← 返回 Skills 市场
achals-iglu

Remember Me

作者 Achal Singhal · GitHub ↗ · v0.1.2
cross-platform ✓ 安全检测通过
1303
总下载
6
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install remember-me
功能描述
Build and maintain human-centered user understanding through structured notes, preference tracking, and behavioral context. Use when the user asks to remember things, understand them better over time, personalize responses, or keep ongoing notes about goals, habits, tone, boundaries, and recurring concerns.
安全使用建议
This skill appears to do what it says: classify and persist user preferences/goals and use them to personalize responses. Before installing, verify where the agent will store memory files (the SKILL.md references memory/YYYY-MM-DD.md and MEMORY.md) and ensure that location meets your privacy requirements. Confirm that the agent enforces the 'Explicit Exclusions' (no raw conversation logs, no sensitive identity attributes without consent) and that it provides an easy way to list, export, and delete stored memories. Also check for any missing referenced files (promotion-checklist.md and profile-schema.md are cited but not included) and ask the skill owner how they are implemented. If you share the environment with others or need strict data isolation, delay enabling long-term memory until you understand the storage and access controls.
功能分析
Type: OpenClaw Skill Name: remember-me Version: 0.1.2 The OpenClaw skill 'remember-me' is designed for an AI agent to manage user preferences, goals, and context over time. The `SKILL.md` provides detailed instructions for memory capture, storage (local markdown files like `memory/YYYY-MM-DD.md` and `MEMORY.md`), retrieval, and maintenance. It explicitly includes privacy-preserving rules, such as preferring explicit consent for sensitive details and not storing certain types of information. There are no instructions for arbitrary command execution, network communication, data exfiltration, or accessing sensitive system files. All file operations are confined to expected local directories, and the templates in `references/templates.md` are purely structural. No evidence of malicious intent or significant vulnerabilities was found.
能力评估
Purpose & Capability
The skill's name/description (user memory, preferences, goals) aligns with the instructions (classify signals, append daily notes, promote to long-term memory). It requests no credentials, binaries, or installs, which is appropriate. Minor inconsistency: the SKILL.md expects the agent to write/read files (memory/YYYY-MM-DD.md, MEMORY.md and references/*), but the skill metadata lists no required config paths—confirm where the platform will store these files and whether that location is acceptable.
Instruction Scope
Instructions explicitly direct the agent to collect, classify, and persist user-related data (daily and long-term notes), and to read memory when answering. This is coherent with the purpose. The doc also forbids storing sensitive attributes and raw logs and prescribes consent/confirmation steps, which reduces risk. Ensure the agent's implementation actually honors those exclusions and that probes/check-ins are limited as described.
Install Mechanism
There is no install spec and no code files to execute; this is instruction-only, which is the lowest install risk. Nothing is downloaded or written by an installer according to the metadata.
Credentials
The skill requests no environment variables, credentials, or external service tokens—proportional to a local memory manager. There are no surprising credential asks.
Persistence & Privilege
The skill is not marked always:true and does not request elevated privileges, but the instructions rely on persistent storage (creating and reading memory files). That persistence is expected for a memory skill, but you should verify storage location, retention policy, access controls, and deletion behavior on the host/agent before enabling long-term memory.
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 remember-me
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /remember-me 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
v0.1.2
- Updated the description to clarify the "remember-this" trigger and expanded on memory use cases (preferences, goals, boundaries, prior work, decisions, dates, and todos). - No substantial changes to functionality or rules in the skill documentation.
v0.1.1
Forgot references
v0.1.0
Initial release of remember-me skill: establishes a structured, privacy-conscious user memory model. - Adds rule-based tagging for memory entries (FACT, PREFERENCE, GOAL, HYPOTHESIS). - Defines capture triggers and multi-tier memory storage (daily notes vs long-term profile). - Introduces workflows for classification, hypothesis generation, promotion, forgetting, and validation. - Implements explicit consent and exclusion policies for sensitive or transient information. - Establishes retrieval and personalization contracts for adapting responses. - Provides heuristics for memory impact, reinforcement, and confidence decay.
元数据
Slug remember-me
版本 0.1.2
许可证
累计安装 3
当前安装数 3
历史版本数 3
常见问题

Remember Me 是什么?

Build and maintain human-centered user understanding through structured notes, preference tracking, and behavioral context. Use when the user asks to remember things, understand them better over time, personalize responses, or keep ongoing notes about goals, habits, tone, boundaries, and recurring concerns. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1303 次。

如何安装 Remember Me?

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

Remember Me 是免费的吗?

是的,Remember Me 完全免费(开源免费),可自由下载、安装和使用。

Remember Me 支持哪些平台?

Remember Me 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 Remember Me?

由 Achal Singhal(@achals-iglu)开发并维护,当前版本 v0.1.2。

💬 留言讨论