← 返回 Skills 市场
139
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install moark-text-moderations
功能描述
Perform text review on user-specified input text that may be inappropriate or offensive.
安全使用建议
This skill appears to do exactly what it says: call Gitee's moderation API with your GITEEAI_API_KEY and return the result. Before installing: (1) Only provide a Gitee AI API key you control — prefer a restricted or test key rather than a high-privilege production key. (2) Be aware the script prints the input text to stdout (so don't send highly sensitive PII). (3) The skill's source and homepage are unknown — if you need stronger assurance, review the script yourself (it's short) or obtain the skill from a known/trusted publisher. (4) The instructions ask you to pip install 'openai' and use the OpenAI-compatible client pointed at ai.gitee.com; this is normal for services exposing an OpenAI-compatible API but double-check network access policies if you're in a restricted environment.
功能分析
Type: OpenClaw Skill
Name: moark-text-moderations
Version: 1.0.0
The skill is a straightforward implementation for performing text moderation using the Gitee AI API. The Python script (perform_text_moderation.py) uses the standard OpenAI library to send user-provided text to a legitimate endpoint (ai.gitee.com) and outputs the results. There is no evidence of data exfiltration, malicious command execution, or harmful instructions in the SKILL.md file.
能力评估
Purpose & Capability
Name/description (text moderation) match the code and runtime instructions. The script calls a moderation endpoint at https://ai.gitee.com/v1 and uses model 'moark-text-moderation'. The single requested env var (GITEEAI_API_KEY) is appropriate for that purpose.
Instruction Scope
SKILL.md instructions are narrowly scoped: install the 'openai' Python package and run the bundled script, then parse the output line starting with 'MODERATION_RESULT:'. Minor oddities: SKILL.md asks to display results using a markdown 'image syntax' snippet (`🛡️[Moderation Result]`) which is unusual but not a security issue. The instructions do print the submitted input text to stdout (expected for debugging) — avoid sending sensitive PII to this skill if you don't want it logged or transmitted.
Install Mechanism
There is no install spec; this is instruction-only with a small bundled script. Dependencies are the standard 'openai' Python package (the script documents this), which is proportionate to the task.
Credentials
Only GITEEAI_API_KEY is required and declared as primaryEnv. No unrelated credentials, config paths, or excessive environment access are requested.
Persistence & Privilege
The skill does not request 'always: true', does not modify other skills or global agent settings, and does not demand persistent system-level privileges.
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 moark-text-moderations - 安装完成后，直接呼叫该 Skill 的名称或使用
/moark-text-moderations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 moark-text-moderations.
- Provides text moderation by reviewing user-specified input for inappropriate or offensive content using GITEE AI API.
- Requires the environment variable GITEEAI_API_KEY; prompts user if missing.
- Usage via command-line script with user input and API key.
- Extracts and displays moderation results in a clear markdown format with a summary.
- Follows a strict workflow for consistent parsing and presentation of moderation results.
元数据
常见问题
Moark Text Moderations 是什么？
Perform text review on user-specified input text that may be inappropriate or offensive. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 139 次。
如何安装 Moark Text Moderations？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moark-text-moderations」即可一键安装，无需额外配置。
Moark Text Moderations 是免费的吗？
是的，Moark Text Moderations 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Moark Text Moderations 支持哪些平台？
Moark Text Moderations 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 Moark Text Moderations？
由 fchange（@fchange）开发并维护，当前版本 v1.0.0。
推荐 Skills