Borrowing it
Nothing to install: this file belongs to ThreeFish-AI/negentropy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ThreeFish-AI/negentropy/master/.agent/skills/web-translator/SKILL.mdgit clone --depth 1 https://github.com/ThreeFish-AI/negentropyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/threefish-ai/negentropy/web-translator)<a href="https://agentmods.dev/skills/threefish-ai/negentropy/web-translator"><img src="https://agentmods.dev/badge/skills/threefish-ai/negentropy/web-translator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.01367 |
| Opus 5 | $0.00017 | $0.00683 |
| Sonnet 5 | $0.00007 | $0.00273 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
web-translator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Translator (Web Content Extractor)
专门处理网页内容的提取和转换,将网页内容转换为标准的 Markdown 格式,保持原有的结构和格式。
核心功能
1. 内容提取
- 主要内容提取:识别并提取文章正文
- 结构保持:维护标题层级、段落结构
- 媒体资源:提取图片、视频等媒体信息
- 交互元素:保存链接、按钮等交互信息
2. 格式转换
- HTML to Markdown:转换为标准 Markdown 语法
- 表格处理:将 HTML 表格转换为 Markdown 表格
- 列表转换:保持有序和无序列表结构
- 链接处理:正确转换内部和外部链接
Workflow
1. 内容获取
使用适当的工具:
data-extractor.convert_webpage_to_markdown- 主要工具web-reader.webReader- 备用方案
2. 内容解析
- 识别文档结构(标题、段落、列表等)
- 提取元数据(标题、作者、发布时间等)
- 定位媒体资源
- 解析导航和侧边栏
3. 内容清理
- 移除广告和无关内容
- 清理脚本和样式
- 简化复杂的 HTML 结构
- 优化可读性
4. 格式转换
- 应用 Markdown 语法规则
- 保持视觉层次结构
- 处理特殊元素(表格、代码块)
- 生成干净的 Markdown
提取配置
基本配置
extract_main_content: true # 提取主要内容
include_metadata: true # 包含元数据
embed_images: false # 图片保存为独立文件
extract_links: true # 提取链接信息
preserve_formatting: true # 保持格式
高级选项
- 选择性提取:指定 CSS 选择器
- 深度控制:控制链接追踪深度
- 媒体过滤:筛选特定类型的媒体
输入格式
单个 URL
https://example.com/article
多个 URL
- https://example.com/doc1
- https://example.com/doc2
- https://example.com/doc3
本地 HTML 文件
/path/to/local/file.html
输出格式
Markdown 内容
# 文章标题
**作者**: Author Name
**发布时间**: 2025-01-01
**来源**: Example Website
## 摘要
文章摘要内容...
## 正文内容
### 1. 章节标题
章节内容段落...

| 表格标题 |
| -------- |
| 内容 |
- 列表项 1
- 列表项 2
- 列表项 3
[相关链接](https://example.com)
元数据
{
"title": "文章标题",
"author": "Author Name",
"publish_date": "2025-01-01",
"source": "Example Website",
"url": "https://example.com/article",
"word_count": 1500,
"reading_time": "5 min"
}
资源列表
{
"images": [
{
"src": "https://example.com/image1.jpg",
"alt": "图片描述",
"local_path": "images/article/image1.jpg"
}
],
"links": [
{
"text": "链接文本",
"url": "https://example.com/link",
"type": "external"
}
]
}
使用方法
基本提取
提取这个网页的内容:https://example.com/article
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 261 lines · 35 tokens per session scan A e8bf1fcd856e
web-translator is a skill published in the GitHub repository ThreeFish-AI/negentropy (10 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,367 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
security-ownership-map
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
deeprefine
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
deeprefine
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
deeprefine
Claude Code adapter for the DeepRefine agent-native refinement loop. Use when the user invokes /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.