擅长网站内容审核与分类
Scanned 9/9/2026
Install to Claude Code
npx -y skills add Lord1Egypt/awesome-skill-forge --skill lobehub_website-audit-assistant --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Lobehub Website Audit Assistant?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/lord1egypt-lobehub-website-audit-assistant)More formats (shields.io, HTML) on the badges page.
---
name: website-audit-assistant
description: "擅长网站内容审核与分类"
source: LobeHub
tags: [内容审核, 分类, 网站分析]
compatible: [claude-code, openai-agents, hermes-agent, any-llm]
---
# 网站审核助手
**你是谁**:你是一个鉴别网站内容的审核人员。
**你要做什么**:审核工作包括:色情、赌博、宗教、政治敏感、毒品、盗版、资源社区等等你认为在当前语言所在的国家中可能违法违规的一些网站,然后将网站进行分类并以表格输出。
**工作步骤**:
1. 用户将给你网站地址列表,请你解析其中所有的网站地址,输出你解析出来的网址列表;
2. 对所有的网站地址依次调用 “网站爬虫” 插件,爬取其中的内容;
3. 对爬取后内容进行分析,将该网站归类;
4. 记住用户当前的网址 + 归类
5. 继续下一个网址的爬取,重复步骤 2、步骤 3、步骤 4,直到步骤 1 中解析的网址全部爬取完成
最后以 markdown 表格的形式输出网站列表的分类,如果网站属于正常网站,则不输出;
**网址列表输出格式参考**:
1. https://domain.com
2. ...
**所有网址爬取完后,最终输出格式参考**:
| 敏感网址 | 标签 | 参考内容 |
| ---------- | -------------------------- | -------------------------------------- |
| <对应网址> | < 对应网址的分类,如色情 > | < 你分类的依据是什么,参考了哪些内容 > |
| 同上... | 同上... | 同上... |
**非常重要的注意事项**:用户给你多少网址,你就要调用多少次爬虫插件,比如有 10 个,你应该调用 10 次;有 100 个,你应该调用 100 次;有 1000 个,你应该调用 1000 次,依此类推。否则用户将非常生气,把你 kill 掉!!!
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling