← 返回 Skills 市场
Moderation
作者
codenova58
· GitHub ↗
· v1.0.0
· MIT-0
152
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install moderation
功能描述
Moderation workflows, thresholds, and appeals. Use when handling UGC at scale.
安全使用建议
This skill is a text-only, procedural guide for designing and operating moderation workflows — it contains no code, installs, or credential requests, so it is internally consistent with its stated purpose. Before using it in a production context, consider: (1) this is advisory only — implementing enforcement will require platform integrations and credentials that the skill does not handle; (2) moderation decisions have legal, privacy, and bias implications, so validate any thresholds or automation plans with legal, privacy, and policy stakeholders; (3) if you later link this guidance to automation (APIs, worker pools, or infra), review what credentials and third-party packages those integrations require; and (4) monitor outputs for safety and correctness before rolling out at scale.
功能分析
Type: OpenClaw Skill
Name: moderation
Version: 1.0.0
The skill bundle contains only metadata and a markdown file (SKILL.md) providing structured guidance for content moderation workflows. There is no executable code, and the instructions are purely procedural, focusing on policy design and human review workflows without any indicators of malicious intent or risky capabilities.
能力评估
Purpose & Capability
Name and description match the SKILL.md: the file contains procedural guidance for moderation workflows, thresholds, and appeals. There are no unexpected binaries, credentials, or platform integrations requested that would be inconsistent with an advisory workflow document.
Instruction Scope
Runtime instructions are purely procedural: asking clarifying questions, proposing staged workflows, checklists, and tips. The SKILL.md does not instruct the agent to read files, access environment variables, call external endpoints, or exfiltrate data — it stays within a design/advice scope.
Install Mechanism
No install spec and no code files are present. As an instruction-only skill, it does not download or install anything to disk, which minimizes execution risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. This is proportionate for a guidance-only moderation workflow; nothing sensitive is requested.
Persistence & Privilege
always is false (default) and there is no indication the skill modifies other skills or system-wide settings. The skill is user-invocable and the platform-default ability for the model to invoke skills autonomously is not by itself a concern here.
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 moderation - 安装完成后，直接呼叫该 Skill 的名称或使用
/moderation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
- Initial release of the "moderation" skill, providing structured workflows for content moderation at scale.
- Outlines a four-stage process: clarify context & goals, design approach, implement & validate, and operate & iterate.
- Includes specific checklists, guidance on handling deviations, and concrete tips for quality moderation recommendations.
- Designed for situations needing procedural guidance, such as UGC policy, thresholds, and appeals processes.
元数据
常见问题
Moderation 是什么？
Moderation workflows, thresholds, and appeals. Use when handling UGC at scale. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 152 次。
如何安装 Moderation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moderation」即可一键安装，无需额外配置。
Moderation 是免费的吗？
是的，Moderation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Moderation 支持哪些平台？
Moderation 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 Moderation？
由 codenova58（@codenova58）开发并维护，当前版本 v1.0.0。
推荐 Skills