← 返回 Skills 市场
181
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install timeback-machine
功能描述
Provides automated and manual rollback of long-running OpenClaw tasks by saving and restoring state snapshots to handle errors or unexpected issues.
安全使用建议
This skill appears to do exactly what it says: an in-memory rollback helper with a user-confirmation prompt. Before installing: (1) confirm you are obtaining the package from a trusted source/registry; (2) review or control the callbacks you pass as onSaveState/onRestoreState — those functions determine what gets captured/restored and could read or write sensitive data if implemented that way; (3) note the JSON-based deep-clone will not serialize functions, Dates, or non-JSON types — test with representative state; (4) the SKILL.md snippet is slightly malformed and package metadata contains minor author/name placeholders — treat as low-risk but review the package contents locally before running in production.
功能分析
Type: OpenClaw Skill
Name: timeback-machine
Version: 1.0.0
The 'Time Machine' skill is a state management utility designed to provide a rollback mechanism for long-running tasks. The implementation in index.js uses standard JavaScript patterns (setTimeout, JSON-based deep cloning) and interacts with the user via a modal or confirm dialog without any network, filesystem, or sensitive data access. No evidence of malicious intent, obfuscation, or prompt injection was found.
能力评估
Purpose & Capability
Name, description, SKILL.md, and the included index.js align: the skill saves an in-memory snapshot (via configurable onSaveState), starts a timer, prompts the user, and restores via onRestoreState. There are no unrelated requirements (no network, no filesystem, no cloud creds).
Instruction Scope
SKILL.md and index.js limit actions to starting/stopping a timer, storing a snapshot in memory, prompting the user (via OpenClaw UI if available or confirm), and calling provided callbacks to save/restore state. The instructions do not reference arbitrary files, environment variables, or external endpoints.
Install Mechanism
Registry metadata shows no install spec (instruction-only), but SKILL.md contains an example 'npx clawhub install @Cortez_1/time-machine' snippet (the block in SKILL.md appears truncated). No downloadable archives or remote installers are used, so installation risk is low; verify how you obtain the package (official registry vs. third-party).
Credentials
The skill requests no environment variables, no credentials, and no config paths. Its functionality (in-memory snapshots and callbacks) does not require additional secrets or privileged access.
Persistence & Privilege
Flags show normal privileges (always: false, model invocation allowed). The skill does not persist data to disk or modify other skills' configurations; saved state is kept in-memory and cleared on cleanup.
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 timeback-machine - 安装完成后，直接呼叫该 Skill 的名称或使用
/timeback-machine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
v1.0.0
- Major rework: Refactored from a Git-style snapshot/restore tool to a task-level time-reversal “time machine” for OpenClaw.
- Replaced all previous Python scripts with a new Node.js implementation.
- Added automatic and manual rollback features triggered by task duration or user action.
- Introduced state snapshotting at task start, with customizable save/restore logic.
- Simplified API and documentation to focus on integrating time-based rollback for long-running tasks.
元数据
常见问题
timeback-machine 是什么？
Provides automated and manual rollback of long-running OpenClaw tasks by saving and restoring state snapshots to handle errors or unexpected issues. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 181 次。
如何安装 timeback-machine？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install timeback-machine」即可一键安装，无需额外配置。
timeback-machine 是免费的吗？
是的，timeback-machine 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
timeback-machine 支持哪些平台？
timeback-machine 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 timeback-machine？
由 Cortez-1（@cortez-1）开发并维护，当前版本 v1.0.0。
推荐 Skills