← 返回 Skills 市场
327
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install wal-memory
功能描述
Session crash and compaction recovery using a two-file WAL (Write-Ahead Log) system. Use when setting up persistent memory for an OpenClaw agent that needs t...
安全使用建议
This skill appears to do exactly what it claims: append timestamped local log entries for session recovery. Before installing: (1) Only run the script from a trusted source — the package metadata has no homepage and a single owner ID, so verify the file if you care about provenance. (2) Do not log passwords, API keys, or other secrets — the log file is plaintext and the README explicitly warns about this. (3) Add ~/clawd/STATE.log to .gitignore as recommended and restrict file permissions (e.g., chmod 600) or consider encrypting the logfile if you will store sensitive operational details. (4) Consider a retention/rotation policy beyond simple rename for long-term storage and ensure backups (if any) are secure.
功能分析
Type: OpenClaw Skill
Name: wal-memory
Version: 1.0.2
The skill provides a write-ahead log (WAL) system for agent memory persistence, which is a legitimate and useful function. The `state-log.js` script simply appends timestamped messages to a local file (`STATE.log`) and performs basic log rotation, without any network calls, `eval`/`exec` of untrusted input, or access to sensitive system resources. The `SKILL.md` instructions are clear, guide the agent to set up the logging system, and explicitly warn against logging sensitive data and recommend adding `STATE.log` to `.gitignore`, demonstrating security awareness. There is no evidence of malicious intent, data exfiltration, unauthorized execution, or prompt injection designed to harm the agent or system.
能力评估
Purpose & Capability
Name/description (WAL memory for session recovery) aligns with the delivered artifacts: a small Node script that appends timestamped entries to ~/clawd/STATE.log and a GOALS template. No unrelated binaries, env vars, or services are requested.
Instruction Scope
SKILL.md directs local operations only: copying script to ~/clawd/scripts, creating ~/clawd/memory/GOALS.md, reading/tailing local STATE.log and memory files, and adding heartbeat logging. These actions match the stated recovery workflow and do not instruct reading unrelated system state or contacting external endpoints.
Install Mechanism
No install spec; this is instruction-only with one small JS script (no downloads or external packages). The only runtime requirement is Node.js being on PATH, which is consistent with the script.
Credentials
The skill does not request environment variables, credentials, or config paths. The only implicit requirement is write access to ~/clawd/STATE.log when the script is installed and run, which is reasonable for a local logger.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent platform privileges, modify other skills, or alter system-wide agent settings. Its persistence is limited to creating/rotating a local log file.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install wal-memory - 安装完成后,直接呼叫该 Skill 的名称或使用
/wal-memory触发 - 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
v1.0.2
**wal-memory 1.0.2 Changelog**
- Added metadata specifying Node.js as a requirement.
- Updated guidance: instructs users to add `STATE.log` to `.gitignore` to prevent committing sensitive data.
- Added explicit warning never to log secrets, passwords, or sensitive tokens in `STATE.log`.
- No code changes; documentation updated for clarity and security.
v1.0.0
Initial release. Two-file WAL recovery system co-designed with Gemini.
元数据
常见问题
WAL Memory 是什么?
Session crash and compaction recovery using a two-file WAL (Write-Ahead Log) system. Use when setting up persistent memory for an OpenClaw agent that needs t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 327 次。
如何安装 WAL Memory?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wal-memory」即可一键安装,无需额外配置。
WAL Memory 是免费的吗?
是的,WAL Memory 完全免费(开源免费),可自由下载、安装和使用。
WAL Memory 支持哪些平台?
WAL Memory 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 WAL Memory?
由 maikunari(@maikunari)开发并维护,当前版本 v1.0.2。
推荐 Skills