ripgrep (rg) are available; if not, install or adapt the verification commands. If you want stricter safety, apply the changes in a test environment first and limit which memories or agents use the new prompt.
功能分析
Type: OpenClaw Skill Name: openclaw-memory-freshness Version: 1.0.0 The skill bundle consists of documentation and instructions (SKILL.md) designed to help an AI agent manage stale memory entries by implementing 'freshness' warnings and verification steps. It suggests using standard search tools like grep and rg to validate old information and proposes configuration changes to openclaw.json, all of which are aligned with the stated purpose and show no signs of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The name/description (memory freshness warnings) align with the instructions: injecting rules into the system prompt, stamping memories with timestamps, and adding freshness annotations to search results are reasonable and expected for this purpose. No unrelated credentials, binaries, or network access are requested.
Instruction Scope
SKILL.md explicitly tells operators/agents to edit ~/.openclaw/openclaw.json, to add timestamps to memory files on write, and to run local verification commands (grep/rg) when using memory that points at files/functions. This is within the feature scope, but it does require the agent/user to perform file edits and local shell operations — ensure you understand the implications (see guidance).
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is downloaded or written by an installer — lowest-risk install footprint.
Credentials
The skill declares no required environment variables, credentials, or config paths. The guidance to edit ~/.openclaw/openclaw.json is a behavioral recommendation rather than a hidden requirement, so requested access is proportional to the stated purpose.
Persistence & Privilege
always is false and disable-model-invocation is not set — normal. The skill does not request persistent elevated privileges or modifications to other skills' configurations. It suggests modifying the agent/system prompt (user action), which is expected for global behavior changes.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install openclaw-memory-freshness
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /openclaw-memory-freshness 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: optimize OpenClaw 4.2 memory search + compact + freshness + trust validation
元数据
Slug openclaw-memory-freshness
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

OpenClaw: memory freshness 是什么?

为 OpenClaw 4.2 记忆搜索结果添加新鲜度警告。当记忆搜索结果返回时自动注入时间戳警告,提示模型验证旧记忆。当用户提到记忆过时、记忆不准确、记忆过期、或要求添加记忆新鲜度提醒时触发。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 92 次。

如何安装 OpenClaw: memory freshness?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-memory-freshness」即可一键安装,无需额外配置。

OpenClaw: memory freshness 是免费的吗?

是的,OpenClaw: memory freshness 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

OpenClaw: memory freshness 支持哪些平台?

OpenClaw: memory freshness 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 OpenClaw: memory freshness?

由 NICSHLIU(@nicshliu)开发并维护,当前版本 v1.0.0。

💬 留言讨论