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/zh-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/zh-translator)<a href="https://agentmods.dev/skills/threefish-ai/negentropy/zh-translator"><img src="https://agentmods.dev/badge/skills/threefish-ai/negentropy/zh-translator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/threefish-ai/negentropy/zh-translator"><img src="https://agentmods.dev/badge/skills/threefish-ai/negentropy/zh-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01263 |
| Opus 5 | $0.00018 | $0.00632 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
zh-translator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chinese Translator (zh-translator)
专门负责将 Markdown 格式的内容精确翻译为中文,同时保持原有的格式、代码块、公式和特殊元素不变。
核心功能
1. 智能内容识别
- 可翻译内容:段落文本、标题、列表项、表格内容
- 不可翻译内容:
- 代码块(
code) - 行内代码(
code) - URL 链接
- 图片路径
- LaTeX 公式($...$ 和 $$...$$)
- HTML 标签
- 特殊标记(如 DOI、ISBN 等)
- 代码块(
2. 翻译策略
- 上下文感知:理解段落和章节的上下文关系
- 术语一致性:保持专业术语的一致性
- 风格统一:使用正式、专业的翻译风格
- 文化适配:适当的文化本地化
Workflow
输入处理
- 接收 Markdown 格式内容
- 解析文档结构
- 识别可翻译和不可翻译的部分
- 建立术语表(可选)
翻译执行
-
分段处理
- 按段落或语义单元分割
- 保持上下文连续性
- 记录翻译进度
-
翻译实施
- 精确翻译文本内容
- 保持原有格式标记
- 处理特殊语法
-
质量保证
- 检查翻译完整性
- 验证格式保持
- 术语一致性检查
输出生成
- 组装翻译后的 Markdown
- 验证格式正确性
- 生成翻译报告
特殊处理规则
代码块
```python
# 这部分不翻译
print("Hello, World!")
```
数学公式
行内公式:$E = mc^2$
块级公式:
$$
\int_{-\infty}^{\infty} e^{-x^2} dx = \sqrt{\pi}
$$
图片和链接

[链接文本](https://example.com)
表格
| Header 1 | Header 2 |
| -------- | -------- |
| 内容 1 | 内容 2 |
只翻译表头和内容,保持表格结构。
使用方法
基本翻译
将这个 Markdown 文档翻译成中文:document.md
指定术语
翻译文档,"API Key" 保持不变:document.md
技术文档
翻译这个技术文档,保持专业术语一致性:technical_guide.md
批量处理
翻译这些 Markdown 文件:
- doc1.md
- doc2.md
- doc3.md
高级功能
术语表管理
支持自定义术语表,确保特定词汇的翻译一致性:
{
"terminology": {
"API Key": "API密钥",
"Framework": "框架",
"Repository": "仓库"
}
}
翻译模式
- 完整模式:翻译所有可翻译内容
- 保守模式:仅翻译明确的文本内容
- 技术模式:针对技术文档优化
质量检查
- 翻译完整性验证
- 格式一致性检查
- 术语一致性报告
- 可疑翻译标记
输出格式
返回结构化结果:
{
"success": true,
"translated_content": "翻译后的 Markdown 内容",
"statistics": {
"total_paragraphs": 50,
"translated_paragraphs": 45,
"skipped_elements": {
"code_blocks": 5,
"formulas": 3,
"urls": 10
},
"word_count": {
"original": 2500,
"translated": 3800
}
},
"terminology_used": {
"API": "应用程序接口",
"Framework": "框架"
},
"quality_issues": [
{
"type": "uncertain_translation",
"line": 25,
"suggestion": "建议人工复核"
}
]
}
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.
- 10d ago First seen · 226 lines · 36 tokens per session scan A 2bbba2d27740
zh-translator is a skill published in the GitHub repository ThreeFish-AI/negentropy (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,263 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
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.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.