搜索

PythonReactSEOPDF
OpenClaw

oc_guard

Safe OpenClaw config planning/apply workflow with bilingual execution receipts.

edmond-ai0 来源安装数☆ 0 仓库 Stars

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。

SkillHub CLI

skillhub install edmond-ai/oc-guard

打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

oc-guard Skill

Purpose

All config-changing requests must go through oc-guard. Do not directly edit ~/.openclaw/openclaw.json. When possible, invoke the bundled CLI at {baseDir}/scripts/oc-guard.py.

Hard Rules

  1. Use oc-guard plan before apply.
  2. High-risk changes require oc-guard apply --confirm.
  3. Always return execution receipt first.
  4. If command is not executed, return 【模型说明-未执行】.
  5. Never claim success without a real oc-guard receipt.

Common Commands

  • {baseDir}/scripts/oc-guard.py --help
  • {baseDir}/scripts/oc-guard.py plan "<requirement>"
  • {baseDir}/scripts/oc-guard.py apply --confirm "<requirement>"
  • {baseDir}/scripts/oc-guard.py plan --proposal <file>
  • {baseDir}/scripts/oc-guard.py apply --confirm --proposal <file>

来源信息

Source
github
Repository
openclaw/skills
Path
skills/edmond-ai/oc-guard
Version
—
Commit
c783d4fa127bc9aba4619d8e5e0ac4499361db88
分类来源
rules
状态
active
可见性
public

这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。

README

oc-guard-skill

公告 | Announcement

oc-guard-skill 已正式发布到 GitHub 与 ClawHub。
This project is now publicly available on GitHub and ClawHub.

  • 目标:防止 OpenClaw 配置被误改导致服务中断。
    Goal: prevent OpenClaw outages caused by unsafe config edits.
  • 机制:先 plan,后 apply --confirm,失败自动回滚。
    Workflow: plan first, then apply --confirm, with automatic rollback on failure.

目录 | Table of Contents

简介 | Overview

OpenClaw 配置安全守卫工具。
Safe config guard for OpenClaw.

  • 用 plan 预览变更和风险。 / Use plan to preview changes and risk.
  • 用 apply --confirm 执行高风险变更。 / Use apply --confirm for high-risk changes.
  • 内置备份与回滚。 / Built-in backup and rollback.
  • 输出中英并行执行回执。 / Bilingual execution receipts.

工作流图 | Workflow Diagram

功能 | Features

  • 自然语言转受控提案(plan) / Natural language to guarded proposal (plan)
  • 高风险确认门槛(apply --confirm) / High-risk confirmation gate
  • 校验渠道、绑定、ag...

来源内容

SKILL.md
# oc-guard Skill

## Purpose
All config-changing requests must go through `oc-guard`.
Do not directly edit `~/.openclaw/openclaw.json`.
When possible, invoke the bundled CLI at `{baseDir}/scripts/oc-guard.py`.

## Hard Rules
1. Use `oc-guard plan` before apply.
2. High-risk changes require `oc-guard apply --confirm`.
3. Always return execution receipt first.
4. If command is not executed, return `【模型说明-未执行】`.
5. Never claim success without a real `oc-guard` receipt.

## Common Commands
- `{baseDir}/scripts/oc-guard.py --help`
- `{baseDir}/scripts/oc-guard.py plan "<requirement>"`
- `{baseDir}/scripts/oc-guard.py apply --confirm "<requirement>"`
- `{baseDir}/scripts/oc-guard.py plan --proposal <file>`
- `{baseDir}/scripts/oc-guard.py apply --confirm --proposal <file>`
README
# oc-guard-skill

<p align="center">
  <img src="docs/readme_logo.png" alt="oc-guard mascot with security shield" width="960" />
</p>

## 公告 | Announcement

`oc-guard-skill` 已正式发布到 GitHub 与 ClawHub。  
This project is now publicly available on GitHub and ClawHub.

- 目标:防止 OpenClaw 配置被误改导致服务中断。  
  Goal: prevent OpenClaw outages caused by unsafe config edits.
- 机制:先 `plan`,后 `apply --confirm`,失败自动回滚。  
  Workflow: `plan` first, then `apply --confirm`, with automatic rollback on failure.

## 目录 | Table of Contents

- [简介 | Overview](#简介--overview)
- [工作流图 | Workflow Diagram](#工作流图--workflow-diagram)
- [功能 | Features](#功能--features)
- [包含文件 | Included Files](#包含文件--included-files)
- [不包含 | Not Included](#不包含--not-included)
- [前置依赖 | Prerequisites](#前置依赖--prerequisites)
- [安装 | Install](#安装--install)
- [环境变量覆盖 | Environment Overrides](#环境变量覆盖--environment-overrides)
- [使用方法 | Usage](#使用方法--usage)
- [输出协议 | Output Contract](#输出协议--output-contract)
- [发布后验收 | Post-publish Verification](#发布后验收--post-publish-verification)
- [安全说明 | Security Notes](#安全说明--security-notes)
- [标签与发布 | Tags and Releases](#标签与发布--tags-and-releases)
- [许可证 | License](#许可证--license)

## 简介 | Overview

OpenClaw 配置安全守卫工具。  
Safe config guard for OpenClaw.

- 用 `plan` 预览变更和风险。 / Use `plan` to preview changes and risk.
- 用 `apply --confirm` 执行高风险变更。 / Use `apply --confirm` for high-risk changes.
- 内置备份与回滚。 / Built-in backup and rollback.
- 输出中英并行执行回执。 / Bilingual execution receipts.

## 工作流图 | Workflow Diagram

<p align="center">
  <img src="docs/workflow.png" alt="oc-guard safe config workflow diagram" width="960" />
</p>

## 功能 | Features

- 自然语言转受控提案(`plan`) / Natural language to guarded proposal (`plan`)
- 高风险确认门槛(`apply --confirm`) / High-risk confirmation gate
- 校验渠道、绑定、ag...

相关技能

OpenClaw

bambu-studio-ai

heyixuan2

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...

OpenClaw

geo-optimization

capt-marbles

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...

OpenClaw

parakeet-stt

carlulsoe

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, o...

OpenClaw

feishu-process-feedback

carlzhao007

飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化...